LinkedIn Profile and Job Scraper
效率与工作流编辑精选by stickerdaniel
LinkedIn Profile and Job Scraper 是让 Claude 直接抓取 LinkedIn 个人资料、公司信息和职位详情的工具。
这个服务器解决了招聘和商业调研中手动复制粘贴 LinkedIn 数据的痛点,适合猎头或市场分析师快速获取候选人背景和公司动态。不过,LinkedIn 反爬机制频繁更新,数据稳定性需要持续维护,使用时建议搭配人工验证。
什么是 LinkedIn Profile and Job Scraper?
LinkedIn Profile and Job Scraper 是让 Claude 直接抓取 LinkedIn 个人资料、公司信息和职位详情的工具。
README
MCP Server for LinkedIn
<!-- mcp-name: io.github.stickerdaniel/linkedin-mcp-server --> <p align="left"> <a href="https://pypi.org/project/mcp-server-linkedin/" target="_blank"><img src="https://img.shields.io/pypi/v/mcp-server-linkedin?color=blue" alt="PyPI"></a> <a href="https://github.com/stickerdaniel/linkedin-mcp-server/actions/workflows/ci.yml" target="_blank"><img src="https://github.com/stickerdaniel/linkedin-mcp-server/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI Status"></a> <a href="https://github.com/stickerdaniel/linkedin-mcp-server/actions/workflows/release.yml" target="_blank"><img src="https://github.com/stickerdaniel/linkedin-mcp-server/actions/workflows/release.yml/badge.svg?branch=main" alt="Release"></a> <a href="https://github.com/stickerdaniel/linkedin-mcp-server/blob/main/LICENSE" target="_blank"><img src="https://img.shields.io/badge/License-Apache%202.0-%233fb950?labelColor=32383f" alt="License"></a> </p>Give your AI agents access to LinkedIn through your own browser session. Read profiles, research companies, find jobs, and manage conversations and connection requests.
<br/> <details open> <summary><strong>LinkedIn MCP Sponsor</strong></summary> <br/> <a href="https://golink.onl/linkupapi-banner" target="_blank"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/df9f3784-4db3-4a30-a908-ca9aae32f54c"> <img src="https://github.com/user-attachments/assets/e3a019f0-0dbe-4b91-8e41-684d5ea69893" alt="LinkupAPI, the outreach API for your AI agents" width="100%"> </picture> </a>Independent open-source project. Not affiliated with LinkedIn or Microsoft. LinkedIn is a trademark of LinkedIn Corporation.
<br/> <a href="https://golink.onl/cadenza-banner" target="_blank"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/e7dc04a7-4b2c-4f8f-bffa-77895f02a9b4"> <img src="https://github.com/user-attachments/assets/8b8ffaf4-ac80-4943-bb14-88562d636a35" alt="Cadenza, hosted LinkedIn MCP for your AI assistant" width="100%"> </picture> </a>Running LinkedIn agents in production? LinkupAPI is the hosted outreach API built for scale, across LinkedIn Classic, Sales Navigator, and Recruiter, plus email, WhatsApp, and iMessage.
Cadenza is the single hosted MCP server for all your LinkedIn needs. It covers Classic, Sales Navigator, and Recruiter with 100+ actions, each within limits you set. Works on web, desktop, and mobile.
Use code <strong>FOUNDING20</strong> for 20% off your first year. <a href="https://golink.onl/cadenza-cta">Try Cadenza →</a>
<br/> <a href="https://golink.onl/unipile-banner" target="_blank"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/c2e7f3b4-6812-4f28-8728-10f882a44e0e"> <img src="https://github.com/user-attachments/assets/89ab8932-ae79-41c2-8416-a699e924218b" alt="Unipile, one API for every LinkedIn feature" width="100%"> </picture> </a><br/> <a href="https://zernio.link/sticker-daniel-banner" target="_blank"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/f8b34875-c2b7-4466-b430-51fda4875720"> <img src="https://github.com/user-attachments/assets/ef30cb05-80a7-4b03-a9d4-186c6db2fe43" alt="Zernio, official APIs for every social channel" width="100%"> </picture> </a>This MCP server is supported by Unipile. Unipile is the fully managed cloud option for developers: a hosted LinkedIn API for Classic, Sales Navigator, and Recruiter that handles auth, sessions, and infrastructure for you.
</details>Zernio gives your agents official APIs for every social channel. Post, reply, and run ads on Instagram, TikTok, X, YouTube, Threads, and more, through one API or MCP server.
<a id="installation-methods"></a>
Installation Methods - LinkedIn MCP Server
| Tool | Description |
|---|---|
get_person_profile | Read profile sections: experience, education, skills, projects, volunteering, posts. |
get_my_profile | Read your own profile, with the same section selection as other profiles. |
connect_with_person | Send a connection request with an optional note, or accept an incoming one. |
get_sidebar_profiles | Find recommended profile links, including people you may know. |
get_inbox | List recent inbox conversations, with links to open individual threads. |
get_conversation | Read a conversation's messages using a LinkedIn username or thread ID. |
search_conversations | Search messages by keyword and return links to matching conversation threads. |
archive_conversation | Archive a conversation by thread ID; a repeat call reports it already archived. |
send_message | Message a profile after confirmation. Threads use reply_to_conversation. |
reply_to_conversation | Reply inside an existing thread or InMail by thread ID. Sends after confirmation. |
get_company_profile | Read company information, with optional sections for posts and open jobs. |
get_company_posts | Read recent posts from a company's feed, with links to the original posts. |
search_companies | Find companies by keyword and return links to their LinkedIn profiles. |
get_company_employees | Find company employees, optionally filtered by name, title, or skill. |
search_jobs | Find job postings by keyword and location, with job IDs for reading details. |
get_saved_jobs | List your saved job postings, with job IDs for looking up their details. |
dismiss_job | Dismiss a job from job search so later searches no longer show it. Irreversible. |
search_people | Find people by keyword, location, degree, company, and mutual connections. |
get_job_details | Read a job posting's description, requirements, and company details. |
get_job_apply_url | Check whether a job uses Easy Apply or links to an employer's application. |
get_easy_apply_form | Read an Easy Apply form's fields, options and prefilled values. Never submits. |
get_feed | Read recent posts from your home feed, with links to the original posts. |
search_posts | Search posts by keyword, optionally filtered by recency or content type. |
get_session_status | Check your saved login and browser state without opening a browser. |
close_session | Close the shared browser session without deleting your saved login. |
Setup with uvx (Recommended)
Prerequisites: Install uv.
Installation
Add to your MCP client's mcpServers configuration
{
"mcpServers": {
"mcp-server-linkedin": {
"command": "uvx",
"args": ["mcp-server-linkedin@latest"],
"env": { "UV_HTTP_TIMEOUT": "300" }
}
}
}
The @latest tag turns on automatic updates, which keep the server working with LinkedIn's current page structure. The server starts quickly and prepares the shared Patchright Chromium browser cache in the background under ~/.linkedin-mcp/patchright-browsers. On the first tool call that needs authentication, it reuses a LinkedIn session from a signed-in local browser if it finds one, and otherwise opens a LinkedIn login browser window.
AI agent? Get a quick confirmation from the user before enabling automatic updates.
[!NOTE] Early tool calls may return a setup/authentication-in-progress error until browser setup or login finishes. If you prefer to create a session explicitly, run
uvx mcp-server-linkedin@latest --login.
Setup Help
<details> <summary><b>🔧 Configuration</b></summary> <details> <summary>Transport modes</summary>- Default (stdio): Standard communication for local MCP servers
- Streamable HTTP: For a web-based MCP server
- If no transport is specified, the server defaults to
stdio - An interactive terminal without explicit transport shows a chooser prompt
Session:
--login- Open a browser to sign in and save the session--import-from-browser [BROWSER]- Reuse a session from a locally signed-in Chromium browser (chrome,chromium,brave,edge,arc,vivaldi,helium,yandex,whale,coccoc,opera,opera_gx,auto). Bare flag picksauto, the most recently used browser with a live LinkedIn session.--auto-import/--no-auto-import- Import a session from a signed-in local browser on the first tool call that needs one, before falling back to manual login (default: on). Skipped in Docker, behind a proxy, and on a non-loopback HTTP bind. On macOS the keychain may prompt once.--logout- Clear the stored session--login-viewer- Docker only: show the--loginbrowser at a token-protected URL on port 6080 (see Authentication)--user-data-dir PATH- Browser profile directory (default: ~/.linkedin-mcp/profile). Rotating or clearing a session deletes this directory and its parent, which holds the stored cookies and derived profiles.--claim-profile-root- Take over a profile directory the server will not claim on its own, such as one whose parent already holds other files. Needed once per directory.
Transport:
--transport {stdio,streamable-http}- Force the transport mode (default: stdio)--host HOST/--port PORT/--path PATH- HTTP server address (defaults: 127.0.0.1, 8000, /mcp)--http-token-file PATH- RequireAuthorization: Bearer <token>from HTTP clients, with the token read from this file (one trailing newline ignored, at least 32 characters). A file whose permission bits grant group or other access is refused (chmod 600). ACLs are not read, so on macOS also remove ACL entries (chmod -N <file>, check withls -le). Windows does not check its permissions, so keep it in a folder only your account can read, or use the environment variable. Required for a--hostother than loopback. Environment:LINKEDIN_MCP_HTTP_TOKEN; the file wins when both are set.
Timeouts:
--timeout MS- Timeout for a single page operation (default: 5000)--tool-timeout SECONDS- Timeout for a whole tool call (default: 180). Raise it for calls that read many pages, slow networks, or a cold-start browser.--login-timeout SECONDS- How long the login browser waits for you to finish signing in (default: 1800; 0 = no limit).--login-viewerends the session after 30 minutes either way.--login-inline-wait SECONDS- How long a tool call waits for a login to finish before telling the model to retry (default: 25, max 45; 0 = return at once)
Shared browser:
--browser-wait SECONDS- How long to wait for another server process to hand over the shared browser (default: 25, max 45; 0 = report busy at once). Only matters with several MCP clients running at once.--browser-min-hold SECONDS- Shortest time this process keeps the shared browser before handing it over (default: 20). Clamped to 3 seconds below--browser-wait, so raise that one along with it. Higher means fewer browser restarts but longer waits for other clients.--browser-idle-timeout SECONDS- Close an idle browser and release the profile after this long without a tool call (default: 600; 0 = keep it open)
Browser:
--no-headless- Show the browser window (useful for debugging)--chrome-path PATH- Path to a Chrome/Chromium executable--proxy-server URL- Route browser traffic through a proxy, asscheme://host:port. Set it up before--login; see Using a proxy.
Other:
--log-level {DEBUG,INFO,WARNING,ERROR}- Logging level (default: WARNING)
If you are already signed into LinkedIn in Chrome, Chromium, Brave, Edge, Arc, Vivaldi, Helium, Yandex, Naver Whale, Cốc Cốc, Opera, or Opera GX, you can skip the manual --login step and reuse that session:
# Auto-pick the most recently used browser with a live LinkedIn session
uvx mcp-server-linkedin@latest --import-from-browser
# Or target a specific browser
uvx mcp-server-linkedin@latest --import-from-browser brave
This reads the browser's LinkedIn cookies, validates them against your feed, and saves them to ~/.linkedin-mcp/profile/, the same place --login writes to. Notes:
- With several signed-in browsers, the most recently used live LinkedIn session is tried first. If LinkedIn rejects it (revoked or remote-logged-out), the next most recent is tried automatically; the first the server accepts is imported. There is no prompt to pick. Pass a browser name to target one specifically.
- On macOS the OS keychain may prompt to allow access to the browser's Safe Storage. Close the source browser first for the most reliable read.
- Cookies protected by Chrome 127+ app-bound encryption (
v20) cannot be decrypted without OS elevation; in that case use--logininstead. - Imported cookies match a real login's on-disk set. The local server reads them back in full from the saved profile; the Docker bridge narrows to the same minimal auth subset it uses for a normal session.
Basic Usage Examples:
# Run with debug logging
uvx mcp-server-linkedin@latest --log-level DEBUG
HTTP Mode Example (for web-based MCP clients):
uvx mcp-server-linkedin@latest --transport streamable-http --host 127.0.0.1 --port 8080 --path /mcp
Any other --host needs a token: set LINKEDIN_MCP_HTTP_TOKEN or pass --http-token-file (a file only your account can read), and send Authorization: Bearer <token> from the client. The Docker HTTP example under Setup with Docker shows both halves.
