Performs a standard REST API request. Supports custom methods, headers, and request bodies. Responses are truncated to a specified limit to prevent context overflow.
AI agents invoke fetch_api to trigger actions in Web-curl 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.
This tool executes arbitrary HTTP requests with custom methods (including POST, PUT, DELETE, PATCH), headers, and request bodies against external APIs. Because it can trigger any HTTP method against any endpoint, it goes beyond simple reading and can cause side effects on external systems depending on the method and target. This places it in the Execute category, as the effects depend on the arguments provided.
From the tool's definition Performs a standard REST API request. Supports custom methods, headers, and request bodies.
Documented attack patterns abuse exactly the kind of access fetch_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Web-curl MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_api:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_api": {
"limits": [
{
"counter": "fetch_api_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}fetch_api stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Performs a standard REST API request. Supports custom methods, headers, and request bodies. Responses are truncated to a specified limit to prevent context overflow. It is categorised as a Execute tool in the Web-curl MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Web-curl MCP Server MCP server in PolicyLayer and add a rule for fetch_api: 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 Web-curl MCP Server. Nothing to install.
fetch_api 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 fetch_api 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 fetch_api. 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.
fetch_api is provided by the Web-curl MCP Server MCP server (rayss868/mcp-web-curl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Web-curl MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Web-curl MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.