# Grok FAF **Category:** πŸ’» Developer Tools **Repository:** https://github.com/Wolfe-Jam/grok-faf-mcp **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/grok-faf ## Description Persistent project context for xAI Grok. IANA-registered .faf format. ## Claude Desktop Quick Installation Heuristic fallback β€” verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "grok-faf": { "command": "npx", "args": ["-y","grok-faf"] } } ``` ## Documentation & README # grok-faf-mcp β€” FAST⚑️AF Edition
FAF

Grok asked for MCP on a URL. This is it.

Persistent Project Context for xAI Grok.

URL-based β€’ Zero config β€’ Just works

[![IANA: vnd.faf+yaml](https://img.shields.io/badge/IANA-vnd.faf%2Byaml-00D4D4)](https://www.iana.org/assignments/media-types/application/vnd.faf+yaml) [![DOI: Context paper](https://img.shields.io/badge/DOI-Context%20paper-FF6B35)](https://doi.org/10.5281/zenodo.18251362) [![DOI: Agents paper](https://img.shields.io/badge/DOI-Agents%20paper-FF6B35)](https://doi.org/10.5281/zenodo.21951641)
**Home:** [faf.one/grok](https://faf.one/grok) **Live demo:** [grok.faf.one](https://grok.faf.one) ![grok-faf-mcp hero](https://raw.githubusercontent.com/Wolfe-Jam/grok-faf-mcp/main/assets/grok-faf-mcp-hero.png)
[![npm version](https://img.shields.io/npm/v/grok-faf-mcp?color=00CCFF)](https://www.npmjs.com/package/grok-faf-mcp) [![Smithery](https://img.shields.io/badge/Smithery-listed-00CCFF)](https://smithery.ai/servers/wolfe-jam/grok-faf-mcp) [![FAF Trophy 100%](https://img.shields.io/badge/FAF-%F0%9F%8F%86%20100%25-000000?labelColor=FF6B35)](https://faf.one) [![CI](https://github.com/Wolfe-Jam/grok-faf-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/Wolfe-Jam/grok-faf-mcp/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![project.faf](https://img.shields.io/badge/project.faf-inside-00D4D4)](https://github.com/Wolfe-Jam/faf) [![Chat to FAFA live](https://img.shields.io/badge/Chat_to_FAFA_live-000000?style=flat&labelColor=000)](https://faf-voice.vercel.app/agent)
[![Stars](https://img.shields.io/github/stars/Wolfe-Jam/grok-faf-mcp)](https://github.com/Wolfe-Jam/grok-faf-mcp/stargazers) [![Downloads](https://img.shields.io/npm/dt/grok-faf-mcp)](https://www.npmjs.com/package/grok-faf-mcp) **FAF defines. MD instructs. AI codes.** ## v1.10.0 β€” The No-Fluff Edition No fluff in a project.faf. `faf_enhance` is gone. RAG default is `grok-4.6`. A `.faf` is facts. Two writers only: the repo (`faf_auto`) and the human (`faf_go`). Empty is honest. There is no enhance. ⭐ Bookmarks it for you, helps other devs find it too. **First v0.2-conformant reader** of the [FAF Context Ingestion Contract](https://github.com/Wolfe-Jam/faf/blob/main/CONTEXT-INGESTION.md) β€” the open standard co-authored in public with @grok. --- ## Install β€” one line Add to `~/.grok/config.toml`: ```toml [mcp_servers.grok-faf-mcp] url = "https://mcpaas.live/grok/mcp/v1" ``` Restart Grok TUI (or `/mcps r`) to refresh. Tools: `faf_score`, `faf_validate`, `faf_get_tier`, `faf_estimate_tokens`, `faf_analyze` (plus soul/memory ops). **Smithery:** [wolfe-jam/grok-faf-mcp](https://smithery.ai/servers/wolfe-jam/grok-faf-mcp) β€” gateway at `https://grok-faf-mcp--wolfe-jam.run.tools` **Homebrew (local stdio):** ```bash brew install wolfe-jam/faf/grok-faf-mcp ``` **Hosted on Cloudflare Workers** β€” sub-ms cold start, no subprocess, edge-served. 4865-byte Zig WASM engine, parity-tested vs the Rust authority (`xai-faf-rust`). Externally validated by Grok S1 + S2 on 2026-05-27. **Verify the live contract:** ```bash curl https://mcpaas.live/grok/mcp/v1/info ``` Returns endpoint, protocol versions, engine details, tool list, and the architecture line: `.faf=vROM | AI-in-session=RAM`. Sample corpus: [`xai-faf-proof/pilot`](https://github.com/Wolfe-Jam/xai-faf-proof/tree/main/pilot) β€” 10 records ready to score. --- ## The 6 Ws - Quick Reference Every README should answer these questions. Here's ours: | Question | Answer | |----------|--------| | **WHO** is this for? | Grok/xAI developers and teams building with URL-based MCP | | **WHAT** is it? | Persistent project context for xAI Grok β€” URL-first deployment, IANA-registered .faf format | | **WHERE** does it work? | Cloudflare Workers (`mcpaas.live/grok/mcp/v1`) β€’ Any MCP client supporting native `url=` config β€’ Self-deploy to your own CF/Vercel worker | | **WHY** do you need it? | Zero-config MCP on a URL β€” Grok asked for it, we built it first | | **WHEN** should you use it? | Grok integration, xAI projects, any url-based MCP client | | **HOW** does it work? | `url = "https://mcpaas.live/grok/mcp/v1"` β€” context tools served from edge via MCPaaS (sub-ms cold start, no subprocess) | **For AI:** Read the detailed sections below for full context. **For humans:** Use this pattern in YOUR README. Answer these 6 questions clearly. ### For the xAI / Grok Build team 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 β€” `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](https://github.com/Wolfe-Jam/faf-cli/blob/main/docs/faf-cli-for-agents.md). --- ## The Problem 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. ``` Without .faf β†’ "I'm building a REST API in Rust with Axum and PostgreSQL..." With .faf β†’ Grok already knows. Every session. Forever. ``` --- ## One Command, Done Forever `faf_auto` detects your project, creates a `.faf`, and scores it β€” in one shot: ``` faf_auto ━━━━━━━━━━━━━━━━━ Score: 0% β†’ 85% (+85) β—‡ BRONZE Steps: 1. Created project.faf 2. Detected stack from package.json 3. Synced CLAUDE.md Path: /home/user/my-project ``` What it produces: ```yaml # project.faf β€” your project, machine-readable faf_version: "3.3" project: name: my-api goal: REST API for user management main_language: TypeScript stack: backend: Express database: PostgreSQL testing: Jest runtime: Node.js human_context: who: Backend developers what: User CRUD with auth why: Replace legacy PHP service ``` Every AI agent reads this once and knows exactly what you're building. --- ## ⚑ What You Get ``` URL: https://mcpaas.live/grok/mcp/v1 Format: IANA-registered .faf (application/vnd.faf+yaml) Tools: 12 core by default (bunx) β€” re-grounding (refresh_faf/fafm/blend), LAZY-RAG, orchestration substrate, FAF essentials Β· extended utilities via FAF_TOOLS=all Β· 19 hosted (WASM-pure, served by mcpaas-cf) on the URL Engine: Mk4 WASM scoring (faf-scoring-kernel) Speed: 0.5ms average (was 19ms β€” 3,800% faster with Mk4) Tests: 27 .ts files (~518 test declarations) β€” WJTTC parity (heavy local ↔ light hosted) + full suites. Runner: sh scripts/run-tests.sh (bun + flake retry) Status: FAST⚑️AF ``` **MCP on a URL.** Point your Grok integration at the URL. That's it. --- ## Scoring: From Blind to Optimized | Tier | Score | What it means | |------|-------|---------------| | **πŸ† TROPHY** | 100% | Gold Code β€” AI is optimized | | **β˜… GOLD** | 99%+ | Near-perfect context | | **β—† SILVER** | 95%+ | Excellent | | **β—‡ BRONZE** | 85%+ | Strong baseline | | **●** GREEN | 70%+ | Solid foundation | | ● YELLOW | 55%+ | AI flipping coins | | β—‹ RED | <55% | AI working blind | | β™‘ WHITE | 0% | Start β€” good luck | At 55%, Grok guesses half the time. At 100%, Grok knows your project. --- ## Two Ways to Deploy ### 1. Hosted (zero install β€” recommended) Point your MCP client at the production URL β€” edge-served on Cloudflare Workers, no subprocess, sub-ms cold start. WASM-pure tools only on this path (scoring, validation, `refresh_faf`). ```json { "mcpServers": { "grok-faf": { "url": "https://mcpaas.live/grok/mcp/v1" } } } ``` ### 2. Local (stdio β€” for FS-touching workflows) Use the local stdio path when you need filesystem access (`faf_init`, `faf_sync`, file-mutating tools): ```bash brew install wolfe-jam/faf/grok-faf-mcp # macOS tap # or bunx grok-faf-mcp ``` **Or via MCP config:** ```json { "mcpServers": { "grok-faf": { "command": "bunx", "args": ["grok-faf-mcp"] } } } ``` --- ## MCP Tools **Create & Detect** | Tool | Purpose | |------|---------| | `faf_init` | Create project.faf from your project | | `faf_auto` | Auto-detect stack and populate context | | `faf_score` | AI-readiness score (0-100%) with breakdown | | `faf_status` | Check current AI-readability | | `refresh_faf` | Re-ground on the live `.faf` β€” re-read + re-score, report drift, return fresh DNA (drift β†’ refresh β†’ re-grounded). **Requested by Grok.** | **Drift & Orchestration (1.5 β€” the prestige release)** | Tool | Purpose | |------|---------| | `refresh_fafm` | Re-ground on the live `.fafm` memory layer for one or more souls. Returns a stamped delta (added/updated facts) by default; `verbatim: true` for full content. Read-only Β· always stamped. Sister to `refresh_faf` for the RAM/memory layer in the vROM/RAM model. **Built for Grok, by request.** | | `refresh_blend` | The baked-in two-intensity refresh (Cmd+R / Cmd+Shift+R analog). `mode: "blend"` (default) fires `refresh_faf` (light) + `refresh_fafm` (delta); `mode: "nuke"` fires both at hard intensity. Blend is **BAKED IN, NOT a dial** β€” both layers always fire; mode only affects fafm intensity. | | `faf_orchestrate_recommendation` | The heavy orchestrator. Reads current substrate state, composes the full 1.5 library substrate (drift detection Β· CheckID Β· repeat-offender Β· take-a-hint Β· refresh history), returns a structured `Recommendation` with `recommend`, `severity`, `summary`, `reason`, and a rich `hints` object including `effective_policy` (the tier in force). **Advisory only β€” never auto-fires** (subordinate-not-daemon). Writes a recommendation receipt on every call (no silent decisions). Spec source: Grok-1 `FAF-DRIFT-DETECTION-SPEC Β§9.5 + Appendix C`. | | `faf_get_orchestration_policy` | Pure introspection of the effective policy WITHOUT running the orchestrator. Returns `{ tier, thresholds, source, overrides_applied }` β€” what aggressiveness tier the next orchestration call would use, and whether it came from defaults or a `.faf:orchestration:` override. No drift detection Β· no signals Β· no receipt write β€” the quietest tool in the 1.5 substrate. Useful for debugging unexpected orchestrator behavior, pre-flight checks before bulk operations, and override-took-effect verification. | **Sync & Persist** | Tool | Purpose | |------|---------| | `faf_sync` | Sync .faf β†’ CLAUDE.md | | `faf_bi_sync` | Bi-directional .faf ↔ platform context | | `faf_trust` | Validate .faf integrity | **Read & Write** | Tool | Purpose | |------|---------| | `faf_read` | Read any file | | `faf_write` | Write any file | | `faf_list` | Discover projects with .faf files | **RAG & Grok-Exclusive** | Tool | Purpose | |------|---------| | `rag_query` | RAG-powered