# Persistent Project Context for xAI Grok (remote · mcpaas.live)

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

- Trust score: 67/100 (medium)
- Change this week: +3
- 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 (this document), [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, [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

- Endpoint: `https://mcpaas.live/grok/mcp/v1`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.8.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 19 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **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 1632 tokens (~60/item across 27 items; 19 tools + 8 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.

## Install

### Claude

```bash
claude mcp add --transport http wolfe-jam-grok-faf-mcp https://mcpaas.live/grok/mcp/v1
```

### Codex

```toml
[mcp_servers.wolfe-jam-grok-faf-mcp]
url = "https://mcpaas.live/grok/mcp/v1"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wolfe-jam-grok-faf-mcp": {
      "type": "remote",
      "url": "https://mcpaas.live/grok/mcp/v1",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add wolfe-jam-grok-faf-mcp --url https://mcpaas.live/grok/mcp/v1 --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  wolfe-jam-grok-faf-mcp:
    url: "https://mcpaas.live/grok/mcp/v1"
```

### Other

```json
{
  "mcpServers": {
    "wolfe-jam-grok-faf-mcp": {
      "type": "http",
      "url": "https://mcpaas.live/grok/mcp/v1"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-08-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 65, −1)

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

### 2026-07-30 (score 66, +1)

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

### 2026-07-29 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 64, +1)

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

### 2026-07-26 (score 63)

First indexed and scored.

## MCP tools (19)

### `get_soul` (~46 tokens)

Get Context Soul

Fetch a context soul by name. Returns structured AI context.

Input parameters:

- `soul` (string, required): Soul identifier (e.g., "spacex", "wolfe", "grok")

### `list_souls` (~16 tokens)

List Available Souls

List all available context souls.

### `delta_check` (~35 tokens)

Delta Doctrine Check

Determine if a topic needs FULL, DELTA, or X-DELTA soul.

Input parameters:

- `topic` (string, required): Topic to check

### `list_tags` (~29 tokens)

List Tags

List all unique tags used in a soul, with counts.

Input parameters:

- `soul` (string, required): Soul identifier

### `search_by_tag` (~40 tokens)

Search by Tag

Find all entries in a soul with a specific tag.

Input parameters:

- `soul` (string, required): Soul identifier
- `tag` (string, required): Tag to search for

### `search_context` (~49 tokens)

Search Context

Full-text search across souls. Returns matching lines only (token-efficient).

Input parameters:

- `query` (string, required): Text to search for
- `soul` (string): Specific soul (optional, searches all if omitted)

### `tag_intel` (~52 tokens)

Tag Intel

Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.

Input parameters:

- `handle` (string): Optional: suggest tags for this specific namepoint

### `generate_faf_from_github` (~92 tokens)

Generate FAF from GitHub

Generate a .faf file from any public GitHub repository WITHOUT cloning. Extracts 6 Ws from README, analyzes stack from languages and package.json, and generates Championship-grade AI context. Returns .faf content, quality score, and metadata.

Input parameters:

- `repo` (string, required): GitHub repository URL or owner/repo format (e.g., "facebook/react" or "https://github.com/facebook/react")

### `faf_score` (~82 tokens)

Score .faf content

Score .faf YAML content via the Mk4 Zig-WASM engine. Returns 0-100 (capped). Same engine as xai-faf-rust + xai-faf-zig (parity-tested). Sub-ms at the edge.

Input parameters:

- `content` (string, required): Raw .faf YAML content. Souls with a [faf] section have it extracted automatically.

### `faf_validate` (~46 tokens)

Validate .faf content

Validate .faf YAML content via the Mk4 Zig-WASM engine. Returns true if mission-ready (>= 100).

Input parameters:

- `content` (string, required): Raw .faf YAML content to validate.

### `faf_get_tier` (~55 tokens)

Get tier for a score

Resolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table.

Input parameters:

- `score` (number, required): Numeric score 0-100.

### `faf_estimate_tokens` (~48 tokens)

Estimate tokens

Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.

Input parameters:

- `content` (string, required): Content to estimate tokens for.

### `faf_analyze` (~49 tokens)

Full analysis (score + tier + validate)

