call_method · Frappe MCP Server MCP: Risk & Policy

WHAT IT DOES

What call_method does on Frappe MCP Server

AI agents invoke call_method to trigger actions in Frappe 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 call_method needs a policy

This tool executes whitelisted Frappe methods, which are server-side operations whose effects depend entirely on which method is called and its arguments. While 'whitelisted' provides some safeguard, the tool enables triggering of external operations and code execution.

From the tool's definition Tool name 'call_method' combined with description 'Execute a whitelisted Frappe method' directly indicates execution of arbitrary code/methods.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_method Rate-limited

call_method 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_method": {
      "limits": [
        {
          "counter": "call_method_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 Frappe MCP Server, so you can run agents against it safely.

FAQ

Questions about call_method

What does the call_method tool do? +

Execute a whitelisted Frappe method. It is categorised as a Execute tool in the Frappe 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_method? +

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

What risk level is call_method? +

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

Can I rate-limit call_method? +

Yes. Add a rate_limit block to the call_method 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_method completely? +

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

call_method is provided by the Frappe MCP Server MCP server (kiran-harbak/frappe_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.