api_put · Upmind MCP Server MCP: Risk & Policy

WHAT IT DOES

What api_put does on Upmind MCP Server

AI agents invoke api_put to trigger actions in Upmind 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.

WHY IT NEEDS A POLICY

Why api_put needs a policy

This tool can make PUT requests to ANY Upmind API endpoint, meaning it can update or overwrite arbitrary resources across the platform. While PUT is typically a Write operation, the unrestricted 'any endpoint' scope means it could be used to overwrite critical configuration, pricing, user data, or other sensitive platform resources.

From the tool's definition Make a PUT request to any Upmind API endpoint

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

api_put Rate-limited

api_put 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": {
    "api_put": {
      "limits": [
        {
          "counter": "api_put_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 Upmind MCP Server, so you can run agents against it safely.

FAQ

Questions about api_put

What does the api_put tool do? +

Make a PUT request to any Upmind API endpoint. It is categorised as a Execute tool in the Upmind 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 api_put? +

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

What risk level is api_put? +

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

Can I rate-limit api_put? +

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

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

api_put is provided by the Upmind MCP Server MCP server (stardeltapower/upmind-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.