io.github.cyberpapiii/imessage-max

平台与服务

by cyberpapiii

面向 macOS 上 iMessage 的 AI 优化型 MCP server,可读取、搜索并发送消息。

什么是 io.github.cyberpapiii/imessage-max

面向 macOS 上 iMessage 的 AI 优化型 MCP server,可读取、搜索并发送消息。

README

<p align="center"> <img src="icon.png" alt="iMessage Max" width="128"> </p>

iMessage Max

A high-performance MCP (Model Context Protocol) server for iMessage that lets AI agents read, search, and send your messages with proper contact resolution.

Built in Swift for native macOS integration - single binary, no runtime dependencies.

Distribution Status

The project now ships a single Swift implementation:

  • GitHub releases
  • Homebrew
  • source builds
  • Codex plugin metadata
  • Claude Desktop MCPB metadata

The old Python package has been retired and removed from the repository. Everything current lives under swift/.

Features

  • 12 Intent-Aligned Tools - Work the way you naturally ask questions, not raw database queries
  • Contact Resolution - See names instead of phone numbers via macOS Contacts
  • Smart Image Handling - Efficient image variants (vision/thumb/full) to avoid token bloat
  • Session Grouping - Messages grouped into conversation sessions with gap detection
  • Attachment Tracking - Know which images are available locally vs offloaded to iCloud
  • Native Performance - Swift with raw SQLite3, Core Image GPU acceleration
  • Read-Only Safe - Only reads from chat.db, send requires explicit permission

Why This Exists

Most iMessage tools expose raw database structures, requiring 3-5 tool calls per user intent. This MCP provides intent-aligned tools:

code
"What did Contact A and I talk about yesterday?"
→ find_chat(participants=["Contact A"]) + get_messages(since="yesterday")

"Show me the exact details for this thread before I reply"
→ get_chat_details(chat_id="chat123")

"Show me photos from the group chat"
→ list_attachments(chat_id="chat123", type="image")

"Find where we discussed the launch timeline"
→ search(query="launch timeline")

Common Agent Workflows

The tools work best when an agent uses them as short workflows instead of isolated one-off calls.

Agents should treat chat_id values like chat123 as internal handles for tool calls and exact sends. When explaining results to a person, use the returned chat name, group name, or participant-derived label instead of saying "Chat 123."

Find the right conversation, then read it

text
find_chat(participants=["Contact A"])
get_chat_details(chat_id="chat123")
get_messages(chat_id="chat123", since="yesterday", limit=50)

Use this when the person matters more than the exact thread id.

Search first, then zoom in

text
search(query="launch timeline", limit=10)
get_context(message_id="msg_456", before=5, after=10)

Use this when you know the topic but not where it was discussed.

Check what needs attention

text
get_unread()
get_active_conversations(hours=24, min_exchanges=2)

Use this to surface unread threads and active conversations after a broad chat-list sweep.

Work with attachments safely

text
list_attachments(chat_id="chat123", type="image", since="30d")
get_attachment(attachment_id="att123", variant="vision")

Use list_attachments to discover the message where files were shared first. It still returns exact attachment ids and local-availability state before you fetch a file.

Send with exact targeting when it matters

text
find_chat(participants=["Contact A", "Contact B"])
send(chat_id="chat456", text="Please use the latest draft")

For sensitive sends, prefer resolving the exact chat first and then using chat_id so the message lands in the intended thread.

Installation

Homebrew (Recommended)

bash
brew tap cyberpapiii/tap
brew install imessage-max

From Source

bash
git clone https://github.com/cyberpapiii/imessage-max.git
cd imessage-max/swift
swift build -c release

# Binary is at .build/release/imessage-max

For local development, advanced setup, and the signed install workflow, see:

Client Icon Metadata

iMessage Max ships icons for the main MCP protocol surface and the client packaging surfaces that use their own metadata:

  • MCP 2025-11-25 initialize responses include PNG serverInfo.icons.
  • Each tool advertises a compact PNG tool icon.
  • Codex plugin metadata lives in .codex-plugin/plugin.json and uses assets/codex/icon.png plus assets/codex/logo.png.
  • Claude Desktop / MCPB metadata lives in mcpb/manifest.json and uses PNG assets under mcpb/assets/.

The committed PNG source set is under assets/icons/ at 16x16, 32x32, 64x64, 128x128, 256x256, and 512x512.

Setup

1. Grant Full Disk Access

Required to read ~/Library/Messages/chat.db:

  1. Open System SettingsPrivacy & SecurityFull Disk Access
  2. Click + to add the binary

For Homebrew installs: The binary is at /opt/homebrew/Cellar/imessage-max/VERSION/bin/imessage-max (not the symlink at /opt/homebrew/bin/). Find it with:

bash
# Open the folder containing the actual binary
open $(dirname $(readlink -f $(which imessage-max)))

For source builds: Add .build/release/imessage-max from your clone directory.

Tip: In the file picker, press ⌘+Shift+G and paste the path to navigate directly.

2. Grant Contacts Access

Required for resolving phone numbers to names. The app will request access on first run, or add manually:

System SettingsPrivacy & SecurityContacts → add imessage-max

3. Configure Your MCP Client

Add imessage-max to your MCP client's server configuration.

Many MCP clients use a JSON structure like this:

For Homebrew:

json
{
  "mcpServers": {
    "imessage": {
      "command": "/opt/homebrew/Cellar/imessage-max/VERSION/bin/imessage-max"
    }
  }
}

For source builds:

json
{
  "mcpServers": {
    "imessage": {
      "command": "/path/to/imessage-max/swift/.build/release/imessage-max"
    }
  }
}

If your client uses a different config format, point it at the same binary path.

4. Reconnect Your MCP Client

After saving the config, reconnect or restart your MCP client. The server should appear in the available tools, and you can verify the connection with diagnose.

Tools

find_chat

Find chats by participants, name, or recent content.

text
find_chat(participants=["Contact A"])              # Find a direct chat
find_chat(participants=["Contact A", "Contact B"]) # Find a group with both
find_chat(name="Project Group")                    # Find by chat name
find_chat(contains_recent="latest draft")          # Find by recent content

get_chat_details

Inspect a known thread without opening the full conversation.

text
get_chat_details(chat_id="chat123")                          # Participants, handles, state, last message
get_chat_details(chat_id="chat123", include_shared_summary=false) # Skip recent shared summary

get_messages

Retrieve messages with flexible filtering. Returns metadata for media.

text
get_messages(chat_id="chat123", limit=50)           # Recent messages
get_messages(chat_id="chat123", since="24h")        # Last 24 hours
get_messages(chat_id="chat123", from_person="Contact A")  # From specific person

get_attachment

Retrieve image content by attachment ID with resolution variants.

text
get_attachment(attachment_id="att123")                 # Default: vision (1568px)
get_attachment(attachment_id="att123", variant="thumb") # Quick preview (400px)
get_attachment(attachment_id="att123", variant="full")  # Original resolution
VariantResolutionUse CaseToken Cost
vision (default)1568pxAI analysis, OCR~1,600 tokens
thumb400pxQuick preview~200 tokens
fullOriginalMaximum detailVaries

list_chats

Browse recent chats with previews.

text
list_chats(limit=20)          # Recent chats
list_chats(is_group=True)     # Only group chats
list_chats(since="7d")        # Active in last week

search

Full-text search across messages.

text
search(query="draft")                           # Search all messages
search(query="budget", from_person="Contact A") # From specific person
search(query="launch", is_group=True)           # Only in group chats

get_context

Get messages surrounding a specific message.

text
get_context(message_id="msg_123", before=5, after=10)

get_active_conversations

Find chats with recent back-and-forth activity.

text
get_active_conversations(hours=24)
get_active_conversations(is_group=True, min_exchanges=3)

list_attachments

Browse shared items grouped by message. Each row includes exact attachment ids for follow-up fetches.

text
list_attachments(type="image", since="7d")
list_attachments(chat_id="chat123", type="any")

get_unread

Get unread threads or unread messages. Default is summary by chat.

text
get_unread()                         # Summary by chat for last 7 days
get_unread(since="24h")              # Summary by chat for last 24 hours
get_unread(format="messages")        # Row-level unread messages

send

Send a message or file attachment (requires Automation permission for Messages.app).

text
send(to="Contact A", text="Checking in")
send(chat_id="chat123", text="Please use the latest draft")
send(chat_id="chat123", file_paths=["/path/save-the-date.jpg"])
send(to="Contact A", file_paths=["/path/reference.png"], text="Sharing the file here")

Rules:

  • Exactly one of to or chat_id
  • At least one of text or file_paths
  • If both are provided, files are sent first and text is sent last

Release Checks

For a lightweight pre-release routine, use:

Additional send note:

  • reply_to is currently unsupported
  • Sends execute immediately when the destination is exact; there is no confirmation gate. Ambiguous destinations are refused with status: "ambiguous". The confirm parameter is deprecated and ignored (kept only for compatibility). Authorization happens in the user's conversation with the agent and in the client's tool-approval UI, not server-side.

Send result semantics (text sends are verified post-send against chat.db):

  • status: "confirmed" means the message row was found in chat.db with no error; verified_message_guid is the evidence
  • status: "uncertain" means transport accepted the send but the row was not found within the polling window; follow up with get_messages
  • status: "mismatch" means the message landed in a different chat than intended; do not treat as success
  • status: "sent" means verification was unavailable (DB unreadable); transport accepted only
  • status: "pending_confirmation" means Messages accepted an attachment send, but the file transfer was not confirmed as finished within the polling window
  • status: "failed" means the send failed
  • status: "ambiguous" means the target could not be resolved safely

Notes:

  • pending_confirmation is a normal non-fatal attachment state, not the same as a hard failure
  • exact chat sends target the existing conversation identified by chat_id
  • JSON-shaped tools return MCP structuredContent as well as legacy text content for older clients

Examples:

  • {"status":"confirmed","verified_message_guid":"...",...} means delivery was verified in chat.db
  • {"status":"pending_confirmation","success":false,...} means Messages accepted the attachment, but the MCP could not yet confirm final completion

diagnose

Troubleshoot configuration and permission issues.

text
diagnose()  # Returns: database status, contacts count, permissions, capabilities

Troubleshooting

Contacts showing as phone numbers

Run diagnose to check status. If contacts_authorized is false:

  • Add the imessage-max binary to System Settings → Privacy & Security → Contacts

"Database not found" error

Add the imessage-max binary to System Settings → Privacy & Security → Full Disk Access

Images show "attachment_offloaded" error

Some attachments are stored in iCloud, not on disk. list_attachments includes nested attachment summaries with available: true/false for each file. To download offloaded attachments, open the conversation in Messages.app.

MCP client not loading the server

  1. Check config file syntax is valid JSON
  2. Verify the binary path is correct
  3. Reconnect or fully restart your MCP client

Architecture

code
┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│  MCP Client /   │◄───►│  iMessage Max   │◄───►│  chat.db        │
│  Agent          │     │  (Swift MCP)    │     │  (SQLite)       │
└─────────────────┘     └────────┬────────┘     └─────────────────┘
                                │
                                ▼
                        ┌─────────────────┐
                        │  Contacts.app   │
                        │  (CNContactStore)│
                        └─────────────────┘

Requirements

  • macOS 13+ (Ventura or later)
  • Full Disk Access permission
  • Contacts permission (for name resolution)
  • Automation permission for Messages.app (send only)

Advanced Setup

For HTTP mode, local background service setup, development commands, and contributor-focused workflow details, see:

License

MIT

常见问题

io.github.cyberpapiii/imessage-max 是什么?

面向 macOS 上 iMessage 的 AI 优化型 MCP server,可读取、搜索并发送消息。

相关 Skills

Slack动图

by anthropics

Universal
热门

面向Slack的动图制作Skill,内置emoji/消息GIF的尺寸、帧率和色彩约束、校验与优化流程,适合把创意或上传图片快速做成可直接发送的Slack动画。

帮你快速做出适配 Slack 的动图,内置约束规则和校验工具,少踩上传与播放坑,做表情包和演示都更省心。

平台与服务
未扫描165.3k

MCP构建

by anthropics

Universal
热门

聚焦高质量 MCP Server 开发,覆盖协议研究、工具设计、错误处理与传输选型,适合用 FastMCP 或 MCP SDK 对接外部 API、封装服务能力。

想让 LLM 稳定调用外部 API,就用 MCP构建:从 Python 到 Node 都有成熟指引,帮你更快做出高质量 MCP 服务器。

平台与服务
未扫描165.3k

接口测试套件

by alirezarezvani

Universal
热门

扫描 Next.js、Express、FastAPI、Django REST 的 API 路由,自动生成覆盖鉴权、参数校验、错误码、分页、上传与限流场景的 Vitest 或 Pytest 测试套件。

帮你把API与集成测试自动化跑顺,减少回归漏测;能力全面,尤其适合复杂接口场景的QA团队。

平台与服务
未扫描23.5k

相关 MCP Server

Slack 消息

编辑精选

by Anthropic

热门

Slack 是让 AI 助手直接读写你的 Slack 频道和消息的 MCP 服务器。

这个服务器解决了团队协作中需要 AI 实时获取 Slack 信息的痛点,特别适合开发团队让 Claude 帮忙汇总频道讨论或发送通知。不过,它目前只是参考实现,文档有限,不建议在生产环境直接使用——更适合开发者学习 MCP 如何集成第三方服务。

平台与服务
89.1k

by netdata

热门

io.github.netdata/mcp-server 是让 AI 助手实时监控服务器指标和日志的 MCP 服务器。

这个工具解决了运维人员需要手动检查系统状态的痛点,最适合 DevOps 团队让 Claude 自动分析性能数据。不过,它依赖 NetData 的现有部署,如果你没用过这个监控平台,得先花时间配置。

平台与服务
79.9k

by d4vinci

热门

Scrapling MCP Server 是专为现代网页设计的智能爬虫工具,支持绕过 Cloudflare 等反爬机制。

这个工具解决了爬取动态网页和反爬网站时的头疼问题,特别适合需要批量采集电商价格或新闻数据的开发者。不过,它依赖外部浏览器引擎,资源消耗较大,不适合轻量级任务。

平台与服务
71.9k

评论