Skip to main content

MCP server for Vaquill legal research API - search 13M+ Indian court judgments via AI

Project description

vaquill-mcp

MCP server for Vaquill legal research API. Search 13M+ Indian court judgments, ask AI-powered legal questions, resolve citations, and traverse citation networks — all from your AI tools.

Quick Start

Prerequisites

Get your API key from vaquill.ai/dashboard/api-keys

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "vaquill": {
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

Claude Code

claude mcp add vaquill -- uvx vaquill-mcp
# Then set the env var in your shell: export VAQUILL_API_KEY=vq_key_...

Or add to .claude/settings.json:

{
  "mcpServers": {
    "vaquill": {
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

Cursor

Add to Cursor Settings > MCP Servers:

{
  "mcpServers": {
    "vaquill": {
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

VS Code (Copilot)

Add to .vscode/settings.json:

{
  "mcp": {
    "servers": {
      "vaquill": {
        "command": "uvx",
        "args": ["vaquill-mcp"],
        "env": {
          "VAQUILL_API_KEY": "vq_key_your_key_here"
        }
      }
    }
  }
}

Windsurf

Add to ~/.windsurf/settings.json:

{
  "mcpServers": {
    "vaquill": {
      "command": "uvx",
      "args": ["vaquill-mcp"],
      "env": {
        "VAQUILL_API_KEY": "vq_key_your_key_here"
      }
    }
  }
}

Available Tools

Tool Description Credits
ask_legal_question AI-powered legal Q&A grounded in court judgments. Standard (fast) or deep (thorough) modes. 0.5 - 2.0
search_legal_cases Boolean keyword search with AND/OR/NOT operators. Filter by court, year, country. 1.0
quick_search Fast compact search returning top 3-5 results with essentials only. 0.1
resolve_citation Resolve any citation format (SCC, AIR, SCR, MANU) to canonical case record. 0.1
search_cases_by_citation Search cases by citation text or case name with filters. 0.1
lookup_case Full case details with citation treatment stats (followed, overruled, etc.). 0.1
get_citation_network Traverse citation graph: which cases cite/are cited by a case. 1-3 hops. 0.2
get_pricing Get current API credit pricing (no auth required). Free

Environment Variables

Variable Required Default Description
VAQUILL_API_KEY Yes - API key (vq_key_...) from dashboard
VAQUILL_BASE_URL No https://api.vaquill.ai API base URL
VAQUILL_TIMEOUT No 120 Request timeout in seconds

Example Usage

Once configured, you can ask your AI assistant things like:

  • "Search for Supreme Court cases on Section 302 IPC"
  • "What is the legal test for negligence in Indian tort law?"
  • "Resolve the citation AIR 1978 SC 597"
  • "Look up the case Maneka Gandhi vs Union of India and show treatment stats"
  • "Show the citation network around ADM Jabalpur vs Shivkant Shukla"
  • "Compare murder and culpable homicide under IPC" (uses deep mode)

Development

# Clone and install
git clone https://github.com/vaquill/vaquill-mcp.git
cd vaquill-mcp
uv sync --all-extras

# Run locally
VAQUILL_API_KEY=vq_key_... uv run vaquill-mcp

# Run tests
uv run pytest

# Test with FastMCP inspector
uv run fastmcp dev src/vaquill_mcp/server.py

How It Works

This package is a thin MCP wrapper around the Vaquill Developer API. At startup, it fetches the OpenAPI spec from the live API and auto-generates MCP tools using FastMCP. Tool names and descriptions are customized for optimal LLM performance.

Because the spec is fetched at startup (not bundled), tools automatically reflect any API changes without a package update.

Credits & Pricing

API calls consume credits. Check current pricing at vaquill.ai/pricing or use the get_pricing tool.

1 credit = $0.10 USD = 10 INR

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vaquill_mcp-0.1.0.tar.gz (93.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vaquill_mcp-0.1.0-py3-none-any.whl (11.0 kB view details)

Uploaded Python 3

File details

Details for the file vaquill_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: vaquill_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 93.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.2

File hashes

Hashes for vaquill_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 de8999c1d9fc0eb89672be7f26dac667707e6862f3a13c262631f7127cd17e44
MD5 4fb695812377a21d5aaaa80ff110b42d
BLAKE2b-256 ff2ed52d7adcea247359a0d6d5e03f69be9152f2c2e06e55eaea0d80a9704b01

See more details on using hashes here.

File details

Details for the file vaquill_mcp-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for vaquill_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 dabe03b18724cfb114ef173af2252c19caeb15aaa5acd73a0b392c4b6e92aed1
MD5 60cd47111e60124788bd117a8fe7247e
BLAKE2b-256 a7bf07a0ca89d221929357e9ecb1b0a06a034340da038d57c809085433d5fa64

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page