// MCP TOOL REFERENCE

MEMORYCLAW TOOLS

6 tools from the MemoryClaw MCP Server, categorised by risk level.

// ALL 6 MEMORYCLAW TOOLS

READ 2 tools

Read memory_get Retrieve specific lines from a memory file. Read memory_search Search long-term conversation memory using hybrid vector + keyword search.

WRITE 3 tools

Write memory_add Intelligently add information to memory with automatic deduplication. Write memory_context Read or write the active working memory (scratchpad) for a user. Write memory_store Save or update a memory file in the workspace.

DESTRUCTIVE 1 tools

Destructive memory_delete Delete a memory file from the workspace.

// FAQ

How many tools does the MemoryClaw MCP server have? +

The MemoryClaw MCP server exposes 6 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on MemoryClaw tools? +

Route the MemoryClaw 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 MemoryClaw tools fall into? +

MemoryClaw tools are categorised as Read (2), Write (3), Destructive (1). Each category has a recommended default policy.

Enforce policy on every MemoryClaw tool call.

Start from MemoryClaw, 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.