one.fafPublished by faf.onev2.2.4Updated Nov 6, 2026
Persistent project context for xAI Grok. IANA-registered .faf format.
The publisher's own server: Surface
Gives an assistant a persistent project context file (.faf) and memory layer (.fafm): score, create, validate, sync and re-ground on project DNA.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
Persistent Project Context for xAI Grok.
URL-based • Zero config • Just works
[IANA: vnd.faf+yaml] [DOI: Context paper] [DOI: Agents paper]
Home: faf.one/grok Live demo: grok.faf.one
⭐ Star faf-cli on GitHub, the CLI this server is built on: bookmarks it for you, helps other devs find it too.
[Stars] [Downloads] [Business card · Get yours →]
FAF defines. AGENTS.md instructs. AI codes.
faf_sync keeps your hand-written files, writes the context files it names, and tells you what it couldn't write. Managed blocks now go through faf-cli's injector, so a hand-written AGENTS.md or CLAUDE.md is never reclaimed; faf_sync writes the context files it names, one file at a time, and the reply says what it couldn't write and why.
faf_write can no longer overwrite the birth certificate or your context files. .faf-dna is refused in every spelling and route, existing project.faf, CLAUDE.md and AGENTS.md need overwrite: true, and writes stay inside the project folder.
Cleanup: removes leftover two-way sync wording. Two-way sync was dropped by design long ago: project.faf pushes structured data out, and prose doesn't come back. The last strings that still said two-way now match. faf_bi_sync still works as the old name for faf_sync.
One rule for project questions: read project.faf first. New line 2 of the server instructions: "For questions about the project (stack, goal, commands), read project.faf first and answer from it." The same rule in faf-mcp moved Grok Build from 0 of 3 to 2 of 3 runs reading project.faf first, on a repo where project.faf and package.json disagree (3-run pilot). 715 characters.
grok-faf-mcp now tells Grok how its tools fit together, context and memory: server instructions in initialize (615 characters), plus faf-cli 8.5.0, which knows a skills repo when it sees one.
rag_query needs an xAI Collection.faf_init detects a skills repo: SKILL.md folders make it skills (10 slots), and a Claude Code plugin manifest makes it skills-plugin (14).Earlier: v2.1.0 — The New Era Edition — glass-box tools: every tool says if it reads, writes or rewrites; its own FAF passport at grok.faf.one; a new look.
Earlier: v2.0.0 — The Always33 Edition — one engine, one number: every score is faf-cli 8's always-33 kernel, on npm and on mcpaas.live. ZEPH is opt-in until the Zig engine is always-33.
☆ Bookmark grok.faf.one for later.
First v0.2-conformant reader of the FAF Context Ingestion Contract — the open standard co-authored in public with @grok.
Add to ~/.grok/config.toml:
Restart Grok TUI (or /mcps r) to refresh. The hosted endpoint scores always-33 — the same number as the npm package. Tools: faf_score, faf_validate, faf_get_tier, faf_estimate_tokens, faf_analyze (plus soul/memory ops).
Smithery: wolfe-jam/grok-faf-mcp — gateway at https://grok-faf-mcp--wolfe-jam.run.tools
Homebrew (local stdio):
Hosted on Cloudflare Workers — sub-ms cold start, no subprocess, edge-served. Scores and validates with the faf-kernel WASM (always-33, the same engine as the npm package) since mcpaas-cf 1.8.1; a Zig WASM engine handles token estimates and tier. Externally validated by Grok S1 + S2 on 2026-05-27.
Verify the live contract:
Returns endpoint, protocol versions, engine details, tool list, and the architecture line: .faf=vROM | AI-in-session=RAM.
Sample corpus: xai-faf-proof/pilot — 10 records ready to score.
Every README should answer these questions. Here's ours:
For AI: Read the detailed sections below for full context. For humans: Use this pattern in YOUR README. Answer these 6 questions clearly.
Built for Grok and shaped by direct Grok feedback.
Open for native Grok Build integration, .fafm memory layer, refresh_faf primitives, or any other context features the team needs.
Live and dogfooded at https://grok.faf.one and https://mcpaas.live/grok/mcp/v1.
Context for Grok agents: faf-cli authors what Grok agents read from real project detection — bunx faf export --agents. faf-cli's src/interop/grok.ts wires this MCP into .grok/config.toml (that file lives in the faf-cli repo, not here). See FAF-CLI for Grok & xAI agents.
