coding_agent_continue_task · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What coding_agent_continue_task does on LocalAnt

AI agents invoke coding_agent_continue_task 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 coding_agent_continue_task needs a policy

A coding agent that executes tasks can run code, modify files, invoke shell commands, or trigger other operations. Continuing a task with additional instructions means driving an autonomous agent further, which constitutes executing actions. The blast radius is high because a coding agent can affect the file system, execute code, and interact with the environment.

From the tool's definition 'coding_agent_continue_task' - continues a coding agent task with additional instructions; the server description mentions 'coding agents' as one of the controlled capabilities

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

coding_agent_continue_task Rate-limited

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

FAQ

Questions about coding_agent_continue_task

What does the coding_agent_continue_task tool do? +

${DEPRECATED} Continue a task with additional instructions on the same branch. 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 coding_agent_continue_task? +

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

What risk level is coding_agent_continue_task? +

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

Can I rate-limit coding_agent_continue_task? +

Yes. Add a rate_limit block to the coding_agent_continue_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 coding_agent_continue_task completely? +

Set action: deny in the PolicyLayer policy for coding_agent_continue_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 coding_agent_continue_task? +

coding_agent_continue_task 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.