complete_project · Clink MCP Server MCP: Risk & Policy

WHAT IT DOES

What complete_project does on Clink MCP Server

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

WHY IT NEEDS A POLICY

Why complete_project needs a policy

This tool creates or modifies data reversibly—it changes a project's status flag but does not delete, destroy, or irreversibly alter the project or its contents. It is consistent with Write category operations (update). The blast radius is low because marking a project complete has minimal side effects: it only affects visibility and status metadata, not deletion or financial/operational consequences.

From the tool's definition Tool description states 'Mark a project as completed', which modifies project state from active to completed.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_project Rate-limited

complete_project 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": {
    "complete_project": {
      "limits": [
        {
          "counter": "complete_project_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 Clink MCP Server, so you can run agents against it safely.

FAQ

Questions about complete_project

What does the complete_project tool do? +

Mark a project as completed. Completed projects remain visible but indicate all work is done. It is categorised as a Write tool in the Clink 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 complete_project? +

Register the Clink MCP Server MCP server in PolicyLayer and add a rule for complete_project: 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 Clink MCP Server. Nothing to install.

What risk level is complete_project? +

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

Can I rate-limit complete_project? +

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

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

complete_project is provided by the Clink MCP Server MCP server (voxos-ai-inc/clink-mcp-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.