// MCP TOOL REFERENCE

CLAUDE DESKTOP API MCP TOOLS

4 tools from the Claude Desktop API MCP MCP Server, categorised by risk level.

View the Claude Desktop API MCP policy →
// ALL 4 CLAUDE DESKTOP API MCP TOOLS
READ 1 tools
Read get_conversation_history Get the conversation history for a specific ID
DESTRUCTIVE 1 tools
Destructive clear_conversation Clear a specific conversation history
EXECUTE 2 tools
Execute query_claude Query Claude API with a prompt and optional system prompt Execute send-message Send a message to Claude

Route Claude Desktop API MCP through PolicyLayer and every one of its 4 tools is checked against your policy before it runs.

CHECK YOUR STACK →

See every tool, the dangerous ones, and the token cost across your stack.

// FAQ
How many tools does the Claude Desktop API MCP MCP server have? +

The Claude Desktop API MCP MCP server exposes 4 tools across 3 categories: Read, Destructive, Execute.

How do I enforce policies on Claude Desktop API MCP tools? +

Route the Claude Desktop API MCP 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 Desktop API MCP tools fall into? +

Claude Desktop API MCP tools are categorised as Read (1), Destructive (1), Execute (2). Each category has a recommended default policy.

Enforce policy on every Claude Desktop API MCP tool call.

Start from Claude Desktop API MCP, 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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.