call_endpoint

THE RISK

High Risk

Why call_endpoint needs a policy

Calling an endpoint is an Execute-category action because it triggers external operations with unpredictable side effects depending on what endpoint is targeted. The blast radius is high because an AI agent could call any arbitrary endpoint, potentially triggering writes, deletions, or other destructive operations on external systems.

From the tool's definition 'Call the given endpoint' — triggers an external HTTP/API operation whose effects depend on the endpoint and arguments provided

Documented attack patterns abuse exactly the kind of access call_endpoint gives an agent:

POLICY

How to control call_endpoint

PolicyLayer is an MCP gateway — it sits between your AI agents and TypeSpec MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for call_endpoint:

policy.json

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

call_endpoint 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.

Create a free account and register TypeSpec MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More TypeSpec MCP Server tools

Destructive deleteTodo Delete a todo Destructive gists_delete Delete a gist Execute build Build typespec mcp project Execute compile Compile the typespec project in the given directory. Execute math_dot_product Computes the dot product of two vectors. Use this to find the scalar\nprojection of one ve Execute math_sub_vector Subtracts one vector from another. Use this to find the difference between\ntwo vectors. F Execute math_add_vector Adds two vectors together. Use this when you want to combine two vectors to\nget a resulta Write gists_fork Fork a gist

All 28 TypeSpec MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in TypeSpec MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about call_endpoint

What does the call_endpoint tool do? +

Call the given endpoint.\nUse the. It is categorised as a Execute tool in the TypeSpec MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on call_endpoint? +

Register the TypeSpec MCP Server MCP server in PolicyLayer and add a rule for call_endpoint: 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 TypeSpec MCP Server. Nothing to install.

What risk level is call_endpoint? +

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

Can I rate-limit call_endpoint? +

Yes. Add a rate_limit block to the call_endpoint 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 call_endpoint completely? +

Set action: deny in the PolicyLayer policy for call_endpoint. 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 call_endpoint? +

call_endpoint is provided by the TypeSpec MCP Server MCP server (microsoft/typespec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every TypeSpec MCP Server tool call.

Start from TypeSpec MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →