substrate_info
AI agents call substrate_info to retrieve information from Weighted Compact without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata or state information about the local memory substrate without modifying, executing operations, or causing side effects. The server architecture explicitly limits this to read-only operations over local project files. Severity is low because it accesses only local cached data with no destructive or external operation capability.
From the tool's definition Tool name 'substrate_info' and server description indicate a read-only MCP tool. Server explicitly states 'three read-only MCP tools' including this one, with 'zero outbound calls'.
Attacks that exploit this kind of access
substrate_info. It is categorised as a Read tool in the Weighted Compact MCP Server, which means it retrieves data without modifying state.
Register the Weighted Compact MCP server in PolicyLayer and add a rule for substrate_info: 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 Weighted Compact. Nothing to install.
substrate_info 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 substrate_info 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 substrate_info. 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.
substrate_info is provided by the Weighted Compact MCP server (zzallirog/weighted-compact). 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 →