
fm-mcp
io.github.yranganav0.1.0更新于 Oct 10, 2026
Delegate summarising, extraction, classification and OCR to the macOS 27 on-device model.
概览
让编程助手把摘要、字段提取、分类和图片 OCR 等简单文本工作交给 macOS 27 上的端侧 Apple Foundation Models 模型处理。
- 功能
- 这是一个本地 stdio MCP 服务器,提供四个工具:summarise(把日志、文档、笔记或转录稿压缩成一段话或最多 7 条要点)、extract(按你给的 JSON Schema 把命名字段提取为 JSON)、classify(把文本归入你指定的标签,可用 multi 选多个)以及 ocr(读取 PNG、JPEG、HEIC、TIFF、GIF 或 BMP 图片中的文字,不支持 PDF)。前三个工具既可接收文本,也可接收最大 1 MB 的文本文件路径,助手无需自己读取文件。首次调用工具时它会自行启动 fm serve 模型服务,会话结束时停止。
- 适用场景
- 适合编程助手原本要花付费远程 token 处理例行文本任务的场景,例如总结日志或从文档中提取字段,同时希望文本留在本机。不适用于代码、数学、推理、文本中不存在的事实,以及答错代价高且无法核对的任务。
- 运行要求
- 需要 Apple Silicon 的 Mac(不支持 Intel)、开启 Apple Intelligence 的 macOS 27,并需先执行一次 fm license 接受许可。可通过 Homebrew、cargo 或安装脚本安装;fm-mcp install 会配置 Claude Code 和 Codex,也可使用 Claude Code 插件。可选环境变量 FM_MCP_REQUEST_TIMEOUT_SECS(默认 120)和 FM_MCP_LOG=debug。
安装
在 SourceWeft 中
- 打开 控制台中的 fm-mcp,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
fm-mcp
An MCP server that lets coding agents such as Claude Code and Codex hand simple text work to the on-device model for Apple Foundation Models, the fm that ships with macOS 27. It's free, private, and runs offline.
mcp-name: io.github.yrangana/fm-mcp
Why
Coding agents spend paid, remote tokens on simple jobs, like summarising a log or pulling fields out of a document. A small model already on your Mac can do much of that for nothing, and your text never leaves the machine. fm-mcp lets the agent hand off that work, and tells it plainly what the small model can't do.
Install
You need a Mac with Apple Silicon (Intel Macs are not supported), macOS 27 with Apple Intelligence turned on, and the fm licence accepted once (fm license).
Then start a new Claude Code or Codex session. fm-mcp starts the model server (fm serve) itself the first time a tool is called, and stops it when the session ends.
Other ways to get the binary:
What fm-mcp install changes
- Claude Code: adds the
fm-mcpMCP server to~/.claude.json(throughclaude mcp addwhen theclaudecommand is there), and installs thefm-delegateskill in~/.claude/skills/. - Codex: adds
[mcp_servers.fm-mcp]to~/.codex/config.toml, and a marked section in~/.codex/AGENTS.md(or inAGENTS.override.md, if you use one).
It backs up each file before changing it and prints every path it touched; running it again changes nothing. --claude or --codex picks one agent, --dry-run shows the changes without writing, and --no-guidance skips the skill and the AGENTS.md section. fm-mcp install --uninstall removes everything it added.
The skill and the AGENTS.md section tell the agent when to delegate. Without them the agent sees only the tool descriptions, and delegates less well.
Or: the Claude Code plugin
The plugin gives Claude Code the MCP server and the skill, without fm-mcp install. It still needs the binary on your PATH, so install that first (Homebrew above); otherwise Claude Code reports the server as failed to connect.
Use the plugin or fm-mcp install for Claude Code, not both: both together give Claude Code two fm-mcp servers. With the plugin, run fm-mcp install --codex to set up Codex only.
Other MCP clients
fm-mcp is a plain stdio MCP server, so other clients that run local servers on the same Mac can use it. fm-mcp install doesn't set them up, and they don't get the delegation guidance: the agent decides from the tool descriptions alone. Each client below was tried on a real Mac; others may work but are untested.
Claude Desktop (tried with 2.31226.1, 2026-10-11). In Settings › Developer › Edit Config, add this to mcpServers in claude_desktop_config.json, then quit and reopen Claude Desktop:
Use the full path (which fm-mcp prints it). fm-mcp helps most with files on your Mac: give Claude the file's path and it passes path, so the text never goes through Claude. For a web page, Claude Desktop reads the page itself first, so delegating it saves nothing.
Devin (formerly Windsurf) (tried with Devin.app 3.8.20, 2026-10-11). Add this to mcpServers in ~/.config/devin/mcp_config.json:
Tools
summarise, extract and classify take text, or a path to a text file (up to 1 MB) so the agent never has to read the file itself.
Limits
- Small model, small context: about 8K tokens, shared by the input and the answer. Logs full of IDs and numbers use far more tokens per word than prose.
- Not for code, maths, reasoning, facts the text doesn't contain, or anything where a wrong answer is costly and you can't check it.
- It makes mistakes. Summaries can drop or distort details.
extractusually returnsnullfor a field the text doesn't contain, but when the text has something close in meaning (no PO number, but line items), about 1 in 3 such fields gets a wrong value. Nested schemas are less reliable than flat ones. Check what matters. - One request at a time. The model is shared by every session on the Mac, so calls queue: a short
extracttakes 1–2 s, a longsummarisea minute or more. - Safety filter: the on-device model sometimes refuses harmless input. fm-mcp reports that clearly, and the agent does the task itself.
Privacy
Everything runs on your Mac. fm-mcp talks to fm serve over a local Unix socket and sends nothing over the network. Your text goes only to the on-device model.
Troubleshooting
Run fm-mcp doctor. It checks the Mac, macOS, fm, the licence, the model, a test request, and both agents' setup, and says how to fix anything that fails.
Uninstall
Development
AGENTS.md has the architecture, the tested facts about fm serve, and the project rules. docs/MANUAL_TEST.md is the checklist for each release.
Licence
MIT. fm-mcp is not affiliated with or endorsed by Apple. It calls the fm tool installed on your Mac and includes nothing from Apple.
来源:README.md,提交 831d5dd
工具
0版本历史
1- v0.1.0最新Oct 10, 2026

