# Wolfe Jam Grok Faf MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.wolfe-jam%2Fgrok-faf-mcp
Registry id: `mcp-registry/io.github.wolfe-jam/grok-faf-mcp`
Status: live (checked 2026-10-26T18:28:14.056Z)

## Verdict

Wolfe Jam Grok Faf MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1184 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (95/100) across 20 tools, costing an agent about 2,590 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1184 ms | 17% of MCP servers |
| p95 handshake latency | 3581 ms | — |
| Checks in 30 days | 4,881 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 20 | — |
| Tool-list size for an agent | ~2,590 tokens | 49% of MCP servers |
| Days observed | 29 | — |

## Install

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

Claude Code:

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

## Tools (22)

- `blend`: Blend multiple .faf contexts together
- `delta_check`: Determine if a topic needs FULL, DELTA, or X-DELTA soul.
- `faf_analyze`: One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.
- `faf_business_card`: Print a business card for an agent from its own name, description, colour and picture. Returns the agent's .fafa (FAF Agent file) and a link that opens its card
- `faf_collections_search`: 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_AP
- `faf_estimate_tokens`: Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.
- `faf_gate`: Phase III (FRC) — pre-promotion quality gate. Scores .faf content (edge Mk4) + estimates tokens and returns a deterministic promote/hold verdict BEFORE it goes 
- `faf_get_tier`: Resolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table.
- `faf_memory`: 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 (prove
- `faf_orchestrate_recommendation`: Takes raw content strings (`.faf`, `.fafm`, and optionally `package.json`/`CHANGELOG.md`/`README.md`) and runs deterministic drift + contradiction signals acros
- `faf_score`: Score .faf YAML content with the always-33 faf-kernel (WASM). Returns 0-100 (capped). The same score faf-cli and every FAF MCP give. Runs at the edge.
- `faf_section`: Phase III (FRC) — returns an EXACT, WHOLE .faf section by dotted path (e.g. "stack", "human_context"), structure preserved — the deterministic complement to bli
- `faf_validate`: Validate .faf YAML content: true if mission-ready (always-33 score of 100).
- `fafm`: Memory operations for .faf context
- `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
- `get_soul`: Fetch a context soul by name. Returns structured AI context.
- `list_souls`: List all available context souls.
- `list_tags`: List all unique tags used in a soul, with counts.
- `refresh_faf`: Re-ground on .faf content — re-score with the always-33 faf-kernel (33 slots; slotignored slots drop out), report drift vs an optional baseline score, and retur
- `search_by_tag`: Find all entries in a soul with a specific tag.
- `search_context`: Full-text search across souls. Returns matching lines only (token-efficient).
- `tag_intel`: Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.