Runtime server logs are emitted by FastMCP/Uvicorn.
Tool calls are serialized to protect the shared LinkedIn browser session, both
within one server process and across separate ones. If you run several MCP
clients at once, each starts its own server process, and only one of them uses
the browser at a time; the others wait briefly and take over as soon as it
finishes a call. A client that waits too long gets a "browser is busy" message
and can simply retry. Use --log-level DEBUG to see the wait/acquire/release
logs.
This covers processes on the same machine and in the same runtime. It does not
extend between the host and a Docker container sharing the same
~/.linkedin-mcp directory, so do not run --login or --logout on the host
while a container is running.
Test with mcp inspector:
- Install and run mcp inspector
bunx @modelcontextprotocol/inspector - Click pre-filled token url to open the inspector in your browser
- Select
Streamable HTTPasTransport Type - Set
URLtohttp://localhost:8080/mcp - Connect
- Test tools
- Ensure you have uv installed:
curl -LsSf https://astral.sh/uv/install.sh | sh - Check uv version:
uv --version(should be 0.4.0 or higher) - On first run,
uvxdownloads all Python dependencies. On slow connections, uv's default 30s HTTP timeout may be too short. The recommended config above already setsUV_HTTP_TIMEOUT=300(seconds) to avoid this. - Windows,
DLL load failed while importing _greenlet: move to greenlet 3.5.5 or newer, whose published Windows wheels carry the C++ runtime inside the extension again. A freshuvxrun resolves that on its own; an environment that pins its dependencies needsuv lock --upgrade-package greenlet. Only greenlet 3.3.1 through 3.5.4 needMSVCP140.dll, which neither the python.org installer nor theuv-managed builds carry, and a greenlet built from source can need it at any version. Where the version cannot be moved, the Microsoft Visual C++ Redistributable supplies that DLL. Reported as greenlet#525, fixed in greenlet#526.
- Browser profile is stored at
~/.linkedin-mcp/profile/ - Managed browser downloads are cached at
~/.linkedin-mcp/patchright-browsers/ - The browser cache keeps growing: a server upgrade can bring a new Chromium revision, and Patchright keeps the old one for as long as any installed version still references it.
uvxkeeps one archive per version you have ever run, so every one of them holds such a reference and the old revisions stay. The server logs a warning naming the revisions it is holding and how much space they take. To reclaim it, stop every LinkedIn MCP Server instance, delete~/.linkedin-mcp/patchright-browsers/, and let the next launch download the current browser.
- Make sure you have only one active LinkedIn session at a time
- LinkedIn may require a login confirmation in the LinkedIn mobile app for
--login - LinkedIn may show a captcha challenge during login. Run
uvx mcp-server-linkedin@latest --loginwhich opens a browser where you can solve it manually.
- Page operations failing (elements not found, navigation hangs): increase the browser page-op timeout:
--timeout 10000orTIMEOUT=10000(milliseconds, default 5000). - Entire tool calls timing out (e.g. multi-section profiles, cold-start Chromium, slow containers): increase the per-tool execution timeout:
--tool-timeout 300orTOOL_TIMEOUT=300(seconds, default 180). - First tool call with no session: if a locally logged-in browser has a live LinkedIn session, the server auto-imports it (see
AUTO_IMPORT_FROM_BROWSER/--auto-import) instead of forcing a manual login. On macOS the keychain may prompt once for Safe Storage access. If no importable browser session exists, it falls back to opening a login window and waits up toLOGIN_INLINE_WAITseconds (default 25, max 45;--login-inline-wait) so a quick sign-in resolves in one call. If the wait elapses, the tool returns a pending signal and the model retries in about 30 seconds. Neither the auto-import nor the inline wait applies under Docker or when the server is bound to a non-loopback HTTP host. Create the session on the host with--login, or use the explicit Docker--login --login-viewercommand. - Users on slow connections may need higher values for either.
- If tool calls answer "No valid LinkedIn session is available in Docker" on a machine that is not a container, the runtime was misdetected. This happened on Linux hosts running a Docker daemon for unrelated services. Set
LINKEDIN_MCP_CONTAINER=falseto override the detection;trueforces the opposite.
- If Chrome is installed in a non-standard location, use
--chrome-path /path/to/chrome - Can also set via environment variable:
CHROME_PATH=/path/to/chrome - On macOS and Linux the browser must be at least as new as the one that last opened your profile, and the server refuses the launch otherwise. (Not on Windows: a browser there cannot be asked its version without starting one, so the check is off.) An older browser can silently drop stores a newer one wrote, the saved session among them, and the failure then looks exactly like an expired login. The message names both versions. Going back to the bundled Chromium after running a newer Chrome once is the usual way to meet this; either run the newer browser again, whichever one that was, or run
--login, which moves the stored session aside and signs in fresh with the browser you have.--logoutalso clears it but discards the old session instead of keeping it recoverable, and it asks for confirmation on the terminal, so it is not usable from a server an MCP client started. - Only Chrome, Chromium and Chrome for Testing are compared this way. Forks number themselves differently (Vivaldi is on 7.x, Edge's build number sits far below Chrome's under the same major), so pointing
CHROME_PATHat one turns the check off rather than producing a refusal nothing could satisfy.
Claude Desktop MCP Bundle (formerly DXT)
Prerequisites: Claude Desktop.
Installation
- Download the latest
.mcpbartifact from releases - Click the downloaded
.mcpbfile to install it into Claude Desktop - Call any LinkedIn tool
On startup, the MCP Bundle prepares the shared Patchright Chromium browser cache in the background. On the first tool call that needs authentication, the server reuses a LinkedIn session from a signed-in local browser if it finds one, and otherwise opens a LinkedIn login browser window.
[!NOTE] Early tool calls may return a setup/authentication-in-progress error until browser setup or login finishes. Retry the tool call once the browser download or sign-in completes.
