PERCEPTION (Phase α / M24.5 observatory snapshot): expose ALL cultivar vital signs from inside the substrate so Claude can read its own metabolic state. Returns the Living Bets signals #1-10 — #1 persistence budget (DAG size + cycle counter), #2 evolution rate, #3 read-pattern diversity, #4 feder...
AI agents call myco_query_substrate_observatory 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.
This tool performs read-only observation of the cognitive substrate's internal state (persistence budget, evolution rate, cost metrics, health scores, etc.). It retrieves system telemetry and diagnostic data without modifying the substrate, triggering external actions, or committing resources. The 'PERCEPTION' label and list of returned signals (signals #1-10 plus detectors) confirm it is introspective monitoring.
From the tool's definition Tool name contains 'query' and description explicitly states 'expose ALL cultivar vital signs' and 'Returns the Living Bets signals' — functions purely as internal system state inspection/telemetry.
Attacks that exploit this kind of access
PERCEPTION (Phase α / M24.5 observatory snapshot): expose ALL cultivar vital signs from inside the substrate so Claude can read its own metabolic state. Returns the Living Bets signals #1-10 — #1 persistence budget (DAG size + cycle counter), #2 evolution rate, #3 read-pattern diversity, #4 federation health, #5 time trends, #6 read-window-relative position (iff a context-window is attested), #7/#8/#9 compute/network/storage cost per cycle, #10 composite health score — plus the C37 doctrine-revision-burst detector and the bet_weakening_quorum (the composite L0/cards/LB_living_bets falsifiability counter). Signals the substrate omits at the current observatory_format_version are absent from the output. Read-only. 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_query_substrate_observatory: 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_query_substrate_observatory 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_query_substrate_observatory 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_query_substrate_observatory. 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_query_substrate_observatory 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 →