run_spec · MCP Workbench MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_spec does on MCP Workbench MCP Server

AI agents invoke run_spec to trigger actions in MCP Workbench 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 run_spec needs a policy

The tool's core function is to execute test specifications, which constitutes code/command execution. While framed as validation/testing, the tool enables an agent to run arbitrary YAML-defined operations against MCP servers without inherent guardrails on what those operations do.

From the tool's definition Tool description states 'Run a YAML test spec against an MCP server' — this executes arbitrary test specifications against external services.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_spec Rate-limited

run_spec 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": {
    "run_spec": {
      "limits": [
        {
          "counter": "run_spec_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 Workbench MCP Server, so you can run agents against it safely.

FAQ

Questions about run_spec

What does the run_spec tool do? +

Run a YAML test spec against an MCP server and return results. Provide either specText (inline YAML) or specPath (path to a file). At least one is required. It is categorised as a Execute tool in the MCP Workbench 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 run_spec? +

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

What risk level is run_spec? +

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

Can I rate-limit run_spec? +

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

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

run_spec is provided by the MCP Workbench MCP Server MCP server (raeseoklee/mcp-workbench-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.