Alias for find_existing_abstractions.
AI agents call find_duplicates to retrieve information from BLUEPRINT MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches/queries architectural data to help agents discover existing abstractions and patterns. It retrieves information without modifying, executing, or deleting anything. No side effects or state changes occur. The lowest severity applies because misuse would only yield incorrect or irrelevant architectural guidance, not cause operational harm.
From the tool's definition Tool is an alias for 'find_existing_abstractions', which queries and retrieves existing code patterns and abstractions. The verb 'find' and the sibling tool 'scan_repo' indicate data retrieval operations with no side effects.
Attacks that exploit this kind of access
Alias for find_existing_abstractions. It is categorised as a Read tool in the BLUEPRINT MCP MCP Server, which means it retrieves data without modifying state.
Register the BLUEPRINT MCP server in PolicyLayer and add a rule for find_duplicates: 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 BLUEPRINT MCP. Nothing to install.
find_duplicates 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_duplicates 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_duplicates. 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_duplicates is provided by the BLUEPRINT MCP server (vedv7/blueprint.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 →