Orient yourself at the START of a session — the first thing a new pilot should do. In one call this surfaces (1) your self-model: the plate labeled \
AI agents call myco_orient 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 retrieves and surfaces existing state information (self-model, orientation data) at session start. It is a read/query operation with no indication of modifying, executing, or deleting data. Severity is low as it only exposes informational content about the agent's current state.
From the tool's definition Orient yourself at the START of a session — the first thing a new pilot should do. In one call this surfaces (1) your self-model
Attacks that exploit this kind of access
Orient yourself at the START of a session — the first thing a new pilot should do. In one call this surfaces (1) your self-model: the plate labeled \. 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_orient: 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_orient 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_orient 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_orient. 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_orient 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 →