Load a FastAPI application from a module path (e.g.,
AI agents invoke load_fastapi_app to trigger actions in FastAPI MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Loading a module from a path executes Python code — it imports and instantiates the application, which runs arbitrary module-level and startup code. This is an Execute-category action because its effects depend on the module being loaded and can trigger side effects beyond mere data retrieval.
From the tool's definition Load a FastAPI application from a module path
Attacks that exploit this kind of access
Load a FastAPI application from a module path (e.g.,. It is categorised as a Execute tool in the FastAPI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FastAPI MCP Server MCP server in PolicyLayer and add a rule for load_fastapi_app: 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.
load_fastapi_app is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the load_fastapi_app 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 load_fastapi_app. 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.
load_fastapi_app 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 →