coord_complete_task · Session Coord MCP: Risk & Policy

WHAT IT DOES

What coord_complete_task does on Session Coord

AI agents use coord_complete_task to create or update resources in Session Coord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Session Coord environment.

WHY IT NEEDS A POLICY

Why coord_complete_task needs a policy

This tool creates or modifies coordination state (task completion status and path claim releases) but does not permanently delete data or trigger external code execution. The changes are reversible—tasks can be reopened and claims reclaimed. While it affects coordination metadata, the blast radius is limited to the local coordination session state, making this a low-severity Write operation.

From the tool's definition Tool description states 'Mark a task as done and optionally release path claims.' The action of marking a task as complete is a write operation that modifies the state of task records in the coordination system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

coord_complete_task Rate-limited

coord_complete_task 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": {
    "coord_complete_task": {
      "limits": [
        {
          "counter": "coord_complete_task_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 Session Coord, so you can run agents against it safely.

FAQ

Questions about coord_complete_task

What does the coord_complete_task tool do? +

Mark a task as done and optionally release path claims. It is categorised as a Write tool in the Session Coord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on coord_complete_task? +

Register the Session Coord MCP server in PolicyLayer and add a rule for coord_complete_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 Session Coord. Nothing to install.

What risk level is coord_complete_task? +

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

Can I rate-limit coord_complete_task? +

Yes. Add a rate_limit block to the coord_complete_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 coord_complete_task completely? +

Set action: deny in the PolicyLayer policy for coord_complete_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 coord_complete_task? +

coord_complete_task is provided by the Session Coord MCP server (lingfeng-vels/session-coord-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.