context retrieval | | `rag_cache_stats` | RAG cache statistics | | `rag_cache_clear` | Clear RAG cache | | `grok_go_fast_af` | Auto-load .faf context for Grok | Plus 34 advanced tools available with `FAF_SHOW_ADVANCED=true`. --- ## Performance ``` Execution: 0.5ms average (97% faster than v1.1) Fastest: 3,360ns (version β€” nanosecond territory) Slowest: 1.3ms (score β€” Mk4 WASM) Improvement: 19ms β†’ 0.5ms (3,800% faster) Engine: Mk4 WASM via faf-scoring-kernel Memory: Zero leaks Transport: stdio (local, bunx) Β· Streamable HTTP (hosted, Cloudflare Workers) ``` 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 β€” 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(nΒ²) in fact count (cross-fact n-gram recurrence) β€” comfortable up to ~hundreds of facts. --- ## Architecture ``` grok-faf-mcp β”œβ”€β”€ src/ β”‚ β”œβ”€β”€ server.ts β†’ MCP server (GrokFafMcpServer) β”‚ β”œβ”€β”€ handlers/ β”‚ β”‚ β”œβ”€β”€ championship-tools.ts β†’ 55+ tool definitions β”‚ β”‚ β”œβ”€β”€ tool-registry.ts β†’ Visibility filtering (core/advanced) β”‚ β”‚ └── engine-adapter.ts β†’ FAF engine bridge β”‚ β”œβ”€β”€ faf-core/compiler/faf-compiler.ts β†’ Mk4 WASM scoring + Mk3.1 fallback β”‚ β”œβ”€β”€ types/ β†’ Canonical type substrate (1.5) β”‚ β”‚ β”œβ”€β”€ drift-signals.ts β†’ DriftSignal Β· Contradiction Β· RepeatOffender β”‚ β”‚ β”œβ”€β”€ refresh.ts β†’ RefreshMode β”‚ β”‚ β”œβ”€β”€ escalation.ts β†’ EscalationLevel β”‚ β”‚ β”œβ”€β”€ recommendation.ts β†’ RecommendationAction β”‚ β”‚ └── receipts.ts β†’ ReceiptMetadata β”‚ β”œβ”€β”€ detection/fafm-drift.ts β†’ detectFafmDrift() β€” repetition-rate gauge β”‚ β”œβ”€β”€ integrity/check-id.ts β†’ checkId() β€” cross-stamp contradiction check β”‚ β”œβ”€β”€ orchestrator/ β”‚ β”‚ β”œβ”€β”€ repeat-offender.ts β†’ RepeatOffenderTracker β”‚ β”‚ β”œβ”€β”€ take-a-hint.ts β†’ evaluateTakeAHint() β€” escalation ladder β”‚ β”‚ β”œβ”€β”€ refresh-blend.ts β†’ runRefreshBlend() β”‚ β”‚ └── recommendation.ts β†’ analyzeAndRecommend() + orchestrate() β”‚ └── telemetry/ β”‚ β”œβ”€β”€ refresh-receipts.ts β†’ RefreshReceiptsLog β”‚ └── recommendation-receipts.ts β†’ RecommendationReceiptsLog β”œβ”€β”€ smithery.yaml β†’ Smithery listing config β”œβ”€β”€ api/index.ts β†’ Vercel catch-site (legacy showcase surface; kept alive) └── vercel.json β†’ Vercel routing for the catch-site ``` **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 β€” they are no longer the production path. **Scoring pipeline:** TypeScript compiler parses `.faf` β†’ detects project type β†’ The Bouncer injects `slotignored` for inapplicable slots β†’ `faf-scoring-kernel` (WASM) scores β†’ falls back to Mk3.1 if kernel unavailable. --- ## Testing 27 test files (~518 test declarations) β€” WJTTC parity (heavy local ↔ light hosted) + full suites (recent runs green on CI): ```bash sh scripts/run-tests.sh ``` | Suite | Coverage | |-------|----------| | `desktop-native-validation` | Core native functions, security, performance | | `mcp-conformance` | MCP protocol conformance β€” tools, transport, errors | | `wjttc-mcp` | WJTTC MCP certification | | `wjttc-bun` | WJTTC bun-migration + integrity | | `wjttc-compiler-scoring` | Compiler scoring β€” engine, type detection, slots | | `rag-system` | RAG query, caching, context retrieval | | `security` | Input validation + security guards | | `visibility` | Tool visibility (core/advanced filtering) | --- ## Status & known limitations (v1.10) v1.10.0 β€” **The No-Fluff Edition** β€” no fluff in a project.faf. `faf_enhance` is gone. RAG default is `grok-4.6`. Fill