AI agents call knitbrain_verify_claim to retrieve information from Knitbrain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and cross-references information from a knowledge graph to verify claims. This is fundamentally a Read operation - it queries and returns data without side effects.
From the tool's definition Tool description states it will 'parse a stated codebase fact and check it against the knowledge graph' - this is a query/verification operation against stored data with no modification capability.
Attacks that exploit this kind of access
Hard claim-check (anti-hallucination): parse a stated codebase fact and check it against the knowledge graph. Supported shapes: \. It is categorised as a Read tool in the Knitbrain MCP Server, which means it retrieves data without modifying state.
Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_verify_claim: 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 Knitbrain. Nothing to install.
knitbrain_verify_claim 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 knitbrain_verify_claim 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 knitbrain_verify_claim. 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.
knitbrain_verify_claim is provided by the Knitbrain MCP server (pdgit12/knitbrain). 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 →