Search for routes by various criteria
AI agents call search_routes to retrieve information from FastAPI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about API routes without modifying, executing, or deleting anything. Searching and querying are classic read operations with no side effects. The blast radius if misused by an AI agent is minimal—it could at most leak information about the API structure.
From the tool's definition Tool name 'search_routes' and description 'Search for routes by various criteria' indicate querying/searching operations.
Attacks that exploit this kind of access
Search for routes by various criteria. It is categorised as a Read tool in the FastAPI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FastAPI MCP Server MCP server in PolicyLayer and add a rule for search_routes: 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 FastAPI MCP Server. Nothing to install.
search_routes 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 search_routes 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 search_routes. 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.
search_routes is provided by the FastAPI MCP Server MCP server (nabeelshar/fastapi-mcp-server). 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 →