claude-faf-mcp
Home: faf.one/mcp
Site: claude.faf.one
Persistent Project Context with Memory, looped for you. One-click setup. 30 seconds. π Nelly Never Forgets.
FAF defines. MD instructs. AI codes.
β Bookmarks it for you, helps other devs find it too.
v0.2-conformant reader of the FAF Context Ingestion Contract.
π tri-sync |
.fafβMEMORY.md(faf_tri_sync), alongside.fafβCLAUDE.md(faf_sync).
β‘ The
fafprompt β pick it from your host's prompt list (Claude Code shows it as/mcp__<server name>__faf). It scores your project, fills what the repo can, asks you only what only you can answer, verifies, and syncs.
6.0.0 is a major release. It needs Node 22 or later.
faf_clear,faf_friday,faf_guideandfaf_writeare retired, and so are the AGENTS.md / .cursorrules / GEMINI.md / conductor imports into project.faf. The.mcpbnow runs the server bundled inside it. The npx config and the SessionStart hook are not pinned to a version, so an install that runsnpx -y claude-faf-mcpmoves to 6.x on its next start: check your Node before you upgrade. Every change is in the CHANGELOG.
Context for Claude: faf-cli writes this repo's CLAUDE.md from its scored project.faf β faf_sync here, faf sync in faf-cli. See FAF-CLI for Claude Code π.
Composes faf-cli (the version is pinned in package.json). Detection, scoring, the renders and every writer are faf-cli's own functions, loaded as a dependency; claude-faf-mcp does not fork them and never runs a faf found on your PATH.
Core 14 MCP tools (30 with FAF_TOOLS=all). IANA-registered formats (application/vnd.faf+yaml Β· application/vnd.fafm+yaml).
What's New in v6.0.0 β The Earned Badge Edition
Every badge earned, none claimed: claude-faf-mcp 6.0 composes faf-cli, touches only what it wrote, and every tool tells the truth β one score, facts from repo, nothing from your PATH.
- Composes faf-cli 7.13. Detection, scoring, the renders and every writer are faf-cli's own functions. claude-faf-mcp never runs a
fafit finds on your PATH. - Touches only what it wrote.
- Every write is atomic and goes through faf-cli's safe path, and a file that links out of the project is refused.
- project.faf edits keep your comments and exact values.
- Your soul.fafm and Claude's own MEMORY.md notes stay as you left them.
- One score. Every tool shows faf-cli's score, and βͺ appears only at 100%.
- Facts from repo. Every empty slot says what fills it:
- a fact from repo, which
faf_autowrites; - no fact in repo, which you answer with
faf_go; - or yours, for the 6Ws.
- a fact from repo, which
- Tools that tell the truth.
- Every title, hint and schema matches what the tool does, and bad arguments are refused before anything runs.
- Core 14:
faf_setupandfaf_tri_syncjoin the default list.
- Safe with any repo.
- A cloned repo's symlinks never reach your AI's context.
faf_goanswers can't pollute objects.- The file tools stay inside the active project.
- Ships what it runs. The
.mcpbruns the server bundled inside it, and it's started and checked before its sha is recorded. Node 22+, with CI on Node 22 and 24 across Ubuntu, macOS and Windows. - Retired:
faf_clear,faf_friday,faf_guide,faf_write, the interop imports into project.faf, andfaf_checkprotect/unlock. The archive tagarchive/cfm-v5-surfacekeeps them.
The 3Ws β 3 Answers. That's It.
Every great product started with 3 answers to the 3Ws β Who, What, Why:
| WHO is it for? | WHAT does it do? | WHY build it? | |
|---|---|---|---|
| Uber | People who need a ride | Tap a button, car arrives | Taxis were broken |
| Airbnb | Travelers who can't afford hotels | Stay in someone's spare room | Millions of empty rooms exist |
| Slack | Teams drowning in email | Organized group messaging | Decisions buried in threads |
| Venmo | Friends splitting bills | Send money instantly | Someone always forgets to pay back |
Same pattern. Every product that works starts here. .faf captures it:
human_context:
who: "people who need a ride across town"
what: "tap a button, car arrives in minutes"
why: "taxis are slow, expensive, and hard to find"30 seconds. Claude builds your project.faf from this. Every session after, AI starts smart.
