// MCP TOOL REFERENCE

CORTEX MEMORY TOOLS

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

View the Cortex Memory policy →
// ALL 5 CORTEX MEMORY TOOLS
READ 4 tools
Read cortex_get_context Returns the current working memory (Layer 1) as formatted text. Read cortex_get_decisions Returns all architectural decisions (ADRs) recorded for this project. Read cortex_search Searches episodic and semantic memory for matching episodes and decisions. Read cortex_status Returns memory health status including health score, entry counts, and warnings.
WRITE 1 tools
Write cortex_save_memory Saves a new memory, decision, or insight from the current session.

Route Cortex Memory through PolicyLayer and every one of its 5 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 Cortex Memory MCP server have? +

The Cortex Memory MCP server exposes 5 tools across 2 categories: Read, Write.

How do I enforce policies on Cortex Memory tools? +

Route the Cortex 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 Cortex Memory tools fall into? +

Cortex Memory tools are categorised as Read (4), Write (1). Each category has a recommended default policy.

Enforce policy on every Cortex Memory tool call.

Start from Cortex 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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.