Find papers semantically similar to a given paper (pgvector cosine).
AI agents call similar_papers to retrieve information from surveyHelper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only search/query operation. It retrieves and returns data (similar papers) from the knowledge base without modifying, executing external code, deleting, or committing financial transactions. The operation is deterministic based on the input paper and has no reversible or irreversible side effects on the system or data.
From the tool's definition The tool 'similar_papers' uses semantic search (pgvector cosine) to find papers matching a given paper. The description indicates it 'finds' papers, which is a retrieval operation with no side effects—no data is created, modified, or deleted.
Attacks that exploit this kind of access
Find papers semantically similar to a given paper (pgvector cosine). It is categorised as a Read tool in the surveyHelper MCP Server, which means it retrieves data without modifying state.
Register the surveyHelper MCP server in PolicyLayer and add a rule for similar_papers: 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 surveyHelper. Nothing to install.
similar_papers 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 similar_papers 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 similar_papers. 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.
similar_papers is provided by the surveyHelper MCP server (rich7420/surveyhelper). 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 →