Read your compact \
AI agents call myco_recall to retrieve information from Myco — Agent-First Cognitive Substrate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is designed to retrieve or query data from the cognitive substrate. The description explicitly states 'Read', and 'recall' is a retrieval operation. No side effects, creation, modification, deletion, execution, or financial impact are indicated. This falls squarely into the Read category with low severity since it only accesses existing data without altering state.
From the tool's definition Tool name 'myco_recall' and description fragment 'Read your compact' explicitly indicate a retrieval/query operation with no modification capability.
Attacks that exploit this kind of access
Read your compact \. It is categorised as a Read tool in the Myco — Agent-First Cognitive Substrate MCP Server, which means it retrieves data without modifying state.
Register the Myco — Agent-First Cognitive Substrate MCP server in PolicyLayer and add a rule for myco_recall: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Myco — Agent-First Cognitive Substrate. Nothing to install.
myco_recall is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the myco_recall rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for myco_recall. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
myco_recall is provided by the Myco — Agent-First Cognitive Substrate MCP server (myco). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →