finish_todo · Code Analysis MCP Server MCP: Risk & Policy

WHAT IT DOES

What finish_todo does on Code Analysis MCP Server

AI agents use finish_todo to create or update resources in Code Analysis MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Analysis MCP Server environment.

WHY IT NEEDS A POLICY

Why finish_todo needs a policy

The tool updates todo status and records git information, which constitute reversible data modifications. This falls under Write rather than Destructive because marking a todo complete does not irreversibly delete or remove the item—it changes metadata. The action is low severity because it only affects internal task tracking and git logs, with minimal blast radius for misuse by an AI agent.

From the tool's definition Tool marks a todo item as 'completed' and records git logs. This modifies state (todo status) and git history, but is reversible (a todo can be unmarked or git commits can be amended).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

finish_todo Rate-limited

finish_todo stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "finish_todo": {
      "limits": [
        {
          "counter": "finish_todo_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Code Analysis MCP Server, so you can run agents against it safely.

FAQ

Questions about finish_todo

What does the finish_todo tool do? +

完成待办事项（标记为completed并记录git日志）. It is categorised as a Write tool in the Code Analysis MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on finish_todo? +

Register the Code Analysis MCP Server MCP server in PolicyLayer and add a rule for finish_todo: 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 Code Analysis MCP Server. Nothing to install.

What risk level is finish_todo? +

finish_todo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit finish_todo? +

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

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

finish_todo is provided by the Code Analysis MCP Server MCP server (zeocax/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.