http_request · MCP Toolkit MCP: Risk & Policy

WHAT IT DOES

What http_request does on MCP Toolkit

AI agents invoke http_request to trigger actions in MCP Toolkit. 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.

WHY IT NEEDS A POLICY

Why http_request needs a policy

Sending HTTP requests can trigger arbitrary external operations depending on the target URL and method — including POST/PUT/DELETE requests to external APIs, webhooks, or services. The effects depend entirely on the arguments provided, making this an Execute-category tool. It could be misused to interact with internal network services, exfiltrate data, or trigger destructive actions on external systems.

From the tool's definition 发送HTTP请求并返回完整响应信息 (Send HTTP request and return complete response information)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

http_request Rate-limited

http_request 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "http_request": {
      "limits": [
        {
          "counter": "http_request_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Toolkit, so you can run agents against it safely.

FAQ

Questions about http_request

What does the http_request tool do? +

发送HTTP请求并返回完整响应信息. It is categorised as a Execute tool in the MCP Toolkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on http_request? +

Register the MCP Toolkit MCP server in PolicyLayer and add a rule for http_request: 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. Nothing to install.

What risk level is http_request? +

http_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit http_request? +

Yes. Add a rate_limit block to the http_request 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.

How do I block http_request completely? +

Set action: deny in the PolicyLayer policy for http_request. 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.

What MCP server provides http_request? +

http_request is provided by the MCP Toolkit MCP server (zxfgds/mcp-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.