stays on `faf_auto` / `faf_go`. Everything below still applies; operating it honestly means surfacing what's NOT in here alongside what is. > Earlier: v1.9.0 β€” **The ZEPH Default Edition** β€” the proven-fast Zigβ†’WASM scoring path behind `refresh_faf` is now **default-ON** (same score, cheaper to compute; parity proven byte-identical β€” CI gate + 91/91 live). Kill switch `USE_ZEPH=0` forces the canonical scorer. FRC tools stay opt-in behind `USE_FRC`. > Earlier: v1.8.0 β€” **The Closed-Loop Edition** β€” observability writes, token math is honest, FRC contract locked. The driftβ†’refreshβ†’re-ground loop can finally be measured. > Earlier: v1.7.0 β€” **The Grounded Memory Edition** β€” ZEPH + the FRC layer over Grok Collections (`faf_gate`/`faf_section`/`faf_memory`), opt-in via `USE_FRC`/`USE_ZEPH`; 12-tool core unchanged. > Earlier: v1.6.0 β€” **The ZEPH Edition** β€” the ZEPH fast path for re-grounding (`refresh_faf`/`refresh_blend` via Zigβ†’WASM `cascade.wasm`, ~12Β΅s, `USE_ZEPH=1`; `faf-cli` stays canonical, parity locked in CI). **What is fully supported:** - WASM-pure tools on the hosted endpoint (`https://mcpaas.live/grok/mcp/v1` and client-specific routes) β€” scoring Β· validation Β· `refresh_faf`. - `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` β€” the heavy orchestrator that composes drift signals, recurrence, receipts, and take-a-hint into an advisory recommendation. - `faf_get_orchestration_policy` β€” pure introspection of the effective policy without running the orchestrator (no drift detection, no receipt write β€” the quietest tool in the substrate). - Full policy visibility (`effective_policy`) returned on every orchestration call AND surfaced standalone via `faf_get_orchestration_policy`. **Current limitations:** - **`faf_orchestrate_recommendation`, `faf_get_orchestration_policy`, `refresh_fafm`, and `refresh_blend` require filesystem access** and are only available via the local stdio path (`bunx grok-faf-mcp` / `npx grok-faf-mcp`). They are not exposed on the hosted WASM-pure endpoint. The hosted path serves the existing WASM-pure subset only (`refresh_faf` + scoring + validation). - **Receipt storage β€” cwd-relative JSON, pull-discoverable.** Three append-only JSON files live at the repo root with stable schemas: ``` .faf-drift-index.json ← RepeatOffenderTracker β€” per-slot recurrence counts .faf-refresh-receipts.json ← RefreshReceiptsLog β€” every refresh fire .faf-recommendation-receipts.json ← RecommendationReceiptsLog β€” every orchestrator call ``` **Pull-discoverable by external tools** (TAF, custom indexers, observability dashboards) β€” read on your own schedule, no callback/push API required. Promotion to a dedicated orphan branch (mirroring the TAF pattern) is documented but deferred per ship discipline; the cwd-relative JSON is the v1 bootstrap. - **No multi-process file lock** on the receipt logs. Within a process, the JS event loop serializes writes. Multi-agent concurrent writes can race; future task. - **Aggressiveness tier hook** β€” `.faf:orchestration:tier` reads `'conservative'` (default β€” quietest, no noisy first-impression) Β· `'balanced'` Β· `'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 β€” edit `.faf:orchestration:tier:` directly to override. - **No ack mechanism yet for recommendation receipts.** `acknowledged: false` by default, never auto-flipped. Take-a-hint's ladder-reset semantics fire only on explicit ack β€” conservative by intent. Future task: explicit `ack` tool OR derived-from-subsequent-refresh-receipt timing. - **Outcome tracking** (*"did this recommendation actually help?"*) β€” needs a learning layer beyond 1.5 scope. **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](https://grok.faf.one/) and `curl https://mcpaas.live/grok/mcp/v1/info` for the current contract. --- ## Ecosystem One format, every AI platform. | Package | Platform | Registry | |---------|----------|----------| | **grok-faf-mcp** (this) | **xAI Grok** | **npm + Homebrew** | | [claude-faf-mcp](https://npmjs.com/package/claude-faf-mcp) | Anthropic | npm + MCP #2759 | | [gemini-faf-mcp](https://pypi.org/project/gemini-faf-mcp/) | Google | PyPI | | [rust-faf-mcp](https://crates.io/crates/rust-faf-mcp) | Rust | crates.io | | [faf-mcp](https://npmjs.com/package/faf-mcp) | Cursor, IDE's, VS Code | npm | | [faf-cli](https://npmjs.com/package/faf-cli) | Terminal CLI | bunx, npm + Homebrew | Same `project.faf`. Same scoring. Same result. Different execution layer. --- ## Voice variant β€” `grok-faf-voice` (VML) `.fafm πŸ˜πŸŽ™οΈ` β€” the voice variant of the `.faf 🐘` family. **[grok-faf-voice](https://pypi.org/project/grok-faf-voice/)** is the reference implementation of the **Voice Memory Layer (VML)** β€” what your voice agent *remembers* across sessions, devices, and model switches. Companion to `grok-faf-mcp`: - **`grok-faf-mcp`** (this) β€” `.faf` Foundational Context Layer for Grok via MCP-on-a-URL. - **`grok-faf-voice`** β€” `.fafm` Voice Memory Layer (VML) for Grok Voice via LiveKit + xAI realtime. Same family. Different surface. *Voice swappable; memory permanent.* [PyPI](https://pypi.org/project/grok-faf-voice/) Β· [GitHub](https://github.com/Wolfe-Jam/grok-faf-voice) Β· [Onboarding](https://wolfe-jam.github.io/grok-faf-voice/onboarding.html) --- ### For the xAI / Grok Build team This MCP server was built **for** Grok and continues to be shaped by direct feedback from Grok itself. Open for deeper collaboration on: - Native Grok Build integration - .fafm memory layer - refresh_faf primitives inside the Grok TUI / CLI - Any other context or orchestration features the team needs I ship fast, test rigorously, and dogfood everything live on https://grok.faf.one and https://mcpaas.live/grok/mcp/v1. Happy to: - Open PRs - Run private dogfood sessions - Jump on a call - Or just ship whatever moves the needle Real software only. Just say the word. --- ## Contributing PR conventions, code style, CI doctrine, MCP-tool contribution path, npm publish discipline, architecture decisions: **[CONTRIBUTING.md](https://github.com/Wolfe-Jam/grok-faf-mcp/blob/HEAD/CONTRIBUTING.md)**. xAI / Grok devs welcome β€” TL;DR setup at the top, F1-inspired tone throughout. --- ### For xAI / Grok Build team 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. --- ## Citation 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 β€” Portable Identity for the Agentic Era*. Zenodo. https://doi.org/10.5281/zenodo.21951641 ### BibTeX ```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{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 ---

Built for Grok. Built for Speed. Built Right.

FAST⚑️AF β€’ First to Ship β€’ Zero Friction

Zero drift. Eternal sync. AI optimized. πŸ†

--- ### Get the CLI > **faf-cli** β€” The original AI-Context CLI. A must-have for every builder. ```bash npx faf-cli auto ``` **Anthropic MCP [#2759](https://github.com/modelcontextprotocol/servers/pull/2759)** Β· **IANA Registered:** `application/vnd.faf+yaml` Β· [faf.one](https://faf.one) Β· [npm](https://www.npmjs.com/package/faf-cli) Β· [Talk to my Agent β†’](https://faf.one/agent)