mcpdev_inspector_call_tool · MCP Dev MCP: Risk & Policy

WHAT IT DOES

What mcpdev_inspector_call_tool does on MCP Dev MCP

AI agents invoke mcpdev_inspector_call_tool to trigger actions in MCP Dev MCP. 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 mcpdev_inspector_call_tool needs a policy

This tool allows an LLM agent to execute any tool exposed by a target MCP server with arbitrary arguments. While the immediate effect depends on what tools exist on the target server, the tool itself is a general-purpose executor that can trigger code, shell commands, or other operations.

From the tool's definition Tool description explicitly states 'Execute a tool on a target MCP server' and 'invoke a specific tool on the target server with provided arguments.' This directly enables running arbitrary operations on remote/local MCP servers.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mcpdev_inspector_call_tool Rate-limited

mcpdev_inspector_call_tool 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": {
    "mcpdev_inspector_call_tool": {
      "limits": [
        {
          "counter": "mcpdev_inspector_call_tool_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 Dev MCP, so you can run agents against it safely.

FAQ

Questions about mcpdev_inspector_call_tool

What does the mcpdev_inspector_call_tool tool do? +

Execute a tool on a target MCP server. Use this to invoke a specific tool on the target server with provided arguments. Args: - target (string): Target MCP server - command or URL - transport (. It is categorised as a Execute tool in the MCP Dev MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mcpdev_inspector_call_tool? +

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

What risk level is mcpdev_inspector_call_tool? +

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

Can I rate-limit mcpdev_inspector_call_tool? +

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

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

mcpdev_inspector_call_tool is provided by the MCP Dev MCP server (kongyo2/mcpdevmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.