// MCP TOOL REFERENCE

AGENT MEMORY TOOLS

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

View the Agent Memory policy → Token cost: 311 tokens →

// ALL 5 AGENT MEMORY TOOLS

READ 3 tools

Read get_memory Retrieve a specific memory by ID. Read search_memories Search memories by namespace with optional text query. Read store_memory Store a memory for an AI agent. Persists across sessions.

DESTRUCTIVE 2 tools

Destructive clear_namespace Delete all memories in a namespace. Destructive delete_memory Delete a specific memory by ID.

// FAQ

How many tools does the Agent Memory MCP server have? +

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

How do I enforce policies on Agent Memory tools? +

Route the Agent 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 Agent Memory tools fall into? +

Agent Memory tools are categorised as Read (3), Destructive (2). 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.