<strong>How did this happen? — a hippocampus for AI agents.</strong>
How did this happen? — a hippocampus for AI agents.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| search_memory | Hybrid search: semantic similarity + BM25 + recency |
| add_memory | Store a memory. Supports client_id for entity tagging |
| log_prediction | Log a pack-grounded prediction. Required when an installed experience pack cites a specific relative_day as the basis for an action recommendation. |
| log_outcome | Resolve a prediction with the observed signal — interpretation-free record. |
| memory_stats | Collection stats: point counts by source/type, session count |
| Variable | Description | Required |
|---|---|---|
| QDRANT_HOST | Endpoint or connection string the server talks to. | Optional |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
A Model Context Protocol (MCP) server enabling AI agents to query information about dependencies in a Ruby project's `Gemfile`. Built with
MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes
A Model Context Protocol (MCP) server that provides semantic search capabilities across files. This server watches specified directories and creates
Finance canon lookup plus 30 deterministic formulas, each with a verifiable receipt.