One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.

Input parameters:

- `content` (string, required): Raw .faf YAML content to analyze.

### `refresh_faf` (~155 tokens)

Re-ground on .faf content (drift → refresh → re-grounded)

Re-ground on .faf content — re-score via the Mk4 Zig-WASM Enterprise scorer (33-slot, honors the authored app-type shape), report drift vs an optional baseline score, and return a stamped re-ground. The explicit re-grounding primitive for long sessions: drift → refresh → re-grounded. Built for Grok, by request.

Input parameters:

- `baseline` (number): Optional last-known score (0-100). When provided, the drift delta (current - baseline) is reported.
- `content` (string, required): Raw .faf YAML content to re-ground on.
- `verbatim` (boolean): When true, return the full .faf content verbatim with the stamp. Default false (stamped delta + summary).

### `faf_orchestrate_recommendation` (~253 tokens)

Orchestrate Context Recommendation (FAF)

Takes raw content strings (`.faf`, `.fafm`, and optionally `package.json`/`CHANGELOG.md`/`README.md`) and runs deterministic drift + contradiction signals across the FAF substrate. Returns a structured `Recommendation` (recommend, severity, reason, summary) with `hints` containing the current `effective_policy` and `partial[]` for any stateful signals unavailable on the current surface. Light-lane execution (hosted) is WASM-pure with no filesystem access. Heavy-lane execution (local via bunx/rust-faf-mcp) has full FS + persisted state. Advisory only — never auto-fires.

Input parameters:

- `changelog` (string): Raw CHANGELOG.md content. Enables changelog cross-stamp checks.
- `faf` (string): Raw .faf YAML content (project DNA). Required for any meaningful analysis.
- `fafm` (string): Raw .fafm YAML content (memory layer). Enables drift detection.
- `packageJson` (string): Raw package.json content. Enables version cross-stamp checks (.faf vs pkg).
- `readme` (string): Raw README.md content. Enables README arch-tree cross-stamp checks.

### `faf_gate` (~136 tokens)

FRC quality gate (promote/hold)

Phase III (FRC) — pre-promotion quality gate. Scores .faf content (edge Mk4) + estimates tokens and returns a deterministic promote/hold verdict BEFORE it goes to a Grok Collection. Promote IFF score >= min_score AND tokens <= max_tokens (defaults 85/8000). Edge parity with the local gate; the hold-hint can't list empty slots at the edge.

Input parameters:

- `content` (string, required): Raw .faf YAML content to gate.
- `max_tokens` (number): Maximum tokens to promote (default 8000).
- `min_score` (number): Minimum score to promote (default 85).

### `faf_section` (~97 tokens)

Structure-aware retrieval

Phase III (FRC) — returns an EXACT, WHOLE .faf section by dotted path (e.g. "stack", "human_context"), structure preserved — the deterministic complement to blind chunking. Omit "section" to list every path.

Input parameters:

- `content` (string, required): Raw .faf YAML content.
- `section` (string): Dotted path to retrieve (e.g. "stack.backend"). Omit to list all paths.

### `faf_memory` (~130 tokens)

Portable structured memory (.fafm)

Phase III (FRC) — query the durable .fafm model by type/tag/priority/text. Omit filters for a structured summary. .fafm is NOT scored: this SELECTS facts (provenance preserved), never grades them.

Input parameters:

- `content` (string, required): Raw .fafm YAML content.
- `priority` (string): Filter by priority (e.g. "critical").
- `query` (string): Case-insensitive substring match on fact text.
- `tag` (string): Filter by a tag.
- `type` (string): Filter by fact type (e.g. "feedback").

### `faf_collections_search` (~125 tokens)

Search a Grok Collection (edge, KV-cached)

Phase III (FRC §7b) — semantic search over a Grok Collection at the edge, KV-cached (1h TTL). Returns matched chunks (content, score, file). Requires the XAI_API_KEY secret; composes with faf_section (structural) for hybrid retrieval. Handled env-aware in the MCP handler (needs the key + KV).

Input parameters:

- `collection_id` (string, required): The Grok Collection id to search.
- `limit` (number): Max chunks to return (default 5).
- `query` (string, required): The search query.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-mcp-v1#diagnostics

## Score history

- 2026-08-03: 67
- 2026-08-02: 66
- 2026-08-01: 66
- 2026-07-31: 65
- 2026-07-30: 66
- 2026-07-29: 65
- 2026-07-28: 64
- 2026-07-27: 64
- 2026-07-26: 63

## Links

- Remote endpoint: https://mcpaas.live/grok/mcp/v1
- 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-mcp-v1/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-mcp-v1/changelog.json
- HTML version of this page: https://verifymcp.io/servers/wolfe-jam-grok-faf-mcp/grok-mcp-v1