Model Context Protocol (MCP) stdio server for auditing AI crawler readiness, 25k
Model Context Protocol (MCP) stdio server for auditing AI crawler readiness, 25k-token RAG truncation, /llms.txt, and Google Lighthouse 13.5 ard-schema (/.well-known/ai-catalog.json)
active Production-safe Score 95/100 http no auth
At a glance
| Endpoint | https://answerrail.com/mcp |
|---|---|
| Source | https://github.com/quitegoodproject/answerrail-mcp |
| Transport | http |
| Tools | 5 |
| Auth | none |
| First seen | 2026-11-10 22:58:10 |
| Last checked | 2026-11-17 21:39:22 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 322 / 527 ms |
| Last successful check | 2026-11-17 21:39:22 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (5)
audit_local_codebase— Inspects a local project directory on disk (checking package.json, public/robots.txt, public/llms.txt, and public/.well-known/ai-catalog.jsoaudit_ai_readiness— Audits a live website URL or domain for AI crawler access (GPTBot, OAI-SearchBot, PerplexityBot, ClaudeBot), 25,000-token HTML RAG truncatiogenerate_ai_manifests— Synthesizes a 6-line /llms.txt documentation index preview and a Google Lighthouse 13.5 /.well-known/ai-catalog.json (ARD 1.0) JSON previewextract_byte0_markdown— Strips JavaScript hydration payloads, theme DOM bloat, and inline SVGs/CSS from a live web page URL, returning clean GitHub-Flavored Markdowquery_truncation_benchmark— Retrieves statistical summary data and domain-level findings from the 2026 50-Site SaaS & E-Commerce AI Truncation Study, returning a Markdo
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:39:22 | ✓ | ✓ | 232 ms | 94 | active |
| 2026-11-17 21:24:07 | ✓ | ✓ | 349 ms | 91 | active |
| 2026-11-17 21:08:58 | ✓ | ✓ | 248 ms | 94 | active |
| 2026-11-17 20:53:50 | ✓ | ✓ | 209 ms | 94 | active |
| 2026-11-17 20:38:48 | ✓ | ✓ | 342 ms | 91 | active |
| 2026-11-17 20:23:44 | ✓ | ✓ | 211 ms | 94 | active |
| 2026-11-17 20:08:36 | ✓ | ✓ | 430 ms | 91 | active |
| 2026-11-17 19:52:49 | ✓ | ✓ | 258 ms | 94 | active |
| 2026-11-17 19:37:41 | ✓ | ✓ | 458 ms | 91 | active |
| 2026-11-17 19:22:23 | ✓ | ✓ | 396 ms | 91 | active |
| 2026-11-17 19:07:11 | ✓ | ✓ | 261 ms | 94 | active |
| 2026-11-17 18:51:56 | ✓ | ✓ | 374 ms | 91 | active |
| 2026-11-17 18:36:50 | ✓ | ✓ | 183 ms | 94 | active |
| 2026-11-17 18:21:46 | ✓ | ✓ | 239 ms | 94 | active |
| 2026-11-17 18:06:31 | ✓ | ✓ | 471 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://answerrail.com/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/answerrail-com-mcp # JSON