.Faf For Grok MCP Server

First MCP server for Grok/xAI. URL-based access. 17 tools for .faf project context.

Remote serverstreamable-httpTypeScript

What is the .Faf For Grok MCP server?

First MCP server for Grok/xAI. URL-based access. 17 tools for .faf project context. Exposed over MCP by the .faf for grok mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Persistent Project Context for xAI Grok. URL-based • Zero config • Just works

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Its toolset

Everything the assistant can do here goes through one of these:

  • 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
  • faf_enhance — Intelligent enhancement
  • refresh_faf — Re-ground on the live .faf — re-read + re-score, report drift, return fresh DNA (drift → refresh → re-grounded). Requested by Grok.
  • 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
  • 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
  • faf_orchestrate_recommendation — The heavy orchestrator. Reads current substrate state, composes the full 1.5 library substrate (drift detection · CheckID · repeat-offender ·
  • faf_get_orchestration_policy — Pure introspection of the effective policy WITHOUT running the orchestrator. Returns { tier, thresholds, source, overrides_applied } — what
  • faf_sync — Sync .faf → CLAUDE.md
  • faf_bi_sync — Bi-directional .faf ↔ platform context

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch .Faf For Grok.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the .faf for grok mcp server does with a few real requests.

When to reach for it

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. .Faf For Grok's toolset — faf_init, faf_auto, faf_score and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Wolfe-Jam; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
faf_initCreate project.faf from your project
faf_autoAuto-detect stack and populate context
faf_scoreAI-readiness score (0-100%) with breakdown
faf_statusCheck current AI-readability
faf_enhanceIntelligent enhancement
refresh_fafRe-ground on the live .faf — re-read + re-score, report drift, return fresh DNA (drift → refresh → re-grounded). **Requested by Grok.**
refresh_fafmRe-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 · always stamped. Sister to refresh_faf for the RAM/mem
refresh_blendThe 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** — bo
faf_orchestrate_recommendationThe heavy orchestrator. Reads current substrate state, composes the full 1.5 library substrate (drift detection · CheckID · repeat-offender · take-a-hint · refresh history), returns a structured Recommendation with recom
faf_get_orchestration_policyPure introspection of the effective policy WITHOUT running the orchestrator. Returns { tier, thresholds, source, overrides_applied } — what aggressiveness tier the next orchestration call would use, and whether it came f
faf_syncSync .faf → CLAUDE.md
faf_bi_syncBi-directional .faf ↔ platform context
faf_trustValidate .faf integrity
faf_readRead any file

How to install the .Faf For Grok MCP server

**Or via MCP config:**

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

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use .Faf For Grok to faf init.
  • Use .Faf For Grok to faf auto.
  • Use .Faf For Grok to faf score.

Frequently asked questions

It connects .Faf For Grok to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (faf_init, faf_auto, faf_score, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with .Faf For Grok directly.