Persistent Project Context for xAI Grok

Deprecated in registry

io.github.Wolfe-Jam/grok-faf-mcpVersion 1.8.1

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

Status

Responds311 msNov 14, 2026, 14:45 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Deprecated in registry

The publisher marked this server as deprecated.

Last checked: Nov 14, 2026, 14:45 UTC
Latency: 311 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://mcpaas.live/grok/mcp/v1Responds311 msNov 14, 2026, 14:45 UTC

No sign-in

Claude Code

claude mcp add --transport http grok-faf-mcp https://mcpaas.live/grok/mcp/v1

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: grok-faf-mcp
Remote MCP server URL: https://mcpaas.live/grok/mcp/v1

Cursor

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

VS Code

code --add-mcp '{"name":"grok-faf-mcp","type":"http","url":"https://mcpaas.live/grok/mcp/v1"}'

Streamable HTTP

npm: grok-faf-mcp 1.8.1

Package only

npm (npx)

claude mcp add grok-faf-mcp -- npx -y grok-faf-mcp@1.8.1

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

20 tools

Tools of Persistent Project Context for xAI Grok
	Description		Read-only	Idempotent	Open world
`delta_check`Determine if a topic needs FULL, DELTA, or X-DELTA soul.	Determine if a topic needs FULL, DELTA, or X-DELTA soul.	No	Yes	Yes	No
`faf_analyze`One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.	One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.	No	Yes	Yes	No
`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. Nothing is stored: the .fafa travels in the link. The card says "self-declared" because nothing is checked against a repo.	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. Nothing is stored: the .fafa travels in the link. The card says "self-declared" because nothing is checked against a repo.	No	Yes	Yes	No
`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_API_KEY secret; composes with faf_section (structural) for hybrid retrieval. Handled env-aware in the MCP handler (needs the key + KV).	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).	No	Yes	Yes	Yes
`faf_estimate_tokens`Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.	Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.	No	Yes	Yes	No
`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 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.	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.	No	Yes	Yes	No
`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.	Resolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table.	No	Yes	Yes	No
`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 (provenance preserved), never grades them.	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.	No	Yes	Yes	No
`faf_orchestrate_recommendation`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.	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.	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	No
`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 blind chunking. Omit "section" to list every path.	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.	No	Yes	Yes	No
`faf_validate`Validate .faf YAML content: true if mission-ready (always-33 score of 100).	Validate .faf YAML content: true if mission-ready (always-33 score of 100).	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	Yes
`get_soul`Fetch a context soul by name. Returns structured AI context.	Fetch a context soul by name. Returns structured AI context.	No	Yes	Yes	No
`list_souls`List context souls: showcase souls first, then claimed souls. Paged: pass the returned cursor for more.	List context souls: showcase souls first, then claimed souls. Paged: pass the returned cursor for more.	No	Yes	Yes	No
`list_tags`List all unique tags used in a soul, with counts.	List all unique tags used in a soul, with counts.	No	Yes	Yes	No
`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 return a stamped re-ground. The explicit re-grounding primitive for long sessions: drift → refresh → re-grounded. Built for Grok, by request.	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 return a stamped re-ground. The explicit re-grounding primitive for long sessions: drift → refresh → re-grounded. Built for Grok, by request.	No	Yes	Yes	No
`search_by_tag`Find all entries in a soul with a specific tag.	Find all entries in a soul with a specific tag.	No	Yes	Yes	No
`search_context`Full-text search across souls (showcase first, then claimed souls; [private] sections are never searched). Returns matching lines only. Searches a page of souls per call: pass the returned cursor for more.	Full-text search across souls (showcase first, then claimed souls; [private] sections are never searched). Returns matching lines only. Searches a page of souls per call: pass the returned cursor for more.	No	Yes	Yes	No
`tag_intel`Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.	Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.	No	Yes	Yes	No

Details

Registry status: Deprecated
Published: Jun 24, 2026
Updated: Jun 29, 2026
Website: https://grok.faf.one/⁠ (opens in a new tab)
Repository: https://github.com/Wolfe-Jam/grok-faf-mcp⁠ (opens in a new tab)
Categories (suggested): Project management Knowledge and notesSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing