AI agents call knitbrain_search_learnings 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 queries stored project learnings data without creating, modifying, deleting, or executing any operations. It is non-destructive read-only access to an internal knowledge store. The low severity reflects minimal blast radius — misuse would only expose existing project knowledge, not cause system changes or data loss.
From the tool's definition Tool performs a search operation that 'returns ranked headlines' — a data retrieval action with no modification or side effects.
Attacks that exploit this kind of access
Search project learnings; returns ranked headlines (id + summary). Call knitbrain_get_learning for a full lesson. 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_search_learnings: 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_search_learnings 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_search_learnings 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_search_learnings. 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_search_learnings 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 →