AI agents call extract_methods 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.
The tool extracts or retrieves methods information from academic papers without modifying, deleting, or executing external operations. This is a read-only operation that queries paper content. No description provided, but context strongly supports Read classification. Severity is low because extraction of academic paper metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'extract_methods' with context from sibling tools (fetch_paper_text, get_paper_metadata, summarize_paper) and server purpose 'structured methods extraction...on academic papers' indicates data retrieval from papers.
Attacks that exploit this kind of access
extract_methods. 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 extract_methods: 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.
extract_methods 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 extract_methods 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 extract_methods. 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.
extract_methods 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 →