task-checker · Spec MCP Server MCP: Risk & Policy

WHAT IT DOES

What task-checker does on Spec MCP Server

AI agents invoke task-checker to trigger actions in Spec 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 task-checker needs a policy

task-checker executes commands (tests, type-checking, linting, builds) against a codebase. While these are typically non-destructive development operations, they are Execute-category because they trigger external processes and their side effects (build artifacts, test databases, temporary files, resource consumption) depend on what the underlying project scripts do.

From the tool's definition Tool description states it 'run[s] tests/type-check/lint/build using commands' and 'Returns a PASS/FAIL decision rule.' The verb 'run' combined with execution of automated testing/build commands indicates this triggers external operations whose effects depend…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

task-checker Rate-limited

task-checker 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": {
    "task-checker": {
      "limits": [
        {
          "counter": "task-checker_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 Spec MCP Server, so you can run agents against it safely.

FAQ

Questions about task-checker

What does the task-checker tool do? +

Prompt-only verification: instruct the agent to verify acceptance criteria and run tests/type-check/lint/build using commands from steering tech.md or detected project setup. Returns a PASS/FAIL decision rule. It is categorised as a Execute tool in the Spec 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 task-checker? +

Register the Spec MCP Server MCP server in PolicyLayer and add a rule for task-checker: 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 Spec MCP Server. Nothing to install.

What risk level is task-checker? +

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

Can I rate-limit task-checker? +

Yes. Add a rate_limit block to the task-checker 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 task-checker completely? +

Set action: deny in the PolicyLayer policy for task-checker. 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 task-checker? +

task-checker is provided by the Spec MCP Server MCP server (karol-f/spec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.