AI agents call knitbrain_get_learning 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 pre-existing lesson data based on a learning ID. It performs a simple data retrieval operation with no capability to modify, execute external operations, delete data, or commit financial transactions. The blast radius of misuse is minimal—an AI agent could only over-retrieve lessons, which has negligible security impact.
From the tool's definition The tool description explicitly states 'Fetch the full lesson' which is a retrieval operation with no modification or side effects. The name 'get_learning' further reinforces this as a read-only operation.
Attacks that exploit this kind of access
Fetch the full lesson for a learning id (from knitbrain_search_learnings). 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_get_learning: 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_get_learning 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_get_learning 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_get_learning. 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_get_learning 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 →