Connect Your AI to Legal Data Worldwide

Give any MCP-compatible AI access to 18M+ legal documents across 110+ countries. Just paste the URL — you'll be asked to sign in, and you're connected.

Just paste this URL Recommended

Works with Claude.ai, Claude Code, Claude Desktop, Cursor, and any MCP-compatible client. You'll be asked to sign in with GitHub or Google — no API key needed.

CLI Install (for agents)

Claude Code Zero installs

Built into Claude Code — agents can run this directly:

claude mcp add --transport http legal-data-hunter https://legaldatahunter.com/mcp

All other clients Requires Node.js

Auto-detects Cursor, VS Code, Lawvable, Windsurf, JetBrains, and Copilot — configures them all at once:

npx legal-data-hunter setup --yes

Drop --yes for interactive mode. Or use npx add-mcp https://legaldatahunter.com/mcp

Setup Guides

Go to Settings → Connectors → Add custom connector
Name: Legal Data Hunter
Remote MCP server URL: paste the URL above
Click Add — you'll be redirected to sign in with GitHub or Google
Once authorized, Claude can search legal documents directly

Add to your project's .mcp.json:

{
  "mcpServers": {
    "legal-data-hunter": {
      "type": "streamable-http",
      "url": "MCP_URL_PLACEHOLDER"
    }
  }
}

On first use, you'll be prompted to sign in via your browser.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "legal-data-hunter": {
      "type": "streamable-http",
      "url": "MCP_URL_PLACEHOLDER"
    }
  }
}

On first use, you'll be prompted to sign in via your browser.

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "legal-data-hunter": {
      "type": "streamable-http",
      "url": "MCP_URL_PLACEHOLDER"
    }
  }
}

On first use, you'll be prompted to sign in via your browser.

Lawvable is a VS Code fork — add to .vscode/mcp.json in your project:

{
  "mcpServers": {
    "legal-data-hunter": {
      "type": "streamable-http",
      "url": "MCP_URL_PLACEHOLDER"
    }
  }
}

On first use, you'll be prompted to sign in via your browser.

Available Tools

Tool	Description
`search`	Hybrid semantic + keyword search across 18M+ legal documents. Supports filters: country, court_tier, jurisdiction, date range, language.
`get_document`	Retrieve the full text and metadata of any document by source + source_id.
`discover_countries`	List all available countries with document counts.
`discover_sources`	List data sources for a specific country — source IDs, types, court names, tiers, counts.
`get_filters`	Get available filter values (courts, jurisdictions, languages, date ranges) for a source.
`resolve_reference`	Resolve a loose legal citation (e.g. "art. 6 code civil", ECLI, CELEX) to the exact document(s). Supports 55+ countries.
`report_source_issue`	Report problems with a data source: broken URLs, missing data, indexing errors, or data quality issues.

Tool Parameters

search — 11 parameters

Parameter	Type	Default	Description
`query`	string	required	Search query text
`namespace`	string	`case_law`	`case_law`, `legislation`, or `doctrine`
`top_k`	integer	`10`	Number of results (1-100)
`alpha`	float	`0.7`	Semantic weight (1.0 = pure semantic, 0.0 = pure keyword)
`country`	string[]	—	ISO country codes, e.g. `["FR","DE"]`
`court_tier`	integer	—	1 = supreme, 2 = appellate, 3 = first instance
`jurisdiction`	string	—	Jurisdiction name filter
`subdivision`	string	—	Court subdivision filter
`date_start`	string	—	Start date (YYYY-MM-DD)
`date_end`	string	—	End date (YYYY-MM-DD)
`language`	string	—	Language code, e.g. `fr`

get_document — 2 parameters

Parameter	Type	Description
`source`	string	Source identifier, e.g. `FR/Judilibre`
`source_id`	string	Document ID within the source

resolve_reference — 3 parameters

Parameter	Type	Default	Description
`reference`	string	required	The legal citation to resolve, e.g. "art. 6 code civil"
`hint_country`	string	—	ISO country code hint for faster resolution
`hint_type`	string	—	`case_law` or `legislation`

discover_countries — no parameters

Returns all countries with document counts by type.

discover_sources — 1 parameter

Parameter	Type	Description
`country_code`	string	ISO country code, e.g. `FR`

get_filters — 1 parameter

Parameter	Type	Description
`source`	string	Source identifier, e.g. `FR/Judilibre`

report_source_issue — 3 parameters

Parameter	Type	Default	Description
`source`	string	required	Source identifier, e.g. `FR/Judilibre`
`issue_type`	string	required	One of: `unavailable`, `indexing`, `invalid_url`, `data_quality`, `other`
`description`	string	`""`	Additional details about the issue

Recommended Flow

For best results, guide your agent through this discovery pattern:

1. discover_countries()              → find country codes + doc counts
2. discover_sources("FR")             → see what sources exist for France
3. get_filters("FR/Judilibre")        → see available courts, date ranges
4. search("droit à l'oubli", ...)     → targeted search with filters
5. get_document("FR/Judilibre", id)   → read full decision text
6. resolve_reference("art. 6 CEDH")  → resolve a citation to its document

Manual Setup (API Key) Advanced

If your MCP client doesn't support OAuth, you can use an API key instead. Create one on your account page, then add the Authorization header:

{
  "mcpServers": {
    "legal-data-hunter": {
      "type": "streamable-http",
      "url": "MCP_URL_PLACEHOLDER",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

REST API

Not using MCP? You can call the REST API directly:

# Search for case law
curl -X POST BASE_URL_PLACEHOLDER/v1/search \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"q": "droit à l oubli", "namespace": "case_law", "top_k": 5}'

Interactive Swagger Docs API Docs llms.txt