Setup Help
<details> <summary><b>❗ Troubleshooting</b></summary> <details> <summary>First-time setup behavior</summary>- Claude Desktop starts the bundle immediately; browser setup continues in the background
- If the Patchright Chromium browser is still downloading, retry the tool after a short wait
- Managed browser downloads are shared under
~/.linkedin-mcp/patchright-browsers/ - The browser cache keeps growing: Patchright keeps an old Chromium revision for as long as any installed version still references it, so an upgrade can leave both on disk. The server logs a warning naming what it holds. To reclaim the space, stop every LinkedIn MCP Server instance, delete
~/.linkedin-mcp/patchright-browsers/, and let the next launch download the current browser. - Windows, the bundle exits with
DLL load failed while importing _greenlet: install the Microsoft Visual C++ Redistributable, or reinstall a bundle pinning greenlet 3.5.5 or newer, whose published Windows wheels carry the C++ runtime inside the extension again. A bundle pinning greenlet 3.3.1 through 3.5.4 needsMSVCP140.dllfrom that redistributable, which neither the python.org installer nor theuv-managed builds carry, and a greenlet built from source can need it at any version. The server names this itself on startup, and only after checking that the loader cannot produce that DLL. Reported as greenlet#525, fixed in greenlet#526.
- Make sure you have only one active LinkedIn session at a time
- LinkedIn may require a login confirmation in the LinkedIn mobile app for
--login - LinkedIn may show a captcha challenge during login. Run
uvx mcp-server-linkedin@latest --loginwhich opens a browser where you can solve captchas manually. See the uvx setup for prerequisites.
- Page operations failing (elements not found, navigation hangs): increase the browser page-op timeout:
--timeout 10000orTIMEOUT=10000(milliseconds, default 5000). - Entire tool calls timing out (e.g. multi-section profiles, cold-start Chromium, slow containers): increase the per-tool execution timeout:
--tool-timeout 300orTOOL_TIMEOUT=300(seconds, default 180). - First tool call with no session: if a locally logged-in browser has a live LinkedIn session, the server auto-imports it (see
AUTO_IMPORT_FROM_BROWSER/--auto-import) instead of forcing a manual login. On macOS the keychain may prompt once for Safe Storage access. If no importable browser session exists, it falls back to opening a login window and waits up toLOGIN_INLINE_WAITseconds (default 25, max 45;--login-inline-wait) so a quick sign-in resolves in one call. If the wait elapses, the tool returns a pending signal and the model retries in about 30 seconds. Neither the auto-import nor the inline wait applies under Docker or when the server is bound to a non-loopback HTTP host. Create the session on the host with--login, or use the explicit Docker--login --login-viewercommand. - Users on slow connections may need higher values for either.
- Set Chrome executable in the extension's settings to a Chrome, Chromium or Chrome for Testing binary, such as
/usr/bin/google-chrome. Leave it blank to keep the bundled Chromium. It setsCHROME_PATH, described under Custom Chrome path in the uvx setup help. - This is the fix when tool calls refuse to open the profile because a newer browser last opened it: point the setting at that newer browser instead of signing in again.
- If tool calls answer "No valid LinkedIn session is available in Docker" on a machine that is not a container, the runtime was misdetected. This happened on Linux hosts running a Docker daemon for unrelated services. Set
LINKEDIN_MCP_CONTAINER=falseto override the detection;trueforces the opposite.
Codex Plugin
Installation
Run in a terminal
codex plugin marketplace add stickerdaniel/linkedin-mcp-server
codex plugin add linkedin-mcp-server@linkedin-mcp-server
The plugin runs the latest server release. On the first tool call that needs authentication, the server reuses a LinkedIn session from a signed-in local browser or opens a login window.
<br/> <br/>[!NOTE] Early tool calls may return a setup/authentication-in-progress error until browser setup or login finishes. Retry the tool call once the browser download or sign-in completes.
Claude Code Plugin
Prerequisites: Claude Code and uv.
Installation
Run in a terminal
claude plugin marketplace add stickerdaniel/linkedin-mcp-server
claude plugin install linkedin-mcp-server@linkedin-mcp-server
The plugin runs the latest server release. On the first tool call that needs authentication, the server reuses a LinkedIn session from a signed-in local browser or opens a login window.
<br/> <br/>[!NOTE] Early tool calls may return a setup/authentication-in-progress error until browser setup or login finishes. Retry the tool call once the browser download or sign-in completes.
Cursor Plugin
Prerequisites: Cursor and uv on your PATH.
Installation
From the Cursor Marketplace: open Customize in the sidebar, search for LinkedIn MCP, and choose Install. The plugin bundles the LinkedIn skill.
One-click MCP install (server only, without the skill):
Both run the latest server release. On the first tool call that needs authentication, the server reuses a LinkedIn session from a signed-in local browser or opens a login window.
<br/> <br/>[!NOTE] Early tool calls may return a setup/authentication-in-progress error until browser setup or login finishes. Retry the tool call once the browser download or sign-in completes.
Setup with Docker
<details> <summary><strong>I know what I'm doing</strong></summary>Prerequisites: Make sure Docker is installed and running.
Authentication
Log in once. The container opens a LinkedIn login browser that you drive from your own browser tab.
macOS / Linux:
# Create the directory first so the container can save your session into it
mkdir -p ~/.linkedin-mcp
docker run -it --rm \
-v ~/.linkedin-mcp:/home/pwuser/.linkedin-mcp \
-p 127.0.0.1:6080:6080 \
stickerdaniel/linkedin-mcp-server:latest \
--login --login-viewer
PowerShell (Windows):
$sessionDir = Join-Path $env:USERPROFILE ".linkedin-mcp"
New-Item -ItemType Directory -Force -Path $sessionDir | Out-Null
docker run -it --rm `
-v "${sessionDir}:/home/pwuser/.linkedin-mcp" `
-p 127.0.0.1:6080:6080 `
stickerdaniel/linkedin-mcp-server:latest `
--login --login-viewer
Open the full URL the command prints (it carries the access token) and sign in. Ctrl+V (Cmd+V on a Mac) pastes plain ASCII text, such as a password from your password manager, into the login browser. The viewer closes itself afterwards; let the command exit on its own so the session is stored completely. It gives up after 30 minutes.
Keep the same host directory mounted at /home/pwuser/.linkedin-mcp on every later docker run, otherwise the server cannot find the session.
