// MCP TOOL REFERENCE

CORTEX TOOLS

14 tools from the Cortex MCP Server, categorised by risk level.

View the Cortex policy →
// ALL 14 CORTEX TOOLS
READ 12 tools
Read active_memory_slice active_memory_slice Read context_assemble context_assemble Read memory_get memory_get Read memory_graph memory_graph Read memory_graph_audit Audit graph quality: orphans, dead links, one-way links, hubs, and stale edges. Read memory_graph_rebuild Rebuild the local typed graph side index from Obsidian memories. Read memory_list memory_list Read memory_recall memory_recall Read memory_remind memory_remind Read memory_search memory_search Read memory_timeline memory_timeline Read transcript_search transcript_search
WRITE 2 tools
Write memory_import memory_import Write memory_save memory_save

Route Cortex through PolicyLayer and every one of its 14 tools is checked against your policy before it runs.

GOVERN CORTEX →

Enforced before the call runs. Nothing to install.

// FAQ
How many tools does the Cortex MCP server have? +

The Cortex MCP server exposes 14 tools across 2 categories: Read, Write.

How do I enforce policies on Cortex tools? +

Route the Cortex 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 Cortex tools fall into? +

Cortex tools are categorised as Read (12), Write (2). Each category has a recommended default policy.

Enforce policy on every Cortex tool call.

Deterministic rules across all 14 Cortex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN CORTEX →

Free to start. No card required.

42,500+ MCP servers and 110,000+ 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.