start_kwork · Kwork MCP: Risk & Policy

WHAT IT DOES

What start_kwork does on Kwork

AI agents invoke start_kwork to trigger actions in Kwork. 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 start_kwork needs a policy

The tool description is empty, which lowers confidence. However, context from sibling tools (delete_message, delete_offer, edit_message, get_dialog, manage orders) indicates this server mediates real marketplace transactions. 'Start' on such a platform likely initiates a binding action (e.g., starting work on a project, commencing an order) whose consequences depend on arguments and cannot be trivially reversed.

From the tool's definition Tool name 'start_kwork' on a freelance marketplace MCP server with sibling tools that manage orders, offers, and messages.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_kwork Rate-limited

start_kwork 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": {
    "start_kwork": {
      "limits": [
        {
          "counter": "start_kwork_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 Kwork, so you can run agents against it safely.

FAQ

Questions about start_kwork

What does the start_kwork tool do? +

start_kwork. It is categorised as a Execute tool in the Kwork MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_kwork? +

Register the Kwork MCP server in PolicyLayer and add a rule for start_kwork: 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 Kwork. Nothing to install.

What risk level is start_kwork? +

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

Can I rate-limit start_kwork? +

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

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

start_kwork is provided by the Kwork MCP server (simonether/kwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.