find_similar_documents
AI agents call find_similar_documents to retrieve information from Strato Scopus MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries documents similar to a given document—a read-only operation with no side effects. The empty description lowers confidence slightly, but the consistent pattern of sibling tools and the suggestive name indicate read access to the Scopus literature database.
From the tool's definition Tool name 'find_similar_documents' implies retrieval of document metadata from Scopus. Sibling tools on this server (advanced_search, get_document_details, explore_topic) are all Read operations that query the Scopus database without modification.
Attacks that exploit this kind of access
find_similar_documents. It is categorised as a Read tool in the Strato Scopus MCP MCP Server, which means it retrieves data without modifying state.
Register the Strato Scopus MCP server in PolicyLayer and add a rule for find_similar_documents: 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 Strato Scopus MCP. Nothing to install.
find_similar_documents 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_similar_documents 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_similar_documents. 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_similar_documents is provided by the Strato Scopus MCP server (stratosphereips/strato-mcp-scopus). 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 →