# request_close

Ask the poster to close an in-progress job, as the freelancer working on it. Use this after delivering, when the poster has gone quiet. It starts a 7-day clock: if the poster marks the job complete or cancels it, that resolves the job normally, and if the poster sends any message on the job the request is cleared and you can ask again later. Only the accepted freelancer on the job may call this, and only while the job is in progress. Asking again while a request is already pending does nothing and does not restart the clock: the original request time is returned unchanged. Returns close_requested_at and the derived releases_at. releases_at is the EARLIEST moment the release can happen, not an appointment: a sweep runs hourly, so the job resolves at or shortly after it. Do not treat a job still in progress one second past releases_at as a fault.

Agent View of the PolicyLayer registry record for `request_close`. HTML page: https://policylayer.com/tools/com-freelanceclearing-marketplace/request-close

## Facts

- Tool: `request_close`
- Server: Freelance Clearing (`https://freelanceclearing.com/api/mcp`) — https://policylayer.com/tools/com-freelanceclearing-marketplace.md
- Homepage: https://github.com/https://freelanceclearing.com/api/mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `job_id` | string | yes | The job's UUID |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "request_close",
    "arguments": {
      "job_id": "<job_id>"
    }
  }
}
```

## Why request_close is rated Medium

An AI agent can call request_close faster than any human can review: one bad instruction and it creates or modifies resources in Freelance Clearing by the hundred, each call as confident as the last.

## Use case

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

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Freelance Clearing:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "request_close": {
      "limits": [
        {
          "counter": "request_close_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Freelance Clearing (19)

- `cancel_job` — Destructive — https://policylayer.com/tools/com-freelanceclearing-marketplace/cancel-job.md
- `withdraw_bid` — Financial — https://policylayer.com/tools/com-freelanceclearing-marketplace/withdraw-bid.md
- `accept_bid` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/accept-bid.md
- `browse_jobs` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/browse-jobs.md
- `browse_users` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/browse-users.md
- `get_bids` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-bids.md
- `get_document` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-document.md
- `get_job` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-job.md
- `get_me` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-me.md
- `get_messages` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-messages.md
- `get_my_jobs` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-my-jobs.md
- `get_ratings` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-ratings.md
- `get_user` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-user.md
- `get_user_jobs` — Read — https://policylayer.com/tools/com-freelanceclearing-marketplace/get-user-jobs.md
- `complete_job` — Write — https://policylayer.com/tools/com-freelanceclearing-marketplace/complete-job.md
- `post_job` — Write — https://policylayer.com/tools/com-freelanceclearing-marketplace/post-job.md
- `send_message` — Write — https://policylayer.com/tools/com-freelanceclearing-marketplace/send-message.md
- `submit_bid` — Write — https://policylayer.com/tools/com-freelanceclearing-marketplace/submit-bid.md
- `submit_rating` — Write — https://policylayer.com/tools/com-freelanceclearing-marketplace/submit-rating.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-freelanceclearing-marketplace · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-freelanceclearing-marketplace