// MCP TOOL REFERENCE

MEMORY TOOLS

5 tools from the Memory MCP Server, categorised by risk level.

// ALL 5 MEMORY TOOLS

READ 2 tools

Read get_memory Get a summary of the memories you have about the user you are currently interacting with. You should call t... Read search_vector_memory Search your vector store for relevant episodic memories to inform the current conversation. This can be use...

WRITE 3 tools

Write add_vector_memory Add episodic memories into your vector store to be searchable at a later time. These memories are NOT part ... Write memory_append Append to the memory you have about the user you are currently interacting with. Write memory_replace Replace the memory you have about the user you are currently interacting with.

// RUNNING THIS SERVER

The managed route: connect Memory through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @letta-ai/memory-mcp

// FAQ

How many tools does the Memory MCP server have? +

The Memory MCP server exposes 5 tools across 2 categories: Read, Write.

How do I enforce policies on Memory tools? +

Route the Memory server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Memory tools fall into? +

Memory tools are categorised as Read (2), Write (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.