Add to your MCP client's mcpServers configuration
macOS / Linux (absolute path in JSON):
{
"mcpServers": {
"mcp-server-linkedin": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "/absolute/path/to/.linkedin-mcp:/home/pwuser/.linkedin-mcp",
"stickerdaniel/linkedin-mcp-server:latest"
]
}
}
}
Spell that first path out in full. A client runs docker directly rather than through a shell, so a leading ~ reaches Docker unexpanded and it refuses the mount.
PowerShell (Windows): use a forward-slash JSON path. A backslash path like
C:\Users\Alice\.linkedin-mcp fails JSON parsing because \U is an invalid
escape. Use C:/Users/Alice/.linkedin-mcp instead, replacing Alice with your
username.
{
"mcpServers": {
"mcp-server-linkedin": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "C:/Users/Alice/.linkedin-mcp:/home/pwuser/.linkedin-mcp",
"stickerdaniel/linkedin-mcp-server:latest"
]
}
}
}
[!NOTE] In PowerShell,
~is not expanded inside a composite Docker-vargument. UseC:/Users/<you>/.linkedin-mcpor build the path with$env:USERPROFILE\.linkedin-mcpbefore passing it to Docker.
[!NOTE] Sessions expire over time. When tool calls start asking for authentication, repeat the login command above, or run
uvx mcp-server-linkedin@latest --loginon the host.
Setup Help
<details> <summary><b>🔧 Configuration</b></summary> <details> <summary>Transport modes</summary>- Default (stdio): Standard communication for local MCP servers
- Streamable HTTP: For a web-based MCP server
- If no transport is specified, the server defaults to
stdio - An interactive terminal without explicit transport shows a chooser prompt
Session:
--auto-import/--no-auto-import- Import a session from a signed-in local browser on the first tool call that needs one, before falling back to manual login (ignored in Docker). On macOS the keychain may prompt once.--logout- Clear the stored session and every profile derived from it--login-viewer- With--login, show the login browser at a token-protected URL on port 6080. Needs the profile mount from Authentication.--user-data-dir PATH- Browser profile directory (default: ~/.linkedin-mcp/profile). Rotating or clearing a session deletes this directory and its parent, which holds the stored cookies and derived profiles.--claim-profile-root- Take over a profile directory the server will not claim on its own, such as one whose parent already holds other files. Needed once per directory.
Transport:
--transport {stdio,streamable-http}- Force the transport mode (default: stdio)--host HOST/--port PORT/--path PATH- HTTP server address (defaults: 127.0.0.1, 8000, /mcp)--http-token-file PATH- RequireAuthorization: Bearer <token>from HTTP clients, with the token read from this file (one trailing newline ignored, at least 32 characters). A file whose permission bits grant group or other access is refused (chmod 600). ACLs are not read, so on macOS also remove ACL entries (chmod -N <file>, check withls -le). Windows does not check its permissions, so keep it in a folder only your account can read, or use the environment variable. Required for a--hostother than loopback. Environment:LINKEDIN_MCP_HTTP_TOKEN; the file wins when both are set.
Timeouts:
--timeout MS- Timeout for a single page operation (default: 5000)--tool-timeout SECONDS- Timeout for a whole tool call (default: 180). Raise it for calls that read many pages, slow networks, or a cold-start browser.--login-timeout SECONDS- How long the login browser waits for you to finish signing in (default: 1800; 0 = no limit).--login-viewerends the session after 30 minutes either way.--login-inline-wait SECONDS- How long a tool call waits for a login to finish before telling the model to retry (default: 25, max 45; 0 = return at once)
Shared browser:
--browser-wait SECONDS- How long to wait for another server process to hand over the shared browser (default: 25, max 45; 0 = report busy at once). Only matters with several MCP clients running at once.--browser-min-hold SECONDS- Shortest time this process keeps the shared browser before handing it over (default: 20). Clamped to 3 seconds below--browser-wait, so raise that one along with it. Higher means fewer browser restarts but longer waits for other clients.--browser-idle-timeout SECONDS- Close an idle browser and release the profile after this long without a tool call (default: 600; 0 = keep it open)
Browser:
--chrome-path PATH- Path to a Chrome/Chromium executable (rarely needed in Docker)--proxy-server URL- Route browser traffic through a proxy, asscheme://host:port. Set it up before--login; see Using a proxy.
Other:
--log-level {DEBUG,INFO,WARNING,ERROR}- Logging level (default: WARNING)
</details> <details> <summary>HTTP mode</summary>[!NOTE] Plain
--loginstill has no visible window in Docker. Add--login-viewerand publish127.0.0.1:6080:6080only for the one-shot login command. Docker is already headed by default, so--no-headlesschanges nothing. The experimental--daemonis ignored in Docker because its owner can outlive the virtual display.
HTTP Mode Example (for web-based MCP clients):
A server bound beyond loopback requires a bearer token, and --host 0.0.0.0
inside the container is beyond loopback. Generate a token, hand it to the
container, and send it from the client.
Bash / macOS / Linux:
export LINKEDIN_MCP_HTTP_TOKEN="$(openssl rand -hex 32)"
docker run -it --rm \
-v ~/.linkedin-mcp:/home/pwuser/.linkedin-mcp \
-e LINKEDIN_MCP_HTTP_TOKEN \
-p 127.0.0.1:8080:8080 \
stickerdaniel/linkedin-mcp-server:latest \
--transport streamable-http --host 0.0.0.0 --port 8080 --path /mcp
PowerShell (Windows):
$env:LINKEDIN_MCP_HTTP_TOKEN = [guid]::NewGuid().ToString("N") + [guid]::NewGuid().ToString("N")
$sessionDir = Join-Path $env:USERPROFILE ".linkedin-mcp"
docker run -it --rm `
-v "${sessionDir}:/home/pwuser/.linkedin-mcp" `
-e LINKEDIN_MCP_HTTP_TOKEN `
-p 127.0.0.1:8080:8080 `
stickerdaniel/linkedin-mcp-server:latest `
--transport streamable-http --host 0.0.0.0 --port 8080 --path /mcp
-e LINKEDIN_MCP_HTTP_TOKEN without a value copies the variable from your
shell, so the token stays out of the docker run command line. Use the
variable rather than --http-token-file in Docker: a read-only secrets mount
often reports mode 0444, which the file check refuses. The client sends the
token as a header on every request:
{
"mcpServers": {
"mcp-server-linkedin": {
"url": "http://127.0.0.1:8080/mcp",
"headers": { "Authorization": "Bearer <your token>" }
}
}
}
The token is a static header, not an OAuth login, so a client has to support
custom headers. A request without it, or with a different one, gets 401. The
token needs at least 32 characters.
