AI agents call find_code_repo to retrieve information from Methods without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries or looks up information about code repositories related to papers—a retrieval operation with no side effects on data or systems. It does not modify, execute, delete, or move resources. Classification as Read is appropriate. Severity is low because discovering public repository metadata poses minimal security risk to the system or user data.
From the tool's definition Tool name 'find_code_repo' and description 'Discover the code repo (if any) associated with a paper' indicate a search/discovery operation that retrieves metadata about code repositories linked to academic papers.
Attacks that exploit this kind of access
Discover the code repo (if any) associated with a paper. It is categorised as a Read tool in the Methods MCP Server, which means it retrieves data without modifying state.
Register the Methods MCP server in PolicyLayer and add a rule for find_code_repo: 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 Methods. Nothing to install.
find_code_repo 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 find_code_repo 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 find_code_repo. 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.
find_code_repo is provided by the Methods MCP server (FlynnLachendro/methods-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 →