mcp_server_run_tool · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What mcp_server_run_tool does on LocalAnt

AI agents invoke mcp_server_run_tool to trigger actions in LocalAnt. 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 mcp_server_run_tool needs a policy

This tool allows invoking any tool on downstream MCP servers, effectively bypassing the gateway's approval/permissioning model by delegating to unvetted downstream tools. An AI agent misusing this could trigger destructive, financial, or arbitrary code execution on connected systems. The critical severity reflects the gateway's loss of control over what actually executes on the target servers.

From the tool's definition Tool name 'mcp_server_run_tool' with description 'Invoke a tool on a downstream MCP server through the gateway' indicates execution of arbitrary tools on remote servers. The note 'Risk 3' (highest risk category) confirms this is a dangerous capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mcp_server_run_tool Rate-limited

mcp_server_run_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": {
    "mcp_server_run_tool": {
      "limits": [
        {
          "counter": "mcp_server_run_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about mcp_server_run_tool

What does the mcp_server_run_tool tool do? +

Invoke a tool on a downstream MCP server through the gateway. Risk 3. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mcp_server_run_tool? +

Register the LocalAnt MCP server in PolicyLayer and add a rule for mcp_server_run_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 LocalAnt. Nothing to install.

What risk level is mcp_server_run_tool? +

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

Can I rate-limit mcp_server_run_tool? +

Yes. Add a rate_limit block to the mcp_server_run_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 mcp_server_run_tool completely? +

Set action: deny in the PolicyLayer policy for mcp_server_run_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 mcp_server_run_tool? +

mcp_server_run_tool is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.