--host 0.0.0.0 and the 127.0.0.1: prefix on -p do different jobs, and
both are needed. --host 0.0.0.0 makes the server reachable inside the
container: a process bound to 127.0.0.1 in there cannot be reached through a
published port at all. The 127.0.0.1: in front of -p limits it outside,
to this machine. Plain HTTP sends the token unencrypted, so reach the server
from another machine through an SSH tunnel or an HTTPS reverse proxy, never by
publishing the port on your network.
Without a token, a bind beyond loopback refuses to start.
LINKEDIN_MCP_ALLOW_UNAUTHENTICATED_HTTP=true starts it anyway, with a
warning. That is unsafe: anyone who can reach the port can use your LinkedIn
session. Use it only when something else restricts the port.
Loopback publishing limits this to the machine, not to the container. Other
containers on the same host can still reach it through host.docker.internal
wherever that name resolves, which is the default on Docker Desktop and
OrbStack but not on native Linux Docker.
Runtime server logs are emitted by FastMCP/Uvicorn.
The HTTP server answers requests addressed to localhost or to the address it
is bound to, and refuses others with 421. That is what stops a website you
merely visit from pointing a domain at this server and using your LinkedIn
session through your own browser.
Reaching the server by any other name is refused, including a machine name on
your network and the public name in front of a reverse proxy. Either have the
proxy rewrite the upstream Host to the backend address, or name the host you
serve it under:
FASTMCP_HTTP_ALLOWED_HOSTS='["mcp.example"]'
That permits exactly that name and keeps refusing everything else. Requests under that name still need the bearer token, and the proxy in front should terminate HTTPS so the token never crosses the network in plain text.
Test with mcp inspector:
- Install and run mcp inspector
bunx @modelcontextprotocol/inspector - Click pre-filled token url to open the inspector in your browser
- Select
Streamable HTTPasTransport Type - Set
URLtohttp://localhost:8080/mcp - Connect
- Test tools
- Make sure Docker is installed
- Check if Docker is running:
docker ps - Permission errors on
~/.linkedin-mcp: an older rootful Docker run may have created the directory as root. Fix it withsudo chown -R "$(id -u):$(id -g)" ~/.linkedin-mcp.
- Make sure you have only one active LinkedIn session at a time
- LinkedIn may require a login confirmation in the LinkedIn mobile app for
--login - LinkedIn may show a captcha challenge during login. Run
uvx mcp-server-linkedin@latest --loginwhich opens a browser where you can solve captchas manually. See the uvx setup for prerequisites. - If Docker auth becomes stale after you re-login on the host, restart Docker once so it can fresh-bridge from the new source session generation.
- Page operations failing (elements not found, navigation hangs): increase the browser page-op timeout:
--timeout 10000orTIMEOUT=10000(milliseconds, default 5000). - Entire tool calls timing out (e.g. multi-section profiles, cold-start Chromium, slow containers): increase the per-tool execution timeout:
--tool-timeout 300orTOOL_TIMEOUT=300(seconds, default 180). - First tool call with no session: if a locally logged-in browser has a live LinkedIn session, the server auto-imports it (see
AUTO_IMPORT_FROM_BROWSER/--auto-import) instead of forcing a manual login. On macOS the keychain may prompt once for Safe Storage access. If no importable browser session exists, it falls back to opening a login window and waits up toLOGIN_INLINE_WAITseconds (default 25, max 45;--login-inline-wait) so a quick sign-in resolves in one call. If the wait elapses, the tool returns a pending signal and the model retries in about 30 seconds. Neither the auto-import nor the inline wait applies under Docker or when the server is bound to a non-loopback HTTP host. Create the session on the host with--login, or use the explicit Docker--login --login-viewercommand. - Users on slow connections may need higher values for either.
- If tool calls answer "No valid LinkedIn session is available in Docker" on a machine that is not a container, the runtime was misdetected. This happened on Linux hosts running a Docker daemon for unrelated services. Set
LINKEDIN_MCP_CONTAINER=falseto override the detection;trueforces the opposite.
- If Chrome is installed in a non-standard location, use
--chrome-path /path/to/chrome - Can also set via environment variable:
CHROME_PATH=/path/to/chrome - On macOS and Linux the browser must be at least as new as the one that last opened your profile, and the server refuses the launch otherwise. (Not on Windows: a browser there cannot be asked its version without starting one, so the check is off.) An older browser can silently drop stores a newer one wrote, the saved session among them, and the failure then looks exactly like an expired login. The message names both versions. Going back to the bundled Chromium after running a newer Chrome once is the usual way to meet this; either run the newer browser again, whichever one that was, or run
--login, which moves the stored session aside and signs in fresh with the browser you have.--logoutalso clears it but discards the old session instead of keeping it recoverable, and it asks for confirmation on the terminal, so it is not usable from a server an MCP client started. - Only Chrome, Chromium and Chrome for Testing are compared this way. Forks number themselves differently (Vivaldi is on 7.x, Edge's build number sits far below Chrome's under the same major), so pointing
CHROME_PATHat one turns the check off rather than producing a refusal nothing could satisfy. - In the documented Docker setup this check does not apply. The container never opens the profile you created with
--login; it derives its own from your cookies, and by default rebuilds that from scratch on every start, so there is nothing for an older image to downgrade. WithEXPERIMENTAL_PERSIST_DERIVED_RUNTIMEthe derived profile is kept, and an image tag that moves backwards then throws it away and re-derives it, again with nothing for you to do. The check matters on the host, where the server opens that profile directly. Not during--loginitself, which moves the old profile aside before it starts a browser and so can never trip it.
Using a proxy
LinkedIn scores the address a session signs in from. Your account's usual IP address is the safe one. You should use a proxy in your country when the server cannot use it: a VPS, another country, or a second account that must not share the first one's address.
