# record_work_item_local_proof

Record that ONE acceptance criterion was checked LOCALLY, at a named commit, with the command that was run and where its output lives. This is the gate in front of staging, and it is a different record from a QA receipt. A QA receipt says an independent credential re-ran a criterion against a deployment; this says the builder ran it on their own machine before asking for a deploy at all. It cannot be filed as QA evidence and it opens no QA gate. A card is

Agent View of the PolicyLayer registry record for `record_work_item_local_proof`. HTML page: https://policylayer.com/tools/adrata-adrata-mcp/record-work-item-local-proof

## Facts

- Tool: `record_work_item_local_proof`
- Server: Adrata (`@adrata/adrata-mcp`) — https://policylayer.com/tools/adrata-adrata-mcp.md
- Install: `npx -y @adrata/adrata-mcp`
- Homepage: https://www.npmjs.com/package/@adrata/adrata-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "record_work_item_local_proof",
    "arguments": {}
  }
}
```

## Why record_work_item_local_proof is rated High

record_work_item_local_proof triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke record_work_item_local_proof to trigger actions in Adrata. 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.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "record_work_item_local_proof": {
      "limits": [
        {
          "counter": "record_work_item_local_proof_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Adrata (394)

- `bulk_delete_buyer_groups` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/bulk-delete-buyer-groups.md
- `cancel_agent_task` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/cancel-agent-task.md
- `delete_action` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-action.md
- `delete_buyer_group` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-buyer-group.md
- `delete_company` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-company.md
- `delete_note` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-note.md
- `delete_opportunity` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-opportunity.md
- `delete_partner` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-partner.md
- `delete_person` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-person.md
- `delete_webhook` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-webhook.md
- `delete_work_item` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-work-item.md
- `delete_work_item_acceptance_criterion` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/delete-work-item-acceptance-criterion.md
- `flag_work_item` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/flag-work-item.md
- `forget` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/forget.md
- `paper_delete_document` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/paper-delete-document.md
- `paper_revoke_share` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/paper-revoke-share.md
- `remove_buyer_group_member` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/remove-buyer-group-member.md
- `remove_work_item_from_launch` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/remove-work-item-from-launch.md
- `requeue_work_item_qa_after_fix` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/requeue-work-item-qa-after-fix.md
- `tag_work_item_criterion_staging_only` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/tag-work-item-criterion-staging-only.md
- `unblock_work_item` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/unblock-work-item.md
- `unfile_document` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/unfile-document.md
- `unlink_proposition` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/unlink-proposition.md
- `unrelate_decisions` — Destructive — https://policylayer.com/tools/adrata-adrata-mcp/unrelate-decisions.md
- `adrata_ai_tool_execute` — Execute — https://policylayer.com/tools/adrata-adrata-mcp/adrata-ai-tool-execute.md
- `adrata_api_request` — Execute — https://policylayer.com/tools/adrata-adrata-mcp/adrata-api-request.md
- `attribute_partner_to_deal` — Execute — https://policylayer.com/tools/adrata-adrata-mcp/attribute-partner-to-deal.md
- `block_work_item` — Execute — https://policylayer.com/tools/adrata-adrata-mcp/block-work-item.md
- `build_pursuit_command_center` — Execute — https://policylayer.com/tools/adrata-adrata-mcp/build-pursuit-command-center.md
- `draft_workflow` — Execute — https://policylayer.com/tools/adrata-adrata-mcp/draft-workflow.md
- …and 364 more: https://policylayer.com/tools/adrata-adrata-mcp.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=adrata-adrata-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/adrata-adrata-mcp
