call_custom_endpoint · MCP Intigriti Server MCP

WHAT IT DOES

What call_custom_endpoint does on MCP Intigriti Server

AI agents invoke call_custom_endpoint to trigger actions in MCP Intigriti 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.

WHY IT NEEDS A POLICY

Why call_custom_endpoint needs a policy

This tool executes arbitrary API calls to an external platform. Since the endpoint is user-specified and could trigger any action (read, write, or destructive), it must be classified at the most severe plausible category. The description explicitly notes it's for 'beta endpoints', meaning effects are unpredictable.

From the tool's definition 'Call a custom API endpoint' - executes arbitrary API calls to the Intigriti platform with unspecified parameters and effects

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_custom_endpoint Rate-limited

call_custom_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "call_custom_endpoint": {
      "limits": [
        {
          "counter": "call_custom_endpoint_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 Intigriti Server, so you can run agents against it safely.

FAQ

Questions about call_custom_endpoint

What does the call_custom_endpoint tool do? +

Call a custom API endpoint (useful for new beta endpoints). It is categorised as a Execute tool in the MCP Intigriti 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_custom_endpoint? +

Register the MCP Intigriti Server MCP server in PolicyLayer and add a rule for call_custom_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 MCP Intigriti Server. Nothing to install.

What risk level is call_custom_endpoint? +

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

Can I rate-limit call_custom_endpoint? +

Yes. Add a rate_limit block to the call_custom_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_custom_endpoint completely? +

Set action: deny in the PolicyLayer policy for call_custom_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_custom_endpoint? +

call_custom_endpoint is provided by the MCP Intigriti Server MCP server (jdc94/mcp-intigriti-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.