# request_hitl

Surface a question to the human-in-the-loop queue. ALWAYS use this to ask the human a question — never just ask in chat, which is invisible to the dashboard and to an unattended/autonomous run. IMPORTANT: when the project's HITL auto-answer mode is on (1=safe, 2=aggressive) and the question is not destructive / not require_human, this tool RESOLVES IMMEDIATELY and returns the chosen answer inline in the response (it does NOT block) — so calling it is cheap and is the right move even when you expect a quick yes/no. The active mode is reported in the start_session orientation as hitl_auto_answer_mode. urgency='blocking' means this session pauses until answered (poll get_hitl_request). urgency='normal'/'high' lands in the dashboard but doesn't block. assigned_to routes to a specific human_id (null = broadcast). kind='correction' files a non-blocking mid-run correction: never auto-answered, never blocks — an unattended executor picks it up at the next sprint-item boundary, applies it, and continues. Pass options (answer choices, rendered as buttons) and recommended (an option string or 0-based index) to flag the safe default — the dashboard highlights it and Enter submits it, and an auto-answer picks it. Set require_human=true for genuinely irreversible/destructive actions (token rotation, data migrations, rollbacks) so auto-answer can never approve it — only an explicit human reply unblocks it. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian's service; self-hosted deployments keep them in the configured local SQLite/Postgres database. This data is visible in the dashboard/API and later project context or handoffs. Delete individual tasks, notes, or decisions where supported, or delete the project/account using the documented controls. Do not include secrets.

Agent View of the PolicyLayer registry record for `request_hitl`. HTML page: https://policylayer.com/tools/io-github-ajc3xc-meridian/request-hitl

## Facts

- Tool: `request_hitl`
- Server: Meridian (`@meridianmcp/mcp`) — https://policylayer.com/tools/io-github-ajc3xc-meridian.md
- Install: `npx -y @meridianmcp/mcp`
- Homepage: https://github.com/meridianmcp/Meridian
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 11 (1 required)
- Recommended policy verdict: Hidden

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `kind` | string | no | question (default, auto-answerable) or correction (non-blocking mid-run human correction). |
| `context` | string | no |  |
| `options` | array | no | Answer choices rendered as selectable buttons in the dashboard. |
| `urgency` | string | no |  |
| `question` | string | yes |  |
| `project_id` | string | no |  |
| `session_id` | string | no |  |
| `assigned_to` | string | no |  |
| `recommended` | object | no | The safe-default option — an option string or a 0-based index into options. Highlighted in the dashboard; Enter submits it; auto-answer prefers it. |
| `project_name` | string | no | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
| `require_human` | boolean | no | When true, the HITL can never be auto-answered — only an explicit human response unblocks it. Reserve for irreversible/destructive actions. |

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_hitl",
    "arguments": {
      "question": "<question>"
    }
  }
}
```

## Why request_hitl is rated Critical

An AI agent that decides to call request_hitl doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Meridian is gone. There is no undo for destructive operations.

Risk signals: High parameter count (11 properties)

## Use case

AI agents call request_hitl to permanently remove resources in Meridian, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "request_hitl"
  ]
}
```

## Other tools on Meridian (174)

- `archive_decision` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/archive-decision.md
- `batch_mutate` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/batch-mutate.md
- `claim_sprint_item` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/claim-sprint-item.md
- `clear_capability_profile` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/clear-capability-profile.md
- `clone_profile_layer` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/clone-profile-layer.md
- `delete_custom_hook` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/delete-custom-hook.md
- `delete_note` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/delete-note.md
- `delete_sprint_item_pointer` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/delete-sprint-item-pointer.md
- `fan_out_sprint_items` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/fan-out-sprint-items.md
- `purge_ai_log` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/purge-ai-log.md
- `record_handoff_correction` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/record-handoff-correction.md
- `release_docx_region_claims` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/release-docx-region-claims.md
- `reset_plugin_override` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/reset-plugin-override.md
- `reset_profile_layer` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/reset-profile-layer.md
- `complete_wave_gate` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/complete-wave-gate.md
- `execute_batch` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/execute-batch.md
- `prospect_symbol` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/prospect-symbol.md
- `run_verification` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/run-verification.md
- `start_session` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/start-session.md
- `analyze_model_efficiency` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/analyze-model-efficiency.md
- `analyze_sprint` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/analyze-sprint.md
- `batch_read` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/batch-read.md
- `find_outputs_by_source` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-outputs-by-source.md
- `find_similar_equation` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-similar-equation.md
- `find_similar_figure` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-similar-figure.md
- `find_similar_table` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-similar-table.md
- `find_symbol_usages` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-symbol-usages.md
- `get_agent_instructions` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/get-agent-instructions.md
- `get_blog_posts` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/get-blog-posts.md
- `get_capability_manifest` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/get-capability-manifest.md
- …and 144 more: https://policylayer.com/tools/io-github-ajc3xc-meridian.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=io-github-ajc3xc-meridian · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-ajc3xc-meridian