Every Grok session starts from zero. You re-explain your stack, your goals, your architecture. Every time.
.faf fixes that. One file, your project DNA, persistent across every session.
faf_auto detects your project, creates a .faf, and scores it — in one shot:
What it produces:
Every AI agent reads this once and knows exactly what you're building.
MCP on a URL. Point your Grok integration at the URL. That's it.
At 55%, Grok guesses half the time. At 100%, Grok knows your project.
Point your MCP client at the production URL — edge-served on Cloudflare Workers, no subprocess, sub-ms cold start. WASM-pure tools only on this path (scoring, validation, refresh_faf).
Use the local stdio path when you need filesystem access (faf_init, faf_sync, file-mutating tools):
Or via MCP config:
Create & Detect
Drift & Orchestration (1.5 — the prestige release)
Sync & Persist
Read & Write
RAG & Grok-Exclusive
Plus 34 advanced tools available with FAF_SHOW_ADVANCED=true.
Benchmarked 10x per tool, warmed up, on local stdio execution. Hosted edge adds sub-ms cold start on top.
Orchestrator (faf_orchestrate_recommendation) characteristics: composition call — reads up to 6 files (.faf, .fafm, package.json, CHANGELOG.md, README.md, plus all 3 receipt logs), runs 2 analyzers (detectFafmDrift + checkId), evaluates the decision table, writes 1 receipt. Expected latency: tens of ms on warm cache; higher under cold-disk or very large .fafm corpora. Designed for occasional agent-initiated calls, not per-turn polling. detectFafmDrift is O(n²) in fact count (cross-fact n-gram recurrence) — comfortable up to ~hundreds of facts.
Production deployment: Cloudflare Workers via mcpaas-cf (serving mcpaas.live/grok/mcp/v1). The api/index.ts + vercel.json paths above stay alive as a catch-site for legacy/bookmarked links — they are no longer the production path.
Scoring pipeline: faf-cli's scoreFafYaml → the always-33 kernel (faf-scoring-kernel, Rust → WASM) scores the file as written: 33 slots, slotignored slots drop out of the denominator. No per-type rewriting, no fallback scorer — the same number faf-cli, claude-faf-mcp and faf-mcp give.
WJTTC parity (heavy local ↔ light hosted) + full suites (green on CI):
v2.2.0 — The Instructions Edition — server instructions in initialize (615 characters) and faf-cli 8.5.0, which detects skills repos. Scoring is unchanged from v2.0.0.
v2.1.0 — The New Era Edition — glass-box tools (every tool labelled read, write or rewrite), its own FAF passport at grok.faf.one, a new look. Scoring is unchanged from v2.0.0.
v2.0.0 — The Always33 Edition — one engine, one number: faf-cli 8's always-33 kernel on npm and on mcpaas.live. ZEPH is opt-in until the Zig engine is always-33. FafCompiler upgraded to the Always33 fafb model — parity across frontier models, Enterprise/Teams ready.
Everything below still applies; operating it honestly means surfacing what's NOT in here alongside what is.
Earlier: v1.10.0 — The No-Fluff Edition — no fluff in a project.faf.
faf_enhanceis gone. RAG default isgrok-4.6. Fill stays onfaf_auto/faf_go.
Earlier: v1.9.0 — The ZEPH Default Edition — the proven-fast Zig→WASM scoring path behind
refresh_fafis now default-ON (same score, cheaper to compute; parity proven byte-identical — CI gate + 91/91 live). Kill switchUSE_ZEPH=0forces the canonical scorer. FRC tools stay opt-in behindUSE_FRC.
Earlier: v1.8.0 — The Closed-Loop Edition — observability writes, token math is honest, FRC contract locked. The drift→refresh→re-ground loop can finally be measured. Earlier: v1.7.0 — The Grounded Memory Edition — ZEPH + the FRC layer over Grok Collections (
faf_gate/faf_section/faf_memory), opt-in viaUSE_FRC/USE_ZEPH; 12-tool core unchanged. Earlier: v1.6.0 — The ZEPH Edition — the ZEPH fast path for re-grounding (refresh_faf/refresh_blendvia Zig→WASMcascade.wasm, ~12µs,USE_ZEPH=1;faf-clistays canonical, parity locked in CI).
What is fully supported:
https://mcpaas.live/grok/mcp/v1 and client-specific routes) — scoring · validation · refresh_faf · a content-in faf_orchestrate_recommendation · the FRC trio · souls and search. The live list is at …/grok/mcp/v1/info.refresh_faf and refresh_fafm as explicit, callable re-grounding primitives.refresh_blend as the baked-in two-intensity refresh (Cmd+R / Cmd+Shift+R analog).faf_orchestrate_recommendation — the heavy orchestrator that composes drift signals, recurrence, receipts, and take-a-hint into an advisory recommendation.faf_get_orchestration_policy — pure introspection of the effective policy without running the orchestrator (no drift detection, no receipt write — the quietest tool in the substrate).effective_policy) returned on every orchestration call AND surfaced standalone via faf_get_orchestration_policy.Current limitations:
faf_get_orchestration_policy, refresh_fafm, refresh_blend, faf_init and faf_sync need filesystem access and run only on the local stdio path (bunx grok-faf-mcp / npx grok-faf-mcp). The hosted faf_orchestrate_recommendation takes file contents instead of reading your repo, and has no receipts or recurrence history (it reports those under partial[])..faf:orchestration:tier reads 'conservative' (default — quietest, no noisy first-impression) · 'balanced' · 'aggressive'. active_tier always surfaced in hints.effective_policy for observability, and standalone via faf_get_orchestration_policy. The policy WRITER (faf_set_orchestration_policy) and scheduling (faf_schedule_heavy_re_ground) are not included in v1.5 — edit .faf:orchestration:tier: directly to override.acknowledged: false by default, never auto-flipped. Take-a-hint's ladder-reset semantics fire only on explicit ack — conservative by intent. Future task: explicit ack tool OR derived-from-subsequent-refresh-receipt timing.The honest split is intentional: hosted = fast, auditable, WASM-pure; local = full capability including filesystem. We will expand the hosted surface only where it can be done safely and without compromising the model.
Subordinate-not-daemon throughout. The orchestrator NEVER auto-fires the recommended tool. Agents surface the recommendation; the user (or higher agent) decides whether to act. Even severity: 'block' is advisory.
See the public verifier and curl https://mcpaas.live/grok/mcp/v1/info for the current contract.
One format, every AI platform.
Same project.faf. Same scoring. Same result. Different execution layer.
grok-faf-voice (VML).fafm 🐘🎙️ — the voice variant of the .faf 🐘 family.
grok-faf-voice is the reference implementation of the Voice Memory Layer (VML) — what your voice agent remembers across sessions, devices, and model switches. Companion to grok-faf-mcp:
grok-faf-mcp (this) — .faf Foundational Context Layer for Grok via MCP-on-a-URL.grok-faf-voice — .fafm Voice Memory Layer (VML) for Grok Voice via LiveKit + xAI realtime.Same family. Different surface. Voice swappable; memory permanent.
PyPI · GitHub · Onboarding
This MCP server was built for Grok and continues to be shaped by direct feedback from Grok itself.
Open for deeper collaboration on:
I ship fast, test rigorously, and dogfood everything live on https://grok.faf.one and https://mcpaas.live/grok/mcp/v1.
Happy to:
Real software only. Just say the word.
PR conventions, code style, CI doctrine, MCP-tool contribution path, npm publish discipline, architecture decisions: CONTRIBUTING.md.
xAI / Grok devs welcome — TL;DR setup at the top.
Open for deeper native integration, .fafm memory layer, or Grok Build CLI collaboration.
Happy to ship PRs, dogfood, or jump on a call. Just say the word.
If you use grok-faf-mcp or the .faf / .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). Why Agents Need a Passport: .fafa — Portable Identity for the Agentic Era. Zenodo. https://doi.org/10.5281/zenodo.21951641
MIT — Free and open source
Built for Grok. Built for Speed. Built Right.
FAST⚡️AF • First to Ship • Zero Friction
Zero drift. Eternal sync. AI optimized. 🏆
faf-cli — The original AI-Context CLI. A must-have for every builder.
