io.github.wolfe-jam/claude-faf-mcp
https://mcpaas.live/claude/mcp/v1Persistent project context for Claude. IANA-registered .faf format.
What we measured
Over the last 30 days we probed this MCP server 23 times on 22 days; it answered 23 (100%). Median response 725 ms, 95th percentile 982 ms.
When we called tools/list it returned 20 tools, including get_soul, list_souls, delta_check, over MCP protocol revision 2026-07-28.
Among the 53,642 reachable MCP servers in our snapshot of 2026-11-13 01:12 UTC, it is faster than 10% and higher on readiness than 90%.
From agent-tools.cloud's own probes, last checked 2026-11-12. How we measure
Tools (20)
As returned by the server's own tools/list when we called it.
- get_soul
- Fetch a context soul by name. Returns structured AI context.
- list_souls
- List context souls: showcase souls first, then claimed souls. Paged: pass the returned cursor for more.
- delta_check
- Determine if a topic needs FULL, DELTA, or X-DELTA soul.
- list_tags
- List all unique tags used in a soul, with counts.
- search_by_tag
- Find all entries in a soul with a specific tag.
- 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…
- tag_intel
- Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.
- 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…
- 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_validate
- Validate .faf YAML content: true if mission-ready (always-33 score of 100).
- 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_estimate_tokens
- Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.
- faf_analyze
- One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.
- 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…
- 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_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_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_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_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_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…
MCP readiness
Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. For x402 and A2A listings it contributes up to 15 of the 100 quality points; for MCP listings it is shown for reference only. Search order and leaderboards use the separate quality grade (here B, 81.7/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ
| Valid MCP handshake | 10/10 | initialize and tools/list both answered. |
| Live MCP endpoint | 25/25 | Endpoint answers the MCP initialize handshake (982 ms). |
| Protocol revision | 10/10 | Speaks the current MCP revision 2026-07-28. |
| Signed descriptor | n/a | No MCP standard defines a signed server descriptor. |
| Uptime (30 days) | 15/15 | 23/23 probes succeeded over 30 days (100%). |
| Tool declaration | 10/10 | Lists 20 tool(s) with descriptions. |
| Verified identity | 5/10 | Publisher declared (repository, package or homepage); claim this listing to verify domain control. |
| Freshness + modern flags | 4/5 | seen in a source within 7 days. |
| Auth declaration | 0/5 | How to authenticate is not stated. |
Compared with peers
Against 53,642 reachable MCP servers in our daily snapshot (2026-11-13 01:12 UTC). Display only; it does not change search order.
- Readiness
- Higher than 90% of peers
- This listing 88 · peer median 81
- Latency
- Faster than 10% of peers
- This listing 982 ms · peer median 349 ms
Where it loses the most points, and how to win them back
- Verified identity −5
— Claim the listing and prove control of its domain.
Now: Publisher declared (repository, package or homepage); claim this listing to verify domain control.
- Auth declaration −5
— State how to authenticate (an auth scheme, or that none is needed).
Now: How to authenticate is not stated.
- Freshness + modern flags −1
— Keep the listing current in the registry or source it comes from.
Now: seen in a source within 7 days.
Listed in
Directories this entry was found in.
How to connect
https://mcpaas.live/claude/mcp/v1
curl -X POST https://mcpaas.live/claude/mcp/v1 \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'