With a paid provider, use a sticky residential session that holds one address (never per-request rotation). A WireGuard full tunnel or Tailscale exit node on your home network works when the server should use your usual home address.
Setup Help
<details> <summary><b>🔧 Configuration</b></summary>- Set the proxy up before
--login. Moving an existing session to a new address triggers a LinkedIn checkpoint. That includes a session from--import-from-browser, which was created on your real address. --proxy-server scheme://host:portorPROXY_SERVER, withhttp,https,socks4orsocks5. Only browser traffic is routed, not the MCP transport.- Pass credentials through
PROXY_USERNAMEandPROXY_PASSWORD, or include them inPROXY_SERVERusing the combinedhttp://user:pass@host:portform. The combined form is not accepted by the--proxy-serverCLI option. PROXY_BYPASS=localhost,127.0.0.1,::1reaches local targets directly. With a proxy set, Chromium routeslocalhostthrough it too.
- Chromium cannot authenticate to a SOCKS proxy, so credentials require an
http(s)endpoint. If your provider only offers authenticated SOCKS5, run a local relay that holds the credentials and point the server at that. - A wrong proxy password shows up as a timeout or a failed sign-in, because Chromium retries the authentication challenge until the page times out. If sessions stop working right after you add a proxy, check the proxy credentials first.
- Auto-import is skipped while a proxy is configured: the imported session would move from your real address to the proxy. Use
--login. - Inside a container
127.0.0.1is the container itself, so a relay on the host ishost.docker.internal; native Linux Docker also needs--add-host=host.docker.internal:host-gateway.
Setup from Source (Develop & Contribute)
Contributions are welcome. See CONTRIBUTING.md for architecture guidelines and checklists. Search existing issues first, then use the issue forms for anything new. AI agents follow the issue-packet skill.
Prerequisites: Git and uv installed
Installation
Run in a terminal
# 1. Clone repository
git clone https://github.com/stickerdaniel/linkedin-mcp-server
cd linkedin-mcp-server
# 2. Install UV package manager (if not already installed)
curl -LsSf https://astral.sh/uv/install.sh | sh
# 3. Install dependencies
uv sync
uv sync --group dev
# 4. Install pre-commit hooks
uv run pre-commit install
# 5. Start the server
uv run -m linkedin_mcp_server
Setup Help
<details> <summary><b>🔧 Configuration</b></summary> <details> <summary>CLI options</summary>Session:
--login- Open a browser to sign in and save the session--import-from-browser [BROWSER]- Reuse a session from a locally signed-in Chromium browser (chrome,chromium,brave,edge,arc,vivaldi,helium,yandex,whale,coccoc,opera,opera_gx,auto). Bare flag picksauto, the most recently used browser with a live LinkedIn session.--auto-import/--no-auto-import- Import a session from a signed-in local browser on the first tool call that needs one, before falling back to manual login (default: on). Skipped in Docker, behind a proxy, and on a non-loopback HTTP bind. On macOS the keychain may prompt once.--status- Check whether the stored session is valid, then exit--logout- Clear the stored session--user-data-dir PATH- Browser profile directory (default: ~/.linkedin-mcp/profile). Rotating or clearing a session deletes this directory and its parent, which holds the stored cookies and derived profiles.--claim-profile-root- Take over a profile directory the server will not claim on its own, such as one whose parent already holds other files. Needed once per directory.
Transport:
--transport {stdio,streamable-http}- Force the transport mode (default: stdio)--host HOST/--port PORT/--path PATH- HTTP server address (defaults: 127.0.0.1, 8000, /mcp)--http-token-file PATH- RequireAuthorization: Bearer <token>from HTTP clients, with the token read from this file (one trailing newline ignored, at least 32 characters). A file whose permission bits grant group or other access is refused (chmod 600). ACLs are not read, so on macOS also remove ACL entries (chmod -N <file>, check withls -le). Windows does not check its permissions, so keep it in a folder only your account can read, or use the environment variable. Required for a--hostother than loopback. Environment:LINKEDIN_MCP_HTTP_TOKEN; the file wins when both are set.
Timeouts:
--timeout MS- Timeout for a single page operation (default: 5000)--tool-timeout SECONDS- Timeout for a whole tool call (default: 180). Raise it for calls that read many pages, slow networks, or a cold-start browser.--login-timeout SECONDS- How long the login browser waits for you to finish signing in (default: 1800; 0 = no limit).--login-viewerends the session after 30 minutes either way.--login-inline-wait SECONDS- How long a tool call waits for a login to finish before telling the model to retry (default: 25, max 45; 0 = return at once)
Shared browser:
--browser-wait SECONDS- How long to wait for another server process to hand over the shared browser (default: 25, max 45; 0 = report busy at once). Only matters with several MCP clients running at once.--browser-min-hold SECONDS- Shortest time this process keeps the shared browser before handing it over (default: 20). Clamped to 3 seconds below--browser-wait, so raise that one along with it. Higher means fewer browser restarts but longer waits for other clients.--browser-idle-timeout SECONDS- Close an idle browser and release the profile after this long without a tool call (default: 600; 0 = keep it open)
Browser:
--no-headless- Show the browser window (useful for debugging)--slow-mo MS- Delay between browser actions (default: 0, useful for debugging)--viewport WxH- Viewport size (default: 1280x720). Applies to windowless mode only; a headed launch uses the real window size.--chrome-path PATH- Path to a Chrome/Chromium executable--installer-temp-dir PATH- Existing directory for browser installation temporary files (environment:INSTALLER_TEMP_DIR).--proxy-server URL- Route browser traffic through a proxy, asscheme://host:port. Set it up before--login; see Using a proxy.
Other:
--log-level {DEBUG,INFO,WARNING,ERROR}- Logging level (default: WARNING)--help- Show help
</details> <details> <summary>HTTP mode and Claude Desktop</summary>Note: Most CLI options have environment variable equivalents. See
.env.examplefor details.
HTTP Mode Example (for web-based MCP clients):
uv run -m linkedin_mcp_server --transport streamable-http --host 127.0.0.1 --port 8000 --path /mcp
Any other --host needs a token: set LINKEDIN_MCP_HTTP_TOKEN or pass --http-token-file (a file only your account can read), and send Authorization: Bearer <token> from the client.
