This MCP server allows users to search and browse their Claude conversation history stored locally, utilizing various search methods including hybrid search and vector embeddings.
From the registry: Hybrid search for Cowork history: FTS, Spotlight, and semantic vectors
Please install the `cowork-history` MCP server into my current AI client (that's you).
Optional prerequisites:
- Ollama (optional, for embeddings) — Install Ollama and pull the nomic-embed-text model for semantic search. Optional. (https://ollama.com)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["cowork-history"]
- optional environment variables:
- `OLLAMA_URL`: Ollama API URL for embeddings. (example: `http://localhost:11434`)
- `EMBEDDING_MODEL`: Ollama embedding model name. (example: `nomic-embed-text`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OLLAMA_URLrequiredOllama server URLEMBEDDING_MODELrequiredOllama embedding modelMCP server for searching Airweave collections with natural language queries.