// MCP TOOL REFERENCE

COGNEE TOOLS

7 tools from the Cognee MCP Server, categorised by risk level.

// ALL 7 COGNEE TOOLS

READ 3 tools

Read cognify_status Get processing status of a cognify job Read list_data List all datasets or data items Read search Query the knowledge graph

WRITE 1 tools

Write save_interaction Log interactions to knowledge graph

DESTRUCTIVE 2 tools

Destructive delete Delete a data item by ID Destructive prune Clear all data and reset knowledge graph

EXECUTE 1 tools

Execute cognify Transform data into knowledge graph

// RUNNING THIS SERVER

The managed route: connect Cognee 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 @topoteretes/cognee

// FAQ

How many tools does the Cognee MCP server have? +

The Cognee MCP server exposes 7 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Cognee tools? +

Route the Cognee 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 Cognee tools fall into? +

Cognee tools are categorised as Read (3), Write (1), Destructive (2), Execute (1). 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.