Mem0 MCP Server

Instructions

    Use filters to narrow results. Common filter patterns:
    - Single user: {"AND": [{"user_id": "john"}]}
    - Agent memories: {"AND": [{"agent_id": "agent_name"}]}
    - Recent memories: {"AND": [{"user_id": "john"}, {"created_at": {"gte": "2024-01-01"}}]}
    - Multiple users: {"AND": [{"user_id": {"in": ["john", "jane"]}}]}
    - Cross-entity: {"OR": [{"user_id": "john"}, {"agent_id": "agent_name"}]}

    user_id is automatically added to filters if not provided.
    

Implementation Reference

• src/mem0_mcp_server/server.py:246-291 (handler)

  Full implementation of the search_memories tool handler, including MCP registration via @server.tool decorator, input parameter definitions, logic to resolve settings, validate args with SearchMemoriesArgs, inject default user filters, and call the Mem0 client's search method.

  @server.tool(
      description="""Run a semantic search over existing memories.
  
      Use filters to narrow results. Common filter patterns:
      - Single user: {"AND": [{"user_id": "john"}]}
      - Agent memories: {"AND": [{"agent_id": "agent_name"}]}
      - Recent memories: {"AND": [{"user_id": "john"}, {"created_at": {"gte": "2024-01-01"}}]}
      - Multiple users: {"AND": [{"user_id": {"in": ["john", "jane"]}}]}
      - Cross-entity: {"OR": [{"user_id": "john"}, {"agent_id": "agent_name"}]}
  
      user_id is automatically added to filters if not provided.
      """
  )
  def search_memories(
      query: Annotated[str, Field(description="Natural language description of what to find.")],
      filters: Annotated[
          Optional[Dict[str, Any]],
          Field(default=None, description="Additional filter clauses (user_id injected automatically)."),
      ] = None,
      limit: Annotated[
          Optional[int], Field(default=None, description="Maximum number of results to return.")
      ] = None,
      enable_graph: Annotated[
          Optional[bool],
          Field(
              default=None,
              description="Set true only when the user explicitly wants graph-derived memories.",
          ),
      ] = None,
      ctx: Context | None = None,
  ) -> str:
      """Semantic search against existing memories."""
  
      api_key, default_user, graph_default = _resolve_settings(ctx)
      args = SearchMemoriesArgs(
          query=query,
          filters=filters,
          limit=limit,
          enable_graph=_default_enable_graph(enable_graph, graph_default),
      )
      payload = args.model_dump(exclude_none=True)
      payload["filters"] = _with_default_filters(default_user, payload.get("filters"))
      payload.setdefault("enable_graph", graph_default)
      client = _mem0_client(api_key)
      return _mem0_call(client.search, **payload)

• src/mem0_mcp_server/schemas.py:50-58 (schema)

  Pydantic BaseModel defining the input schema (SearchMemoriesArgs) used for validating and structuring arguments to the search_memories tool.

  class SearchMemoriesArgs(BaseModel):
      query: str = Field(..., description="Describe what you want to find.")
      filters: Optional[Dict[str, Any]] = Field(
          None, description="Additional filter clauses; user_id is injected automatically."
      )
      limit: Optional[int] = Field(None, description="Optional maximum number of matches.")
      enable_graph: Optional[bool] = Field(
          None, description="Set True only when the user asks for graph knowledge."
      )

• src/mem0_mcp_server/server.py:246-258 (registration)

  MCP tool registration for 'search_memories' using the @server.tool decorator with detailed description.

  @server.tool(
      description="""Run a semantic search over existing memories.
  
      Use filters to narrow results. Common filter patterns:
      - Single user: {"AND": [{"user_id": "john"}]}
      - Agent memories: {"AND": [{"agent_id": "agent_name"}]}
      - Recent memories: {"AND": [{"user_id": "john"}, {"created_at": {"gte": "2024-01-01"}}]}
      - Multiple users: {"AND": [{"user_id": {"in": ["john", "jane"]}}]}
      - Cross-entity: {"OR": [{"user_id": "john"}, {"agent_id": "agent_name"}]}
  
      user_id is automatically added to filters if not provided.
      """
  )