# conv_request_human

Flag the current conversation as needing human attention. Use this when you can\

Agent View of the PolicyLayer registry record for `conv_request_human`. HTML page: https://policylayer.com/tools/com-getmunin-munin/conv-request-human

## Facts

- Tool: `conv_request_human`
- Server: Munin (`https://mcp.getmunin.com/mcp`) — https://policylayer.com/tools/com-getmunin-munin.md
- Homepage: https://github.com/getmunin/munin
- Risk category: Write (Medium risk)
- Registry record: grade D, identity unverified
- Server auth posture: gated
- 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": "conv_request_human",
    "arguments": {}
  }
}
```

## Why conv_request_human is rated Medium

This tool modifies conversation state by adding a flag/marker, which is a reversible write operation. It does not execute external operations, delete data, or cause financial transactions. The blast radius is minimal—worst case is incorrect flagging that can be undone. Low severity because the impact is limited to internal workflow state.

From the tool's own definition: "Tool description states 'Flag the current conversation as needing human attention.' Flagging is a metadata modification action that creates or updates a status marker on a conversation record."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Munin (241)

- `analytics_revoke_tracker` — Destructive — https://policylayer.com/tools/com-getmunin-munin/analytics-revoke-tracker.md
- `analytics_rotate_tracker_key` — Destructive — https://policylayer.com/tools/com-getmunin-munin/analytics-rotate-tracker-key.md
- `bookings_cancel_booking` — Destructive — https://policylayer.com/tools/com-getmunin-munin/bookings-cancel-booking.md
- `bookings_cancel_my_booking` — Destructive — https://policylayer.com/tools/com-getmunin-munin/bookings-cancel-my-booking.md
- `cms_delete_asset` — Destructive — https://policylayer.com/tools/com-getmunin-munin/cms-delete-asset.md
- `cms_delete_collection` — Destructive — https://policylayer.com/tools/com-getmunin-munin/cms-delete-collection.md
- `cms_delete_entry` — Destructive — https://policylayer.com/tools/com-getmunin-munin/cms-delete-entry.md
- `connectors_delete_connection` — Destructive — https://policylayer.com/tools/com-getmunin-munin/connectors-delete-connection.md
- `conv_delete_attachment` — Destructive — https://policylayer.com/tools/com-getmunin-munin/conv-delete-attachment.md
- `conv_rotate_widget_key` — Destructive — https://policylayer.com/tools/com-getmunin-munin/conv-rotate-widget-key.md
- `crm_delete_segment` — Destructive — https://policylayer.com/tools/com-getmunin-munin/crm-delete-segment.md
- `kb_delete_document` — Destructive — https://policylayer.com/tools/com-getmunin-munin/kb-delete-document.md
- `kb_dismiss_curation_candidate` — Destructive — https://policylayer.com/tools/com-getmunin-munin/kb-dismiss-curation-candidate.md
- `outreach_cancel_scheduled_send` — Destructive — https://policylayer.com/tools/com-getmunin-munin/outreach-cancel-scheduled-send.md
- `slack_unlink_user` — Destructive — https://policylayer.com/tools/com-getmunin-munin/slack-unlink-user.md
- `webhooks_delete` — Destructive — https://policylayer.com/tools/com-getmunin-munin/webhooks-delete.md
- `conv_request_callback` — Execute — https://policylayer.com/tools/com-getmunin-munin/conv-request-callback.md
- `conv_retry_delivery` — Execute — https://policylayer.com/tools/com-getmunin-munin/conv-retry-delivery.md
- `conv_send_email_channel_test` — Execute — https://policylayer.com/tools/com-getmunin-munin/conv-send-email-channel-test.md
- `conv_send_sms_channel_test` — Execute — https://policylayer.com/tools/com-getmunin-munin/conv-send-sms-channel-test.md
- `conv_test_email_channel` — Execute — https://policylayer.com/tools/com-getmunin-munin/conv-test-email-channel.md
- `conv_test_voice_sms_channel` — Execute — https://policylayer.com/tools/com-getmunin-munin/conv-test-voice-sms-channel.md
- `outreach_approve_proposal` — Execute — https://policylayer.com/tools/com-getmunin-munin/outreach-approve-proposal.md
- `seo_submit_urls` — Execute — https://policylayer.com/tools/com-getmunin-munin/seo-submit-urls.md
- `cancel_subscription` — Financial — https://policylayer.com/tools/com-getmunin-munin/cancel-subscription.md
- `outreach_withdraw_proposal` — Financial — https://policylayer.com/tools/com-getmunin-munin/outreach-withdraw-proposal.md
- `analytics_export_config` — Read — https://policylayer.com/tools/com-getmunin-munin/analytics-export-config.md
- `analytics_export_events` — Read — https://policylayer.com/tools/com-getmunin-munin/analytics-export-events.md
- `analytics_get_contact_journey` — Read — https://policylayer.com/tools/com-getmunin-munin/analytics-get-contact-journey.md
- `analytics_get_funnel` — Read — https://policylayer.com/tools/com-getmunin-munin/analytics-get-funnel.md
- …and 211 more: https://policylayer.com/tools/com-getmunin-munin.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-getmunin-munin · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-getmunin-munin