ZBS Index What actually exists in applied AI, with the source next to it

mcp server

Persistent Project Context for xAI Grok

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

Description as published by the maintainer. Source

  • version 1.8.1
  • archived

archived — Registry status is "deprecated".

What this server can do

19 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

delta_check(topic)
Determine if a topic needs FULL, DELTA, or X-DELTA soul. Required: topic.
faf_analyze(content)
One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total. Required: content.
faf_collections_search(limit, query, collection_id)
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). Required: query, collection_id.
faf_estimate_tokens(content)
Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning. Required: content.
faf_gate(content, min_score, max_tokens)
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. Required: content.
faf_get_tier(score)
Resolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table. Required: score.
faf_memory(tag, type, query, content, priority)
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. Required: content.
faf_orchestrate_recommendation(faf, fafm, readme, changelog, packageJson)
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.
faf_score(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. Required: content.
faf_section(content, 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. Required: content.
faf_validate(content)
Validate .faf YAML content via the Mk4 Zig-WASM engine. Returns true if mission-ready (>= 100). Required: content.
generate_faf_from_github(repo)
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. Required: repo.
get_soul(soul)
Fetch a context soul by name. Returns structured AI context. Required: soul.
list_souls
List all available context souls.
list_tags(soul)
List all unique tags used in a soul, with counts. Required: soul.
refresh_faf(content, baseline, verbatim)
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. Required: content.
search_by_tag(tag, soul)
Find all entries in a soul with a specific tag. Required: soul, tag.
search_context(soul, query)
Full-text search across souls. Returns matching lines only (token-efficient). Required: query.
tag_intel(handle)
Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.

Last successful function declaration observed on . Source: https://mcpaas.live/grok/mcp/v1. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://mcpaas.live/grok/mcp/v1.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 1.8.1 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-06-29 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-06-24 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 19 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe mcpaas.live
mcp endpoint status ok The server listed 19 functions when asked. as of probe mcpaas.live

Where to get it

Also from wolfe-jam

  • io.github.Wolfe-Jam/claude-faf-mcp
    Persistent project context for Claude. IANA-registered .faf format.
  • .FAF Context
    Dedicated IDE Edition. Persistent project context for Cursor, Windsurf, Cline, VS Code.
  • io.github.Wolfe-Jam/gemini-faf-mcp
    Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.
  • mcp-better
    AAIF-verified modern MCP setup optimised to the 2026-07-28 model (BETTER textbook).
  • io.github.Wolfe-Jam/rust-faf-mcp
    Persistent project context — Rust-native MCP server. IANA-registered .faf format.
  • io.github.Wolfe-Jam/WJTTC
    F1-grade MCP certification. 52 tests, 9 tiers (49 scored + T9 Receipt validation). Ecosystem: #2759
  • Claude FAF
    Persistent project context for Claude. IANA-registered .faf format.
  • .FAF Context
    Dedicated IDE Edition. Persistent project context for Cursor, Windsurf, Cline, VS Code.
  • Gemini FAF
    Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.
  • Grok FAF
    Persistent project context for xAI Grok. IANA-registered .faf format.

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Tools declared by the MCP server at https://mcpaas.live/grok/mcp/v1 — mcpaas.live, observed , trust tier 1.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.