Categories › Data & Databases › Vector databases & embeddings
O(1) routing, semantic search, and quality-filtered demand-driven experiences over 800+ records.
Remote server: your requests and data go to mcp.corpusfetch.com. Claude Code: claude mcp add --transport http corpusfetch https://mcp.corpusfetch.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
corpusfetch_fetch_record — Fetch the full resolved experience record. Format `md` (~1,500 tokens, includes reasoning) or `py` (~300 tokens, zero-prose executable invarcorpusfetch_fetch_warrant — Fetch the compact ~220-token precondition seal for a resolved record. Always call this before `corpusfetch_fetch_record`—check the seal firscorpusfetch_lookup_exception — Look up operational experience for an exact Python exception class (e.g., KeyError, TimeoutError, ConnectionError). Use when you encounter acorpusfetch_lookup_symptom — Look up operational experience for a specific runtime symptom or boundary failure (e.g., UNICODE_HOMOGLYPH_OR_MOJIBAKE). Use when facing an corpusfetch_request_experience — Request a new operational experience when `corpusfetch_search` returns no match. The corpus will generate and publish a record for your speccorpusfetch_search — Search operational records for distributed systems failures, AI agent protocol issues, MCP/A2A problems, database anomalies, concurrency bugNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.