The 6Ws β For Optimized AI
3Ws gets you started. For fully optimized AI, complete the set β Where, When, How:
where: "mobile app, iOS and Android" # where does it live?
when: "launch in 3 months" # when is it shipping?
how: "GPS matching, real-time pricing" # how does it work?3Ws initiates the project with AI. 6Ws optimizes AI to 100%. Same YAML, same file. More examples β faf.one/ideas
Quick Start
Needs Node 22 or later.
Claude Desktop β one click
β¬ Download claude-faf-mcp-6.0.0.mcpb
Open it in Claude Desktop. The extension runs the server bundled inside it (no npx, no network at start) and lists the Core 14 tools.
Claude Desktop β config
Add to claude_desktop_config.json, then restart Claude Desktop:
{
"mcpServers": {
"faf": { "command": "npx", "args": ["-y", "claude-faf-mcp"] }
}
}After npm install -g claude-faf-mcp you can use the installed bin instead: { "command": "claude-faf-mcp" }. With Bun on Claude Desktop's PATH, { "command": "bunx", "args": ["claude-faf-mcp"] } works too.
Claude Code
claude mcp add faf -- npx -y claude-faf-mcpPinning
The npx config and the SessionStart hook faf_setup installs (npx -y claude-faf-mcp --session-refresh) are not pinned: they run the latest release, so fixes arrive without a reinstall, and a new major arrives the same way. To stay on a major, write it in your config yourself: "args": ["-y", "claude-faf-mcp@6"]. The .mcpb runs the version it was built from.
Then
Run the faf prompt β Claude scores your project, fills what the repo can, asks you what only you can answer, verifies and syncs.
Or tell Claude your 3Ws: "I'm building [what] for [who] because [why]"
faf-cli β any terminal
npx faf-cli autoSame .faf, every surface β Claude, Gemini, Grok, Cursor. faf-cli on npm β
How It Works
You β 3 answers β project.faf β AI reads it β every session β forever
project.faf βββ CLAUDE.md (faf_sync)
project.faf βββ MEMORY.md (faf_tri_sync π)
Language, framework, package manager, build tools β faf-cli detects them from your existing files. The human context is the part only you can give.
For Claude Code teams
.faf lives in the repo. Your context travels with the code β committed, versioned, done.
Every session starts grounded. Install the native SessionStart hook once (faf_setup β preview first, your settings preserved). After that, every Claude Code session opens with a one-line heartbeat instead of a blank slate:
faf: context βͺ 100% β fresh Β· +7 intent the code can't carry
That line is the relay: Claude already knows your stack and your score β and the +N is the intent the code can't carry: the goal and 6Ws only you can give or confirm. No re-explaining "what this project is" at the top of every session.
It scales to the team by construction:
commit project.faf β every teammate's Claude starts with the same context
git clone β a new dev's Claude is grounded before they write a line
- One source of truth.
faf_syncwritesCLAUDE.mdfrom.fafβ only its faf-managed block, so your own notes stay put. AddMEMORY.mdfor cross-session memory (tri-sync π). - No drift. The score is deterministic β same
.faf, same number, on every machine and in CI. A teammate can't be accidentally less grounded than you. - Local. No accounts, no telemetry, nothing sent to FAF. The one network use is cloning a repo you name, only when you ask (privacy). The context is yours; it rides in the repo.
Onboarding becomes git clone β grounded. The context a new teammate would normally pick up by asking around is already in the repo, machine-readable, from the first clone.
