mcpbeat

Persistent Project Context for xAI Grok MCP Server

io.github.Wolfe-Jam/grok-faf-mcp
answering

Persistent Project Context for xAI Grok is answering right now. Last checked 10 min ago. It exposes 19 tools. Last commit 2 Aug 2026.

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

Uptime history 45 hours of history
45 hours agonow
100.0%
Uptime 24h
91 of 91 checks
19
Tools
read from the server
334 ms
Response time
average over 24h
17
Stars
last commit 2 Aug 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

run in your terminal
claude mcp add grok-faf-mcp --transport http https://mcpaas.live/grok/mcp/v1
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "grok-faf-mcp": {
      "url": "https://mcpaas.live/grok/mcp/v1"
    }
  }
}
~/.codex/config.toml
[mcp_servers.grok-faf-mcp]
url = "https://mcpaas.live/grok/mcp/v1"
.cursor/mcp.json
{
  "mcpServers": {
    "grok-faf-mcp": {
      "url": "https://mcpaas.live/grok/mcp/v1"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "grok-faf-mcp": {
      "url": "https://mcpaas.live/grok/mcp/v1"
    }
  }
}

Available tools 19

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

faf
faf_analyze
One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.
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).
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 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_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 (provenance preserved), never grades them.
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.
faf_score
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.
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.
faf_validate
Validate .faf YAML content via the Mk4 Zig-WASM engine. Returns true if mission-ready (>= 100).
tag
search_by_tag
Find all entries in a soul with a specific tag.
tag_intel
Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.
context
search_context
Full-text search across souls. Returns matching lines only (token-efficient).
delta
delta_check
Determine if a topic needs FULL, DELTA, or X-DELTA soul.
generate
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.
refresh
refresh_faf
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.
soul
get_soul
Fetch a context soul by name. Returns structured AI context.
souls
list_souls
List all available context souls.
tags
list_tags
List all unique tags used in a soul, with counts.

Endpoints

URLTransportStateLatencyChecked
https://mcpaas.live/grok/mcp/v1 streamable-http answering 656 ms 10 min ago

Persistent Project Context for xAI Grok — questions

Answers built from our own checks of this server.

What can Persistent Project Context for xAI Grok do?
It exposes 19 tools, read directly from the server on our last check. Among them: delta_check, faf_analyze, faf_collections_search, faf_estimate_tokens, faf_gate, faf_get_tier and 13 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is Persistent Project Context for xAI Grok mostly used for?
Its tools cluster around faf and tag. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Persistent Project Context for xAI Grok working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 334 ms. The bar chart above shows every period we have measured.
How do I connect Persistent Project Context for xAI Grok?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Persistent Project Context for xAI Grok need an API key?
No. Persistent Project Context for xAI Grok completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 19 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Persistent Project Context for xAI Grok?
It answers our handshake in 334 ms on average, which is faster than 42% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Persistent Project Context for xAI Grok open source?
Yes — it is published under the MIT licence, written in TypeScript and 17 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.