Claude Desktop:
{
"mcpServers": {
"mcp-server-linkedin": {
"command": "uv",
"args": ["--directory", "/path/to/linkedin-mcp-server", "run", "-m", "linkedin_mcp_server"]
}
}
}
stdio is used by default for this config.
- Make sure you have only one active LinkedIn session at a time
- LinkedIn may require a login confirmation in the LinkedIn mobile app for
--login - LinkedIn may show a captcha challenge during login. The
--logincommand opens a browser where you can solve it manually.
- Use
--no-headlessto watch the browser when a tool returns wrong or missing data - Add
--log-level DEBUGto see more detailed logging
- Browser profile is stored at
~/.linkedin-mcp/profile/ - Managed browser downloads are cached at
~/.linkedin-mcp/patchright-browsers/, shared with theuvxand MCP Bundle installations - The browser cache keeps growing: Patchright keeps an old Chromium revision for as long as any installed version still references it, and a
uvarchive or a second worktree is such a reference. The server logs a warning naming what it holds. To reclaim the space, stop every LinkedIn MCP Server instance, delete~/.linkedin-mcp/patchright-browsers/, and let the next launch download the current browser. - Use
--logoutto clear the profile and start fresh
- Check Python version:
python --version(should be 3.12.4+) - Reinstall Patchright:
uv run patchright install chromium - Reinstall dependencies:
uv sync --reinstall
- Page operations failing (elements not found, navigation hangs): increase the browser page-op timeout:
--timeout 10000orTIMEOUT=10000(milliseconds, default 5000). - Entire tool calls timing out (e.g. multi-section profiles, cold-start Chromium, slow containers): increase the per-tool execution timeout:
--tool-timeout 300orTOOL_TIMEOUT=300(seconds, default 180). - First tool call with no session: if a locally logged-in browser has a live LinkedIn session, the server auto-imports it (see
AUTO_IMPORT_FROM_BROWSER/--auto-import) instead of forcing a manual login. On macOS the keychain may prompt once for Safe Storage access. If no importable browser session exists, it falls back to opening a login window and waits up toLOGIN_INLINE_WAITseconds (default 25, max 45;--login-inline-wait) so a quick sign-in resolves in one call. If the wait elapses, the tool returns a pending signal and the model retries in about 30 seconds. Neither the auto-import nor the inline wait applies under Docker or when the server is bound to a non-loopback HTTP host. Create the session on the host with--login, or use the explicit Docker--login --login-viewercommand. - Users on slow connections may need higher values for either.
- If tool calls answer "No valid LinkedIn session is available in Docker" on a machine that is not a container, the runtime was misdetected. This happened on Linux hosts running a Docker daemon for unrelated services. Set
LINKEDIN_MCP_CONTAINER=falseto override the detection;trueforces the opposite.
- If Chrome is installed in a non-standard location, use
--chrome-path /path/to/chrome - Can also set via environment variable:
CHROME_PATH=/path/to/chrome - On macOS and Linux the browser must be at least as new as the one that last opened your profile, and the server refuses the launch otherwise. (Not on Windows: a browser there cannot be asked its version without starting one, so the check is off.) An older browser can silently drop stores a newer one wrote, the saved session among them, and the failure then looks exactly like an expired login. The message names both versions. Going back to the bundled Chromium after running a newer Chrome once is the usual way to meet this; either run the newer browser again, whichever one that was, or run
--login, which moves the stored session aside and signs in fresh with the browser you have.--logoutalso clears it but discards the old session instead of keeping it recoverable, and it asks for confirmation on the terminal, so it is not usable from a server an MCP client started. - Only Chrome, Chromium and Chrome for Testing are compared this way. Forks number themselves differently (Vivaldi is on 7.x, Edge's build number sits far below Chrome's under the same major), so pointing
CHROME_PATHat one turns the check off rather than producing a refusal nothing could satisfy.
[!IMPORTANT] FAQ
Is this safe to use? Will I get banned? This tool controls a real browser session; it doesn't exploit undocumented APIs or bypass authentication. LinkedIn's User Agreement prohibits automated access, and accounts using automated tools can be restricted or banned. Use at your own risk; there is no guarantee of account safety. If you encounter any issues, let me know in the Discussions.
What if my agents execute too many actions? Tool calls run sequentially through a queue. You are responsible for the volume of automation you run; use it sparingly and prompt your agents responsibly.
Contributors
Thanks to everyone who has contributed code, bug reports and fixes.
<a href="https://github.com/stickerdaniel/linkedin-mcp-server/graphs/contributors"> <img alt="Contributors to linkedin-mcp-server" src="https://contrib.rocks/image?repo=stickerdaniel/linkedin-mcp-server" /> </a>Acknowledgements
Built with FastMCP and Patchright.
Use in accordance with LinkedIn's User Agreement. Automated access may violate LinkedIn's terms and can lead to account restrictions. This tool is for personal use only and comes with no warranty of any kind.
License
This project is licensed under the Apache 2.0 license.
Building on this project is welcome! See the license for terms and the NOTICE for attribution.
常见问题
LinkedIn Profile and Job Scraper 是什么?
使AI助手能够抓取LinkedIn个人资料、公司信息和职位发布,进行详细数据提取和会话管理,支持招聘和商业研究工作流程。通过安全的凭证处理和无缝集成简化LinkedIn数据访问。
相关 Skills
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
技能工坊
by anthropics
覆盖 Skill 从创建到迭代优化全流程:起草能力、补测试提示、跑评测与基准方差分析,并持续改写内容和描述,提升效果与触发准确率。
✎ 技能工坊把技能从创建、迭代到评测串成闭环,方差分析加描述优化,特别适合把触发准确率打磨得更稳。
表格处理
by anthropics
围绕 .xlsx、.xlsm、.csv、.tsv 做读写、修复、清洗、格式整理、公式计算与格式转换,适合修改现有表格、生成新报表或把杂乱数据整理成交付级电子表格。
✎ 做 Excel/CSV 相关任务很省心,能直接读写、修复、清洗和格式转换,尤其擅长把乱七八糟的表格整理成交付级文件。
相关 MCP Server
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by microsoft
使用此服务器轻松自动化Web交互。让您的LLM利用结构化可访问性快照在网页上导航、提取数据并执行操作,无需视觉模型即可提升可靠性和性能。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。