record_measurement
AI agents use record_measurement to create or update resources in Librarian MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Librarian MCP environment.
The name 'record_measurement' strongly implies writing/storing a measurement or metric value into a data store. Given the server context (benchmark metrics, accuracy tracking), this tool likely creates or updates a measurement record. Without a description, confidence is reduced. Classified as Write since recording data is a reversible write operation; no evidence of execution, deletion, or financial activity.
From the tool's definition Tool name: record_measurement; description is empty/uninformative.
Attacks that exploit this kind of access
record_measurement. It is categorised as a Write tool in the Librarian MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Librarian MCP server in PolicyLayer and add a rule for record_measurement: 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 Librarian MCP. Nothing to install.
record_measurement is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_measurement 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 record_measurement. 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.
record_measurement is provided by the Librarian MCP server (liana-banyan/librarian-mcp). 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 →