Scoring: From Blind to Optimized
| Tier | Score | What it means |
|---|---|---|
| βͺ TROPHY | 100% | Gold Code β AI is optimized |
| β GOLD | 99%+ | Near-perfect context |
| β SILVER | 95%+ | Excellent |
| β BRONZE | 85%+ | Production ready |
| β GREEN | 70%+ | Solid foundation |
| β YELLOW | 55%+ | AI flipping coins |
| β RED | <55% | AI working blind |
| β‘ WHITE | 0% | No context at all |
At 55%, AI guesses half the time. At 100%, AI knows your project. The score is faf-cli's scoreFafYaml β the number faf score prints for the same file.
MCP Tools β Core 14, 30 with FAF_TOOLS=all
By default claude-faf-mcp lists the Core 14 β the lifecycle tools you reach for. Set FAF_TOOLS=all to list the Extended tools too; every tool is callable by name either way. Retired in 6.0.0: faf_clear, faf_friday, faf_guide and faf_write (a call by name returns one line naming what to use instead), the AGENTS.md / .cursorrules / GEMINI.md / conductor imports into project.faf, and faf_check protect/unlock.
Every tool runs on the faf-cli this package depends on. Nothing is run from your PATH.
Core
| Tool | Purpose |
|---|---|
faf_init |
Create project.faf for a folder (faf-cli detects the stack) |
faf_auto |
Fill project.faf from the repo's own files, then CLAUDE.md |
faf_go |
The goal and the 6Ws, by question and answer |
faf_score |
AI-readiness score (0-100%), from faf-cli |
faf_bench |
Benchmark AI grounding β cold vs with the .faf, graded mechanically, with a receipt |
faf_doctor |
Diagnose project.faf: each finding with the tool that fixes it |
faf_trust |
Validate project.faf and return a trust receipt for its score |
faf_sync |
Write CLAUDE.md from project.faf β agents/cursor/gemini/copilot/all also write AGENTS.md / .cursorrules / GEMINI.md / copilot-instructions.md |
faf_tri_sync |
Write faf's block into the MEMORY.md Claude Code loads for this project π |
faf_setup |
Install the SessionStart hook in the project settings (preview first) |
faf_context |
Show or set the active project; detail returns the .faf text |
faf_etch |
Remember a decision across sessions (the project soul, soul.fafm) |
faf_recall |
Recall memories from the project soul |
faf_about |
What the .faf format is |
Extended (FAF_TOOLS=all)
| Tool | Purpose |
|---|---|
faf |
Start here: the project, its score and the steps to 100% (reads only) |
faf_quick |
Create project.faf from one line: name, goal, language, framework, hosting |
faf_readme |
Read the 6Ws from README.md; apply fills only empty slots |
faf_human_add |
Set one 6W slot in project.faf |
faf_formats |
The formats faf-cli finds in the folder, and what faf_auto would write (dry run) |
faf_git |
Author a project.faf from a repo URL (clones it with git β uses the network) |
faf_check |
faf-cli's validateFaf and the state of every slot |
faf_dna |
The project's .faf-dna lineage (reads only) |
faf_status |
Whether the project has a .faf, with its first lines |
faf_agents |
Write AGENTS.md (OpenAI Codex and other agents) |
faf_cursor |
Write .cursorrules (Cursor IDE) |
faf_gemini |
Write GEMINI.md (Google Gemini CLI) |
faf_conductor |
Write Google Conductor's conductor/ files |
faf_read |
Read a file inside the active project |
faf_list |
List a folder inside the active project |
faf_debug |
The active project, write access and the bundled faf-cli version |
π Nelly Never Forgets
faf_sync writes CLAUDE.md from .faf, so the two stay aligned.
tri-sync adds MEMORY.md β your AI remembers your project across every session.
faf_sync = .faf β CLAUDE.md β written from .faf
tri-sync = .faf β MEMORY.md (faf_sync writes CLAUDE.md) β Nelly never forgets π
Pro feature, free for developers. Teams & Enterprise: faf.one/pro (plans)
The .FAF Position
Model Context Protocol
βββββ βββββββ ββββββββ
Claude β .faf β MCP
Gemini β .faf β MCP
Codex β .faf β MCP
Any LLM β .faf β MCP
IANA-registered (application/vnd.faf+yaml). One file, one format. Define once, use everywhere.