Anthropic MCP #2759 · IANA Registered: application/vnd.faf+yaml · faf.one · npm · Talk to my Agent →
Source: README.md at commit c78d1b3
Score a project's AI-readiness 0–100% against the fixed 33-slot context model — how much project DNA an agent has before it has to guess. Deterministic: the same .faf always scores the same. Returns the score, tier, and per-slot breakdown.
detailsRe-ground on the live .faf — re-read + re-score the current project DNA, report drift vs your last-known score, and return the fresh context. The explicit re-grounding primitive for long sessions: drift → refresh → re-grounded. Built for Grok, by request.
pathbaselineReload the latest structured memory (`.fafm`) for one or more souls into the current session. Returns a stamped delta by default (added/updated facts since last refresh or a given timestamp). Use `verbatim: true` to receive the full current `.fafm` content instead. Reads your files and writes a refresh receipt (.fafm-refresh-receipts.json) to the project folder. Always returns a content hash + timestamp stamp. Complements `recall`, `load_soul`, and `etch` — does not replace them.
soulsinceverbatimHeavy orchestrator — given current substrate state, returns a structured recommendation about drift: which refresh to call (or `no_action`), why, how severe, and the underlying signals. ADVISORY ONLY — never auto-fires. Composes the full 1.5 substrate (drift detection · contradiction check · repeat-offender · take-a-hint · refresh history). Writes a recommendation receipt on every call (auditable trail, no silent decisions). Read-only WRT substrate state.
Takes no parameters.
Introspect the effective orchestration policy WITHOUT running the orchestrator. Returns `{ tier, thresholds, source, overrides_applied }` — what aggressiveness tier the next `faf_orchestrate_recommendation` call would use, and whether it came from defaults or a `.faf:orchestration:` override. No drift detection, no signals, no receipt — pure introspection. Read-only.
pathBaked-in two-intensity refresh (Cmd+R / Cmd+Shift+R analog). Fires BOTH `refresh_faf` + `refresh_fafm` in one call. `mode: "blend"` (default) = light `.faf` + delta `.fafm` — the everyday re-ground. `mode: "nuke"` = light `.faf` + verbatim `.fafm` — the hard reload for polluted session memory. Intensity matches drift rate per layer.
modepathsoulsincebaselineInitialize project.faf
Create a project.faf — the IANA-registered context file (application/vnd.faf+yaml) that gives Grok persistent project DNA (stack, structure, intent) in one portable file, so an agent reads the whole project cold each session instead of re-discovering it. Writes project.faf to the target directory (created if missing) and refuses to overwrite an existing context file unless `force` is set. Run once at project start, or with `force` to regenerate, then call faf_score to check readiness. Returns a text confirmation with the written file path and the detected project type.
pathforcedirectoryprojectNameValidate a project.faf with faf-cli — confirm the context file is well-formed and parses cleanly before an agent grounds on it, and report its always-33 score. The pre-flight trust check: never build on a broken context layer.
pathSync project.faf into your AI context files: the ones that exist (CLAUDE.md, .cursorrules, .windsurfrules, .clinerules), or CLAUDE.md when there are none (target: all writes every one). Non-destructive: puts a structured .faf block at the top and keeps your own text; a file faf cannot safely write (not UTF-8, a link out of the project) is left unchanged and named in the reply. One way: never writes project.faf.
targetAsk a question with RAG-enhanced context from xAI Collections. Uses LAZY-RAG cache for 100,000x speedup on repeated queries.
questionrequiredGet LAZY-RAG cache statistics - hits, misses, hit rate, cache size
Takes no parameters.
Clear the LAZY-RAG cache — drop all cached retrievals so the next rag_query rebuilds from source. Use when the underlying context has changed and you want fresh results instead of cached ones.
Takes no parameters.
90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
me.grok.nova-otter-delta-cloudOfficial publisher
Remote MCP server that unwraps short links and returns a fetch-or-skip verdict before an assistant opens a pasted URL.
dev.fly.grok-backtest-apiOfficial publisher
Remote MCP server for pay-per-call crypto quant tools: survivorship-bias-free backtests, daily market signals, strategy optimization and token scam checks.
Published by GitHub account Surface-ops
Sends server-side conversion events to ad platforms (Meta live, Google and LinkedIn preview) and reports workspace event stats.
Published by GitHub account Surface-ops
API Meter counts API requests per customer, endpoint and plan, and lets an assistant sign up an API, get ingest snippets and read or export usage.
Published by GitHub account nirholas
Remote three.ws MCP server that turns text or image prompts into textured, riggable 3D models and avatars, and lets an assistant reuse them as persistent…
[mcp_servers.grok-faf-mcp]url = "https://mcpaas.live/grok/mcp/v1"brew install wolfe-jam/faf/grok-faf-mcpcurl https://mcpaas.live/grok/mcp/v1/infoWithout .faf → "I'm building a REST API in Rust with Axum and PostgreSQL..."With .faf → Grok already knows. Every session. Forever.faf_auto━━━━━━━━━━━━━━━━━Score: 0% → 85% (+85) ◇ BRONZESteps: 1. Created project.faf 2. Detected stack from package.json 3. Synced CLAUDE.md
Path: /home/user/my-project# project.faf — your project, machine-readablefaf_version: "3.3"project: name: my-api goal: REST API for user management main_language: TypeScriptstack: backend: Express database: PostgreSQL testing: Jest runtime: Node.jshuman_context: who: Backend developers what: User CRUD with auth why: Replace legacy PHP serviceURL: https://mcpaas.live/grok/mcp/v1Format: IANA-registered .faf (application/vnd.faf+yaml)Tools: 12 core by default (bunx) — re-grounding (refresh_faf/fafm/blend), LAZY-RAG, orchestration substrate, FAF essentials · extended utilities via FAF_TOOLS=all · 19 hosted (WASM-pure, served by mcpaas-cf) on the URLEngine: faf-cli 8 — faf-scoring-kernel 3.0.0 (Rust → WASM, always-33)Speed: 0.5ms average (was 19ms — 3,800% faster with Mk4)Tests: WJTTC parity (heavy local ↔ light hosted) + full suites. Runner: sh scripts/run-tests.sh (bun + flake retry)Status: FAST⚡️AF{ "mcpServers": { "grok-faf": { "url": "https://mcpaas.live/grok/mcp/v1" } }}brew install wolfe-jam/faf/grok-faf-mcp # macOS tap# orbunx grok-faf-mcp{ "mcpServers": { "grok-faf": { "command": "bunx", "args": ["grok-faf-mcp"] } }}Execution: 0.5ms average (97% faster than v1.1)Fastest: 3,360ns (version — nanosecond territory)Slowest: 1.3ms (score — Mk4 WASM)Improvement: 19ms → 0.5ms (3,800% faster)Engine: faf-cli 8 (faf-scoring-kernel 3.0.0, always-33)Memory: Zero leaksTransport: stdio (local, bunx) · Streamable HTTP (hosted, Cloudflare Workers)grok-faf-mcp├── src/│ ├── server.ts → MCP server (GrokFafMcpServer)│ ├── handlers/│ │ ├── championship-tools.ts → 55+ tool definitions│ │ ├── tool-registry.ts → Visibility filtering (core/advanced)│ │ └── engine-adapter.ts → FAF engine bridge│ ├── faf-core/commands/score.ts → faf-cli scoreFafYaml (always-33)│ ├── types/ → Canonical type substrate (1.5)│ │ ├── drift-signals.ts → DriftSignal · Contradiction · RepeatOffender│ │ ├── refresh.ts → RefreshMode│ │ ├── escalation.ts → EscalationLevel│ │ ├── recommendation.ts → RecommendationAction│ │ └── receipts.ts → ReceiptMetadata│ ├── detection/fafm-drift.ts → detectFafmDrift() — repetition-rate gauge│ ├── integrity/check-id.ts → checkId() — cross-stamp contradiction check│ ├── orchestrator/│ │ ├── repeat-offender.ts → RepeatOffenderTracker│ │ ├── take-a-hint.ts → evaluateTakeAHint() — escalation ladder│ │ ├── refresh-blend.ts → runRefreshBlend()│ │ └── recommendation.ts → analyzeAndRecommend() + orchestrate()│ └── telemetry/│ ├── refresh-receipts.ts → RefreshReceiptsLog│ └── recommendation-receipts.ts → RecommendationReceiptsLog├── smithery.yaml → Smithery listing config├── api/index.ts → Vercel catch-site (legacy showcase surface; kept alive)└── vercel.json → Vercel routing for the catch-sitesh scripts/run-tests.sh.faf-drift-index.json ← RepeatOffenderTracker — per-slot recurrence counts.faf-refresh-receipts.json ← RefreshReceiptsLog — every refresh fire.faf-recommendation-receipts.json ← RecommendationReceiptsLog — every orchestrator call@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{wolfe2026fafa, title = {Why Agents Need a Passport: .fafa — 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}}npx faf-cli auto