Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Runs on your computer
fm-mcp
Overview
Description from the maker (original English)
Delegate summarising, extraction, classification and OCR to the macOS 27 on-device model.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiVery new★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Other
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
The maker has not listed install details in the registry. See the maker’s README below.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account yrangana, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Otheri
- More stars than 0% of the other 18665 servers in this category
- Published to the registry more recently than 67% of the other 18665 servers in this category
- Basic checks equal to or better than 100% of the other 18665 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is fm-mcp safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.1.3) reached the registry 21 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Rust on your computer.
What can I use instead?
In the same category: Spec Driven Development, Remote Desktop Commander, Systemdox
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Remote Desktop Commander
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Runs in the cloud✓ desktopcommander.app
Systemdox
Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
Runs on your computer
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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
Site: yrangana.github.io/fm-mcp, with what we learned building it: the measured limits of the on-device model.
Created by Yasiru Rangana, AI Architect and AI Engineer, Sydney.
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
fm-mcp is a public beta (0.1.x): it works and is tested, but tool details may change between releases. CHANGELOG.md lists what changed.
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). That's the whole support policy: fm-mcp doctor checks each of these, and nothing else is supported.
No Homebrew yet? Install it from brew.sh first. Its installer asks to install Xcode's command line tools: accept, and let it finish.
brew install yrangana/tap/fm-mcpfm-mcp install # sets up Claude Code and Codex fm-mcp doctor # checks everything fm-mcp needs
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:
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/yrangana/fm-mcp/releases/latest/download/fm-mcp-installer.sh | shcargo install fm-mcp
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.
/plugin marketplace add yrangana/fm-mcp/plugin install fm-mcp@fm-mcp
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:
"fm-mcp": {"command": "/opt/homebrew/bin/fm-mcp", "args": [] }
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:
"fm-mcp": {"type": "stdio", "command": "/opt/homebrew/bin/fm-mcp", "args": [] }
Tools
| Tool | What it does | How much it takes |
|---|---|---|
summarise | Condenses logs, documents, notes and transcripts into a gist: a paragraph, or at most 7 bullets. Not a full record. | About 30,000 words of prose, but only about 1,000 lines of a dense log. Long input is split and combined, which takes a minute or two and can drop details. |
extract | Pulls named fields out of one text as JSON, from a JSON Schema you give. Works best with a flat schema. | About 3,500 words of prose. |
classify | Sorts one text into labels you choose (one label, or several with multi). | About 3,500 words of prose. |
ocr | Reads the text in a PNG, JPEG, HEIC, TIFF, GIF or BMP image. Not PDF. | One image. |
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. docs/TOOLS.md lists every parameter, with example calls.
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.
extractoften returnsnullfor a field the text doesn't contain, but not reliably: on short invoices a missing PO number took the supplier's name in 10 of 25 runs. When the model gets stuck on a field, fm-mcp keeps the finished fields, sets the stuck one tonulland says so; that call takes about 15 s. Ask only for fields the text is likely to have. 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. SECURITY.md has the details, and how to report a security problem privately.
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.
| Problem | Fix |
|---|---|
| Licence not agreed | Run fm license once. |
| Model not available | Turn on Apple Intelligence in System Settings and wait for the model to finish downloading. |
| A tool says the model "got stuck" | Usually a schema with fields the text doesn't contain, or another session using the model. Try a flatter schema. |
| A tool times out on long input | Raise the limit: set FM_MCP_REQUEST_TIMEOUT_SECS (default 120) in the MCP server's environment. |
| You need more detail | Set FM_MCP_LOG=debug in the MCP server's environment. fm-mcp logs to stderr only (stdout carries the MCP protocol). |
Uninstall
fm-mcp install --uninstallbrew uninstall fm-mcp
Development
git clone https://github.com/yrangana/fm-mcp.gitcd fm-mcp cargo build --release ./target/release/fm-mcp install # points your agents at this build
cargo test --features fake-fm # needs no Apple Intelligence: uses a fake fm cargo clippy --all-targets --all-features -- -D warnings cargo fmt --check scripts/real_fm_smoke.sh # checks against the real fm on this Mac
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.
Created by Yasiru Rangana.