com.files/python-mcp

效率与工作流

by files-com

安全地为 LLM 提供受控权限,使其可在你的 Files.com 环境中执行真实操作。

什么是 com.files/python-mcp

安全地为 LLM 提供受控权限,使其可在你的 Files.com 环境中执行真实操作。

README

Files.com MCP Server

Files.com MCP allows your AI model, like ChatGPT or Claude, to use Files.com.

Files.com is the cloud-native, next-gen MFT, SFTP, and secure file-sharing platform that replaces brittle legacy servers with one always-on, secure fabric. Automate mission-critical file flows—across any cloud, protocol, or partner—while supporting human collaboration and eliminating manual work.

With universal SFTP, AS2, HTTPS, and 50+ native connectors backed by military-grade encryption, Files.com unifies governance, visibility, and compliance in a single pane of glass.

Introduction

Modern AI models like ChatGPT and Claude are no longer just answering questions—they’re taking action. With Files.com MCP, you can securely give LLMs controlled access to real-world operations inside your Files.com environment.

Whether it's uploading, downloading, querying folders, or managing users, MCP enables your AI agent to interact with your Files.com infrastructure as if it were an extension of your team—without compromising on security, auditability, or control.

What Is MCP?

Model Context Protocol (MCP) is a structured interface that lets Large Language Models call real APIs as part of their workflow. Think of it as a way to “hand tools” to the LLM—where the tools are real, authenticated functions from your Files.com environment.

When integrated via MCP, your LLM can:

  • Transfer files between cloud and on-prem systems

  • Query folders or file metadata

  • Create and manage users

  • Automate workflows like archival or sharing

  • And much more

MCP turns the LLM from a passive assistant into an active file operations agent.

What is Files.com?

Files.com is the modern platform for secure file transfer, automation, and storage integration. Used by thousands of enterprises, Files.com connects cloud apps, on-prem systems, and human workflows—all through a single, powerful interface.

With robust APIs, native protocol support (SFTP, FTPS, AS2, and more), and enterprise-grade access controls, Files.com is built to move your files—reliably, securely, and at scale.

Common Use Cases

AI Assistants for Operations Teams: Let your internal chatbot fetch or archive files on request.

Automated LLM Workflows: Build AI agents that react to incoming support requests, then retrieve or upload the necessary files from your environment.

Developer Copilots: Enable your dev-focused LLMs to create users, provision folders, or debug via real-time file access.

Important Information

Large Language Models perform best when their toolset is focused. If you're integrating with Files.com MCP and noticing inconsistent tool usage, your LLM may be overloaded with too many available functions.

Most LLM clients allow you to selectively enable or disable tools exposed through MCP. For best results, only include the specific tools your agent needs for its task. This reduces ambiguity and improves the model’s ability to pick the right operation every time.

Installation Into Your LLM

Each LLM client has its own method for installing an MCP, and they typically provide specific instructions. Many clients follow a pattern similar to Claude, so our Claude example is a great starting point if you’re working with one of those.

For LLMs that require a more detailed or technical setup, our MCP is implemented in Python and available on PyPI: https://pypi.org/project/files-com-mcp/

If your LLM client needs you to supply execution details for our MCP, we recommend using uvx, as demonstrated in the Claude example. This approach ensures a smooth, reproducible setup with minimal effort.

Using with Claude

To install into Claude you have to add JSON to the claude_desktop_config.json file

An official tutorial can found here: https://modelcontextprotocol.io/quickstart/user#2-add-the-filesystem-mcp-server

To add the Files.com MCP, use the Claude Config JSON below (be sure to change the FILES_COM_API_KEY value)

uv Required

These examples require uv which is a popular modern environment manager for running isolated python tools. You will need to install it first. Using uvx is a huge improvement over older Python environment setup methods. It is simple, runs smoothly, and eliminates the need for manual configuration or unnecessary complexity.

Claude Config

code
{
  "mcpServers": {
    "Files.com": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "files-com-mcp"
      ],
      "env": {
        "FILES_COM_API_KEY": "CHangeME"
      }
    }
  }
}

Authentication

There are two ways to authenticate: API Key authentication and Session-based authentication.

Authenticate with an API Key

Authenticating with an API key is the recommended authentication method for most scenarios, and is the method used in the examples on this site.

To use an API Key, first generate an API key from the web interface or via the API or an SDK.

Note that when using a user-specific API key, if the user is an administrator, you will have full access to the entire API. If the user is not an administrator, you will only be able to access files that user can access, and no access will be granted to site administration functions in the API.

Don't forget to replace the placeholder, YOUR_API_KEY, with your actual API key.

Authenticate with a Session

You can also authenticate by creating a user session using the username and password of an active user. If the user is an administrator, the session will have full access to all capabilities of Files.com. Sessions created from regular user accounts will only be able to access files that user can access, and no access will be granted to site administration functions.

Sessions use the exact same session timeout settings as web interface sessions. When a session times out, simply create a new session and resume where you left off. This process is not automatically handled by our SDKs because we do not want to store password information in memory without your explicit consent.

Logging In

Using a Session

Logging Out

Configuration

Sort and Filter

Several of the Files.com API resources have list operations that return multiple instances of the resource. The List operations can be sorted and filtered.

Sorting

To sort the returned data, pass in the sort_by method argument.

Each resource supports a unique set of valid sort fields and can only be sorted by one field at a time.

Special note about the List Folder Endpoint

For historical reasons, and to maintain compatibility with a variety of other cloud-based MFT and EFSS services, Folders will always be listed before Files when listing a Folder. This applies regardless of the sorting parameters you provide. These will be used, after the initial sort application of Folders before Files.

Filtering

Filters apply selection criteria to the underlying query that returns the results. They can be applied individually or combined with other filters, and the resulting data can be sorted by a single field.

