Persistent Project Context for Claude — IANA-registered .faf format · 32 tools +
Persistent Project Context for Claude — IANA-registered .faf format · 32 tools + 1 prompt · MCP Registry #2759
active Production-safe Score 91/100 http no auth
At a glance
| Endpoint | https://claude-faf-mcp.vercel.app/sse |
|---|---|
| Source | https://github.com/Wolfe-Jam/claude-faf-mcp |
| Transport | http |
| Tools | 20 |
| Auth | none |
| First seen | 2026-05-23 12:28:19 |
| Last checked | 2026-11-17 22:01:37 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 710 / 1503 ms |
| Last successful check | 2026-11-17 22:01:37 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (20)
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. Seartag_intel— Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handlegenerate_faf_from_github— Generate a .faf file from any public GitHub repository WITHOUT cloning. Extracts 6 Ws from README, analyzes stack from languages and packagefaf_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 atfaf_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 baselfaf_orchestrate_recommendation— Takes raw content strings (`.faf`, `.fafm`, and optionally `package.json`/`CHANGELOG.md`/`README.md`) and runs deterministic drift + contradfaf_gate— Phase III (FRC) — pre-promotion quality gate. Scores .faf content (edge Mk4) + estimates tokens and returns a deterministic promote/hold verfaf_section— Phase III (FRC) — returns an EXACT, WHOLE .faf section by dotted path (e.g. "stack", "human_context"), structure preserved — the deterministfaf_memory— Phase III (FRC) — query the durable .fafm model by type/tag/priority/text. Omit filters for a structured summary. .fafm is NOT scored: thisfaf_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).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
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 22:01:37 | ✓ | ✓ | 798 ms | 90 | active |
| 2026-11-17 21:46:30 | ✓ | ✓ | 570 ms | 90 | active |
| 2026-11-17 21:31:25 | ✓ | ✓ | 910 ms | 90 | active |
| 2026-11-17 21:16:12 | ✓ | ✓ | 823 ms | 90 | active |
| 2026-11-17 21:01:05 | ✓ | ✓ | 1136 ms | 86 | active |
| 2026-11-17 20:45:54 | ✓ | ✓ | 765 ms | 90 | active |
| 2026-11-17 20:30:52 | ✓ | ✓ | 1100 ms | 86 | active |
| 2026-11-17 20:15:46 | ✓ | ✓ | 668 ms | 90 | active |
| 2026-11-17 19:59:43 | ✓ | ✓ | 987 ms | 90 | active |
| 2026-11-17 19:44:37 | ✓ | ✓ | 732 ms | 90 | active |
| 2026-11-17 19:29:35 | ✓ | ✓ | 789 ms | 90 | active |
| 2026-11-17 19:14:33 | ✓ | ✓ | 664 ms | 90 | active |
| 2026-11-17 18:58:46 | ✓ | ✓ | 1097 ms | 86 | active |
| 2026-11-17 18:43:44 | ✓ | ✓ | 618 ms | 90 | active |
| 2026-11-17 18:28:43 | ✓ | ✓ | 597 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://claude-faf-mcp.vercel.app/sse") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/claude-faf-mcp-vercel-app-sse # JSON