// MCP TOOL REFERENCE

CLAUDE PERSISTENT MEMORY TOOLS

4 tools from the Claude Persistent Memory MCP Server, categorised by risk level.

View the Claude Persistent Memory policy →

// ALL 4 CLAUDE PERSISTENT MEMORY TOOLS

READ 2 tools

Read memory_search Search persistent memories (hybrid BM25 + vector semantic retrieval). Use when you need to recall previous ... Read memory_stats View memory system statistics: total memories, type distribution, domain distribution, cluster status, etc.

WRITE 2 tools

Write memory_validate Validate whether a memory was helpful. Helpful increases confidence by +0.1, unhelpful decreases by -0.05. Write memory_save Save a new persistent memory. Use to record important patterns, decisions, bug fixes, user preferences, etc.

// FAQ

How many tools does the Claude Persistent Memory MCP server have? +

The Claude Persistent Memory MCP server exposes 4 tools across 2 categories: Read, Write.

How do I enforce policies on Claude Persistent Memory tools? +

Route the Claude Persistent 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 Claude Persistent Memory tools fall into? +

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

Enforce policy on every Claude Persistent Memory tool call.

Start from Claude Persistent Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.