claude_code_task · MCP-Claude Code Bridge MCP: Risk & Policy

WHAT IT DOES

What claude_code_task does on MCP-Claude Code Bridge

AI agents invoke claude_code_task to trigger actions in MCP-Claude Code Bridge. 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 claude_code_task needs a policy

This tool executes arbitrary coding tasks via Claude Code CLI. While the name doesn't explicitly say "run" or "exec", the verb "Execute" in the description combined with the context of building projects, APIs, and scripts means it triggers external operations whose effects depend entirely on the task arguments.

From the tool's definition Tool description states "Execute a coding task using Claude Code CLI"; sibling tools include run_command which suggests arbitrary command execution; server description mentions "creating React apps, building APIs, and debugging scripts" which are all…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claude_code_task Rate-limited

claude_code_task 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": {
    "claude_code_task": {
      "limits": [
        {
          "counter": "claude_code_task_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-Claude Code Bridge, so you can run agents against it safely.

FAQ

Questions about claude_code_task

What does the claude_code_task tool do? +

Execute a coding task using Claude Code CLI. It is categorised as a Execute tool in the MCP-Claude Code Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on claude_code_task? +

Register the MCP-Claude Code Bridge MCP server in PolicyLayer and add a rule for claude_code_task: 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-Claude Code Bridge. Nothing to install.

What risk level is claude_code_task? +

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

Can I rate-limit claude_code_task? +

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

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

claude_code_task is provided by the MCP-Claude Code Bridge MCP server (sobieskicodes/claude-desktop-mcp-to-claude-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.