FAST⚡️AF Context

Home: faf.one/grok Live demo: grok.faf.one

FAF defines. MD instructs. AI codes.

Install — one line

Add to ~/.grok/config.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).

Hosted on Cloudflare Workers — 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:

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 — 10 records ready to score.

Related MCP server: MCP Server Demo

The 6 Ws - Quick Reference

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.

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.

Happy to ship PRs, run private dogfood sessions, or jump on a call. Real software only. Just say the word.

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  →  "I'm building a REST API in Rust with Axum and PostgreSQL..."
With .faf     →  Grok already knows. Every session. Forever.

One Command, Done Forever

faf_auto detects your project, creates a .faf, and scores it — in one shot:

faf_auto
━━━━━━━━━━━━━━━━━
Score: 0% → 85% (+85) ◇ BRONZE
Steps:
  1. Created project.faf
  2. Detected stack from package.json
  3. Synced CLAUDE.md

Path: /home/user/my-project

What it produces:

# project.faf — 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:   14 hosted (WASM-pure: 13 + refresh_faf) · 59 local (bunx — incl. refresh_fafm, refresh_blend, faf_orchestrate_recommendation, faf_get_orchestration_policy)
Engine:  Mk4 WASM scoring (faf-scoring-kernel)
Speed:   0.5ms average (was 19ms — 3,800% faster with Mk4)
Tests: 27 .ts files (~518 test declarations) — 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

At 55%, Grok guesses half the time. At 100%, Grok knows your project.

Two Ways to Deploy

1. Hosted (zero install — recommended)

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).

{
  "mcpServers": {
    "grok-faf": {
      "url": "https://mcpaas.live/grok/mcp/v1"
    }
  }
}

2. Local (bunx — for FS-touching workflows)

Use the local stdio path when you need filesystem access (faf_init, faf_sync, file-mutating tools):

bunx grok-faf-mcp

Or via MCP config:

{
  "mcpServers": {
    "grok-faf": {
      "command": "bunx",
      "args": ["grok-faf-mcp"]
    }
  }
}

MCP Tools

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.

Performance

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:       Mk4 WASM via faf-scoring-kernel
Memory:       Zero leaks
Transport:    stdio (local, bunx) · 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 — 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.

Architecture

grok-faf-mcp v1.5.2
├── 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/compiler/faf-compiler.ts → Mk4 WASM scoring + Mk3.1 fallback
│   ├── 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-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 — they are no longer the production path.

Scoring pipeline: TypeScript compiler parses .faf → detects project type → The Bouncer injects slotignored for inapplicable slots → faf-scoring-kernel (WASM) scores → falls back to Mk3.1 if kernel unavailable.

Testing

27 test files (~518 test declarations) — WJTTC parity (heavy local ↔ light hosted) + full suites (recent runs green on CI):

sh scripts/run-tests.sh

Status & known limitations (v1.5)

This release ships the core 1.5 substrate and orchestration primitives, with the new tools available on the local stdio path. Operating it honestly means surfacing what's NOT in v1 alongside what is.

What is fully supported:

• WASM-pure tools on the hosted endpoint (https://mcpaas.live/grok/mcp/v1 and client-specific routes) — scoring · validation · 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 — 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).

• 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 — cwd-relative JSON, pull-discoverable. Three append-only JSON files live at the repo root with stable schemas:

  .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

  Pull-discoverable by external tools (TAF, custom indexers, observability dashboards) — 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 — .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.

• 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 — conservative by intent. Future task: explicit ack tool OR derived-from-subsequent-refresh-receipt timing.

• Outcome tracking ("did this recommendation actually help?") — 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 and curl https://mcpaas.live/grok/mcp/v1/info for the current contract.

Ecosystem

One format, every AI platform.

Same project.faf. Same scoring. Same result. Different execution layer.

Voice variant — 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

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.

xAI / Grok devs welcome — TL;DR setup at the top, F1-inspired tone throughout.

If grok-faf-mcp has been useful, consider starring the repo ⭐️ it helps others find it.

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.

License

MIT — Free and open source

Get the CLI

faf-cli — The original AI-Context CLI. A must-have for every builder.

npx faf-cli auto

Anthropic MCP #2759 · IANA Registered: application/vnd.faf+yaml · faf.one · npm · Talk to my Agent →