# ask_legal

Request fixed legacy Themis source/citation records and attach a proposed Laws & Regulations agent/source/synthesis plan whose routes are planned_not_run. Check the law uses fixed legacy provider-record retrieval, but returned records do not prove exact citation identity, relevance, authority, or corpus coverage. Generated research requires authentication, exact THEMIS_NEUTRAL_SCHEMA_VERSION=themis_neutral_research/v1, the operator gate, a verified authenticated corpus manifest, and an atomic spend reservation. The manifest verifier is not available yet, so generated mode remains disabled. Provider assertions/gaps are enum codes linked to evidence whose quote-fidelity state is provider-reported and rendered with fixed server text; any legacy verdict or answer prose is withheld. Returns legal_evidence_graph/v1. Automated research only, not legal advice. Requires legal:run.

Agent View of the PolicyLayer registry record for `ask_legal`. HTML page: https://policylayer.com/tools/com-meta-council-decision-intelligence/ask-legal

## Facts

- Tool: `ask_legal`
- Server: Meta Council (`https://meta-council.com/mcp`) — https://policylayer.com/tools/com-meta-council-decision-intelligence.md
- Homepage: https://github.com/daliu/meta-council
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 10 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `context` | string | no | Optional factual context; treated as unverified input. The normalized question plus context must fit 2,000 characters total. |
| `domains` | array | no | Optional domain hints such as OSHA, building_codes, or sports_regulation. |
| `quality` | string | no | Policy for proposed, unexecuted model-quality and reasoning-effort routes. |
| `question` | string | yes | Laws or regulations research question (no credentials or secrets). After normalized context is appended, the combined provider question must fit 2,000 character |
| `jurisdiction` | string | no | Request hint forwarded to the legacy provider; it does not prove corpus coverage. |
| `max_sections` | integer | no | Optional maximum number of provider-returned source/citation records. |
| `research_mode` | string | no | Fixed legacy provider-record retrieval or an explicit request for fail-closed, neutral Themis generation. |
| `model_overrides` | object | no | Optional model-id overrides for proposed, unexecuted agent routes. |
| `requested_agents` | array | no | Up to seven catalog agent additions for the proposed plan; one of the eight total agent slots is reserved for its baseline agent. |
| `reasoning_effort_overrides` | object | no | Optional effort overrides for proposed, unexecuted agent routes. |

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

## Why ask_legal is rated Low

Even though ask_legal only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signals: High parameter count (10 properties)

## Use case

AI agents call ask_legal to retrieve information from Meta Council without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "ask_legal": {}
  }
}
```

## Other tools on Meta Council (279)

- `account_export` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/account-export.md
- `cancel_booking` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/cancel-booking.md
- `decide_approval` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/decide-approval.md
- `delete_accounting_run` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/delete-accounting-run.md
- `delete_monitor` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/delete-monitor.md
- `delete_saved_view` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/delete-saved-view.md
- `delete_workflow_template` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/delete-workflow-template.md
- `preview_scheduling_action` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/preview-scheduling-action.md
- `project_unlink_feature` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/project-unlink-feature.md
- `reconcile_attention_notification_delivery` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/reconcile-attention-notification-delivery.md
- `revoke_portfolio_report_share` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/revoke-portfolio-report-share.md
- `ticket_dependency_remove` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/ticket-dependency-remove.md
- `void_invoice` — Destructive — https://policylayer.com/tools/com-meta-council-decision-intelligence/void-invoice.md
- `dismiss_ticket_integration_effect` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/dismiss-ticket-integration-effect.md
- `execute_saved_view` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/execute-saved-view.md
- `preview_accounting_ticket_sync` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/preview-accounting-ticket-sync.md
- `project_link_feature` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/project-link-feature.md
- `retry_workflow` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/retry-workflow.md
- `review_external_workflow` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/review-external-workflow.md
- `run_comparison` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/run-comparison.md
- `run_council` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/run-council.md
- `run_workflow` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/run-workflow.md
- `start_external_workflow` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/start-external-workflow.md
- `ticket_scenario_revise` — Execute — https://policylayer.com/tools/com-meta-council-decision-intelligence/ticket-scenario-revise.md
- `add_invoice_line_item` — Financial — https://policylayer.com/tools/com-meta-council-decision-intelligence/add-invoice-line-item.md
- `mark_invoice_paid` — Financial — https://policylayer.com/tools/com-meta-council-decision-intelligence/mark-invoice-paid.md
- `advance_workflow` — Read — https://policylayer.com/tools/com-meta-council-decision-intelligence/advance-workflow.md
- `browse_ticket_integration_import` — Read — https://policylayer.com/tools/com-meta-council-decision-intelligence/browse-ticket-integration-import.md
- `campaign_pipeline_stats` — Read — https://policylayer.com/tools/com-meta-council-decision-intelligence/campaign-pipeline-stats.md
- `check_ticket_provider_fields` — Read — https://policylayer.com/tools/com-meta-council-decision-intelligence/check-ticket-provider-fields.md
- …and 249 more: https://policylayer.com/tools/com-meta-council-decision-intelligence.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-meta-council-decision-intelligence · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-meta-council-decision-intelligence