# Persistent Project Context for xAI Grok (npm · grok-faf-mcp)

Persistent project context for xAI Grok. IANA-registered .faf format.

- Trust score: 63/100 (medium)
- Change this week: +10
- Registry status: deprecated
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

> **Deprecated**: this server is marked deprecated in the MCP registry.

## Components

- remote · `mcpaas.live`: 67/100, [markdown](https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-mcp-v1.md), [page](https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-mcp-v1)
- npm · `grok-faf-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-faf-mcp.md), [page](https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-faf-mcp)

## Channel facts

- Registry: `npm`
- Package: `grok-faf-mcp`
- Version: `1.8.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (117 of 121), so this covers what we could see, not the whole tree.
  - Runs a script at install time (postinstall) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does.
  - Only part of the dependency tree could be resolved (117 of 121), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 32 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1326 tokens (~88/item across 15 items; 12 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add wolfe-jam-grok-faf-mcp -- npx -y grok-faf-mcp
```

### Codex

```bash
codex mcp add wolfe-jam-grok-faf-mcp -- npx -y grok-faf-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wolfe-jam-grok-faf-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "grok-faf-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add wolfe-jam-grok-faf-mcp --command npx --arg -y --arg grok-faf-mcp
```

### Hermes

```yaml
mcp_servers:
  wolfe-jam-grok-faf-mcp:
    command: "npx"
    args: ["-y", "grok-faf-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "wolfe-jam-grok-faf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "grok-faf-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 63, +32)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → partial
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [security] The scripts that run when this package is installed changed: postinstall
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 31, +5)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass

### 2026-07-31 (score 26, −9)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 35, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (12)

### `faf_score` (~78 tokens)

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.

Input parameters:

- `details` (boolean): Include detailed breakdown and improvement suggestions

### `refresh_faf` (~114 tokens)

Re-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.

Input parameters:

- `baseline` (number): Your last-known score (0-100). If provided, the drift delta is reported.
- `path` (string): Project directory or .faf path (supports ~). Defaults to the session working directory.

### `refresh_fafm` (~201 tokens)

Reload 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. Read-only. Always returns a content hash + timestamp stamp. Complements `recall`, `load_soul`, and `etch` — does not replace them.

Input parameters:

- `since` (string): Optional ISO timestamp. Only return facts modified after this time. Ignored when verbatim=true.
- `soul` (string): Specific soul to refresh. Omit or use 'default' for the primary memory layer. Use 'all' to refresh every available soul.
- `verbatim` (boolean): If true, returns the full current .fafm content for the requested soul(s) instead of a delta. Use sparingly — deltas are preferred for normal operation.

### `faf_orchestrate_recommendation` (~112 tokens)

Heavy 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.

### `faf_get_orchestration_policy` (~130 tokens)

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.

Input parameters:

- `path` (string): Optional explicit `.faf` file path or project directory (supports ~). When omitted, the live process cwd is searched for project.faf / .faf.

### `refresh_blend` (~269 tokens)

Baked-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.

Input parameters:

- `baseline` (number): For refresh_faf: your last-known score (0-100). Drift delta reported if provided.
- `mode` (string): 'blend' (Cmd+R analog, default) = .faf + .fafm delta. 'nuke' (Cmd+Shift+R analog) = .faf + .fafm verbatim.
- `path` (string): For refresh_faf: project directory or .faf path (supports ~).
- `since` (string): For refresh_fafm (delta mode only): ISO timestamp. Only facts modified after this. Ignored when mode=nuke (verbatim).
- `soul` (string): For refresh_fafm: specific soul. Omit or 'default' for primary; 'all' for every soul.

### `faf_init` (~134 tokens)

Create a project.faf — the IANA-registered context file (application/vnd.faf+yaml) that gives Grok persistent project DNA: stack, structure, and intent in one portable file. Write it once; an agent reads the whole project cold every session instead of re-discovering it.

Input parameters:

- `directory` (string): Project directory path (supports ~ tilde expansion). Creates directory if it doesn't exist.
- `force` (boolean): Force reinitialize existing FAF context
- `path` (string): Alias for directory parameter
- `projectName` (string): Project name for path inference (used with Projects convention)

### `faf_trust` (~52 tokens)

Validate a project.faf's structure and integrity — confirm the context file is well-formed and parses cleanly before an agent grounds on it. The pre-flight trust check: never build on a broken context layer.

### `faf_sync` (~71 tokens)

Sync project.faf into your AI context files (CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md). Non-destructive: injects a structured .faf block at the top for fast machine reading and preserves your prose below. One source of truth, every tool kept current.

### `rag_query` (~50 tokens)

Ask a question with RAG-enhanced context from xAI Collections. Uses LAZY-RAG cache for 100,000x speedup on repeated queries.

Input parameters:

- `question` (string, required): Question to ask

### `rag_cache_stats` (~27 tokens)

Get LAZY-RAG cache statistics - hits, misses, hit rate, cache size

### `rag_cache_clear` (~49 tokens)

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.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-faf-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 31
- 2026-07-31: 26
- 2026-07-30: 35
- 2026-07-28: 53
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/grok-faf-mcp
- Socket report: https://socket.dev/npm/package/grok-faf-mcp
- Repository: https://github.com/Wolfe-Jam/grok-faf-mcp
- Website: https://grok.faf.one/
- Changelog RSS feed: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-faf-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-faf-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-faf-mcp