Claude FAF

claude-faf-mcp FAF MCP server for Claude-compatible clients, with 33 tools for creating, validating, scoring, and syncing .faf Project DNA files.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Get Soul: Fetch a context soul by name. Returns structured AI context.
  • List Souls: List all available context souls.
  • Write Soul: Append an entry to a soul or replace it entirely. Entries can be typed as note, fact, todo, or question.

What data it sees

Do you need an account

No: the server works without sign-in

claude-faf-mcp

FAF MCP server for Claude-compatible clients, with 33 tools for creating, validating, scoring, and syncing .faf Project DNA files.

Install: npm install -g claude-faf-mcp

It helps reduce AI context drift by making project context operations structured and repeatable across sessions and IDE agents.

GitHub: https://github.com/Wolfe-Jam/claude-faf-mcp
npm: https://www.npmjs.com/package/claude-faf-mcp
Smithery (auto-CLI): https://smithery.ai/servers/wolfe-jam/claude-faf-mcp

claude-faf-mcp logo

Server tool list (23)

Raw names from tools/list. Only developers need these.

get_soulFetch a context soul by name. Returns structured AI context.
list_soulsList all available context souls.
write_soulAppend an entry to a soul or replace it entirely. Entries can be typed as note, fact, todo, or question.
delta_checkDetermine if a topic needs FULL, DELTA, or X-DELTA soul.
list_tagsList all unique tags used in a soul, with counts.
search_by_tagFind all entries in a soul with a specific tag.
search_contextFull-text search across souls. Returns matching lines only (token-efficient).
create_soulCreate a new soul with initial content. Admin-only operation.
update_soulReplace entire content of an existing soul. Admin-only operation.
delete_soulPermanently delete a soul from storage. Admin-only operation.
tag_intelDiscover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.
generate_faf_from_githubGenerate 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.
faf_scoreScore .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.
faf_validateValidate .faf YAML content via the Mk4 Zig-WASM engine. Returns true if mission-ready (>= 100).
faf_get_tierResolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table.
faf_estimate_tokensEstimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.
faf_analyzeOne-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.
refresh_fafRe-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.
faf_orchestrate_recommendationTakes 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.
faf_gatePhase 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.
faf_sectionPhase 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.
faf_memoryPhase 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.
faf_collections_searchPhase 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).