Read back the HUMAN-READABLE content of a single DAG node by its hash — fetched directly via the substrate (ANY node, not just the recent window). Decodes the node
AI agents call myco_read_node_content 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 is a Read operation: it retrieves and decodes existing data from the cognitive substrate without side effects. Severity is medium rather than low because unrestricted read access to 'ANY node' in an agent's cognitive substrate (including internal reasoning, intents, and decision context) could expose sensitive planning information, previous agent states, or private reasoning chains that an attacker might…
From the tool's definition Tool name contains 'read' and description states 'Read back the HUMAN-READABLE content of a single DAG node' — explicitly a retrieval operation with no modification. Decodes and fetches existing node data.
Attacks that exploit this kind of access
Read back the HUMAN-READABLE content of a single DAG node by its hash — fetched directly via the substrate (ANY node, not just the recent window). Decodes the node. 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_read_node_content: 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_read_node_content 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_read_node_content 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_read_node_content. 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_read_node_content 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.
myco_read_node_content is one line of Myco — Agent-First Cognitive Substrate's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →