AI agents call get_paper_metadata 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 performs a lookup/resolution operation to fetch canonical metadata about academic papers. This is a pure Read operation: it retrieves information about papers (metadata) with no side effects, no data modification, no code execution, and no destructive actions. The low severity reflects that metadata retrieval poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description states 'Resolve an arXiv ID/URL, bioRxiv URL, DOI, or generic URL to canonical metadata' — this is a retrieval operation that queries metadata without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Resolve an arXiv ID/URL, bioRxiv URL, DOI, or generic URL to canonical metadata. 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 get_paper_metadata: 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.
get_paper_metadata 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 get_paper_metadata 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 get_paper_metadata. 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.
get_paper_metadata 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 →