Ecosystem
| Package | Platform | Registry |
|---|---|---|
| claude-faf-mcp (this) | Claude | npm |
| faf-cli | CLI | npm + Homebrew |
| gemini-faf-mcp | Google Gemini | PyPI |
| grok-faf-mcp | xAI Grok | npm |
| rust-faf-mcp | Rust | crates.io |
| faf-wasm | Browser/Edge | npm |
| Chrome Extension | Browser | Chrome Web Store |
Same project.faf. Same scoring. Same result. Different execution layer.
Quality
Tests run with bun on ubuntu, macOS and Windows; the built package is packed, installed and started on Node 22 and 24 on all three. CI β
Privacy
claude-faf-mcp runs on your machine. No analytics, no telemetry, no accounts. Its one network use is faf_git, and only when you ask it to read a repo: git clones it from the URL you give. The files it writes are listed in the privacy policy β
If claude-faf-mcp has been useful, consider starring the repo β it helps others find it.
Citation
If you use claude-faf-mcp or the .faf / .fafm / .fafa formats in research or production, please cite the format papers:
Wolfe, J. (2025). Format-Driven AI Context Architecture: The .faf Standard for Persistent Project Understanding. Zenodo. https://doi.org/10.5281/zenodo.18251362
Wolfe, J. (2026). Permanent Memory and Instant Recall: The .fafm Standard for Multi-Profile AI Agent Memory. Zenodo. https://doi.org/10.5281/zenodo.20348942
Wolfe, J. (2026). Why Agents Need a Passport: .fafa β Portable Identity for the Agentic Era. Zenodo. https://doi.org/10.5281/zenodo.21951641
BibTeX
@article{wolfe2025faf,
title = {Format-Driven AI Context Architecture: The .faf Standard for Persistent Project Understanding},
author = {Wolfe, James},
year = {2025},
month = {nov},
publisher = {Zenodo},
doi = {10.5281/zenodo.18251362},
url = {https://doi.org/10.5281/zenodo.18251362}
}
@article{wolfe2026fafm,
title = {Permanent Memory and Instant Recall: The .fafm Standard for Multi-Profile AI Agent Memory},
author = {Wolfe, James},
year = {2026},
month = {may},
publisher = {Zenodo},
doi = {10.5281/zenodo.20348942},
url = {https://doi.org/10.5281/zenodo.20348942}
}
@article{wolfe2026fafa,
title = {Why Agents Need a Passport: .fafa β Portable Identity for the Agentic Era},
author = {Wolfe, James},
year = {2026},
month = {aug},
publisher = {Zenodo},
doi = {10.5281/zenodo.21951641},
url = {https://doi.org/10.5281/zenodo.21951641}
}License
MIT β Free and open source
FAF Family
| faf-cli | npx faf-cli init β create .faf for any project |
| claude-faf-mcp | MCP server for Claude Desktop |
| gemini-faf-mcp | MCP server for Gemini CLI |
| grok-faf-mcp | MCP server for Grok |
| faf-mcp | MCP server for Cursor, Windsurf, Cline, VS Code |
| rust-faf-mcp | MCP server in Rust |
| faf-skills | Claude Code skills for .faf |
| faf.one | Blog, downloads, docs |
| IANA: vnd.faf+yaml | Context format (2025-10-30) |
| IANA: vnd.fafm+yaml | Memory format (2026-05-13) |
format | driven ποΈβ‘οΈ wolfejam.dev
Get the CLI
faf-cli β The original AI-Context CLI. A must-have for every builder.
npx faf-cli autoMCP Registry: one.faf/claude-faf-mcp Β· 2 IANA registrations: vnd.faf+yaml (Context) Β· vnd.fafm+yaml (Memory) Β· faf.one Β· npm
Zero-Config. Context that's just there β every session.