Each resource supports a unique set of valid filter fields, filter combinations, and combinations of filters and sort fields.

Filter Types

FilterTypeDescription
filterExactFind resources that have an exact field value match to a passed in value. (i.e., FIELD_VALUE = PASS_IN_VALUE).
filter_prefixPatternFind resources where the specified field is prefixed by the supplied value. This is applicable to values that are strings.
filter_gtRangeFind resources that have a field value that is greater than the passed in value. (i.e., FIELD_VALUE > PASS_IN_VALUE).
filter_gteqRangeFind resources that have a field value that is greater than or equal to the passed in value. (i.e., FIELD_VALUE >= PASS_IN_VALUE).
filter_ltRangeFind resources that have a field value that is less than the passed in value. (i.e., FIELD_VALUE < PASS_IN_VALUE).
filter_lteqRangeFind resources that have a field value that is less than or equal to the passed in value. (i.e., FIELD_VALUE <= PASS_IN_VALUE).

Paths

Working with paths in Files.com involves several important considerations. Understanding how path comparisons are applied helps developers ensure consistency and accuracy across all interactions with the platform.

<div></div>

Capitalization

Files.com compares paths in a case-insensitive manner. This means path segments are treated as equivalent regardless of letter casing.

For example, all of the following resolve to the same internal path:

Path VariantInterpreted As
Documents/Reports/Q1.pdfdocuments/reports/q1.pdf
documents/reports/q1.PDFdocuments/reports/q1.pdf
DOCUMENTS/REPORTS/Q1.PDFdocuments/reports/q1.pdf

This behavior applies across:

  • API requests
  • Folder and file lookup operations
  • Automations and workflows

See also: Case Sensitivity Documentation

Slashes

All path parameters in Files.com (API, SDKs, CLI, automations, integrations) must omit leading and trailing slashes. Paths are always treated as absolute and slash-delimited, so only internal / separators are used and never at the start or end of the string.

Path Slash Examples

PathValid?Notes
folder/subfolder/file.txtCorrect, internal separators only
/folder/subfolder/file.txtLeading slash not allowed
folder/subfolder/file.txt/Trailing slash not allowed
//folder//file.txtDuplicate separators not allowed
<div></div>

Unicode Normalization

Files.com normalizes all paths using Unicode NFC (Normalization Form C) before comparison. This ensures consistency across different representations of the same characters.

For example, the following two paths are treated as equivalent after NFC normalization:

InputNormalized Form
uploads/\u0065\u0301.txtuploads/é.txt
docs/Café/Report.txtdocs/Café/Report.txt
  • All input must be UTF‑8 encoded.
  • Precomposed and decomposed characters are unified.
  • This affects search, deduplication, and comparisons across SDKs.
<div></div>

Foreign Language Support

The Files.com MCP will soon be updated to support localized responses by using a configuration method. When available, it can be used to guide the API in selecting a preferred language for applicable response content.

Language support currently applies to select human-facing fields only, such as notification messages and error descriptions.

If the specified language is not supported or the value is omitted, the API defaults to English.

Errors

Mock Server

Files.com publishes a Files.com API server, which is useful for testing your use of the Files.com SDKs and other direct integrations against the Files.com API in an integration test environment.

It is a Ruby app that operates as a minimal server for the purpose of testing basic network operations and JSON encoding for your SDK or API client. It does not maintain state and it does not deeply inspect your submissions for correctness.

Eventually we will add more features intended for integration testing, such as the ability to intentionally provoke errors.

Download the server as a Docker image via Docker Hub.

The Source Code is also available on GitHub.

A README is available on the GitHub link.

Development

While our MCP works well out-of-the-box, some power users find value in modifying MCP code to suit their unique needs. For those power users, it is recommended to use STDIO mode. Upload and Download tools rely on the file system where the MCP is running.

To test LLM tools we recommend a popular command-line program called inspector. This will start a WebUI on a local port, the output of the command will give you the link to the inspector GUI. Ex: http://127.0.0.1:6274

Development - STDIO

code
FILES_COM_API_KEY="dummyKey" npx @modelcontextprotocol/inspector uv run -m files_com_mcp

Development - SSE

code
FILES_COM_API_KEY="dummyKey" uv run -m files_com_mcp --mode server --port 12345

Launch the inspector

code
npx @modelcontextprotocol/inspector

Development Claude Config

code
{
  "mcpServers": {
    "Files.com": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/folder-containing-files_com_mcp",
        "run",
        "-m",
        "files_com_mcp"
      ],
      "env": {
        "FILES_COM_API_KEY": "CHangeME"
      }
    }
  }
}

MCP Registry Metadata

code
mcp-name: com.files/python-mcp

常见问题

com.files/python-mcp 是什么?

安全地为 LLM 提供受控权限,使其可在你的 Files.com 环境中执行真实操作。

相关 Skills

表格处理

by anthropics

Universal
热门

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。

效率与工作流
未扫描109.6k

PDF处理

by anthropics

Universal
热门

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。

效率与工作流
未扫描109.6k

Word文档

by anthropics

Universal
热门

覆盖Word/.docx文档的创建、读取、编辑与重排,适合生成报告、备忘录、信函和模板,也能处理目录、页眉页脚、页码、图片替换、查找替换、修订批注及内容提取整理。

搞定 .docx 的创建、改写与精排版,目录、批量替换、批注修订和图片更新都能自动化,做正式文档尤其省心。

效率与工作流
未扫描109.6k

相关 MCP Server

文件系统

编辑精选

by Anthropic

热门

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。

效率与工作流
82.9k

by wonderwhy-er

热门

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。

效率与工作流
5.8k

EdgarTools

编辑精选

by dgunning

热门

EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。

这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。

效率与工作流
1.9k

评论