Make an HTTP request to any external API endpoint and return the response. Supported features: - All HTTP methods: GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS - Custom headers (including Authorization / Bearer tokens) - JSON and form-urlencoded request bodies - URL query parameters (via url or p...
AI agents invoke api_call to trigger actions in MCP Toolkit 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.
This tool can trigger arbitrary external HTTP requests including destructive methods (DELETE), financial operations (payment APIs), data exfiltration, and webhook triggers. It supports all HTTP methods with custom auth headers, meaning an AI agent could misuse it to interact with any external service — including deleting resources, initiating payments, or exfiltrating data.
From the tool's definition Make an HTTP request to any external API endpoint... All HTTP methods: GET, POST, PUT, PATCH, DELETE... Custom headers (including Authorization / Bearer tokens)... Sending webhooks
Attacks that exploit this kind of access
Make an HTTP request to any external API endpoint and return the response. Supported features: - All HTTP methods: GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS - Custom headers (including Authorization / Bearer tokens) - JSON and form-urlencoded request bodies - URL query parameters (via url or params) - Configurable timeout (default 15 seconds) - Response includes status code, headers, and body Use cases: - Fetching data from REST APIs - Sending webhooks - Querying third-party services (weather, maps, etc.) - Testing and debugging API endpoints. It is categorised as a Execute tool in the MCP Toolkit Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Toolkit Server MCP server in PolicyLayer and add a rule for api_call: 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 MCP Toolkit Server. Nothing to install.
api_call 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 api_call 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 api_call. 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.
api_call is provided by the MCP Toolkit Server MCP server (vyshnavi-nandyala/mcp-toolkit-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 →