Vaquill-AI/vaquill-mcp
MCP server for Vaquill legal research API. Covers US federal + 50-state law (USC, CFR, state legislation, CourtListener case law)
README
vaquill-mcp
MCP server for Vaquill legal research API. Covers US federal and 50-state law (USC, CFR, state legislation, CourtListener case law). Ask AI-powered legal questions, search statutes, and ground answers in primary sources, all from your AI tools.
Quick Start
Prerequisites
Sign up at vaquill.ai to get your API key.
Claude.ai (Web)
No installation needed. Add as a remote MCP server in Claude.ai Settings > Integrations:
Option A: Simple URL (API key in path)
https://mcp.vaquill.ai/s/vq_key_your_key_here
Option B: Bearer token (recommended)
URL: https://mcp.vaquill.ai/s/_
Token: vq_key_your_key_here
Available on Claude Pro, Max, Team, and Enterprise plans.
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
Remote (no install):
claude mcp add-json vaquill '{"type":"http","url":"https://mcp.vaquill.ai/s/_","headers":{"Authorization":"Bearer vq_key_your_key_here"}}'
Local (via uvx):
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
General
| Tool | Description | Credits |
|---|---|---|
ask_legal_question |
AI-powered legal Q&A across USC, CFR, 50-state law, and CourtListener case law. Standard (fast) or deep (multi-hop) modes. | 5 - 20 |
get_pricing |
Get current API credit pricing (no auth required). | Free |
US law (USC + CFR)
| Tool | Description | Credits |
|---|---|---|
search_us_statutes |
Semantic search across the United States Code (USC) and Code of Federal Regulations (CFR). Filter by corpusType and titleNumber. |
2 |
get_us_statute_section |
Metadata for a specific USC/CFR section by act_id (citation, title hierarchy, links). |
1 |
get_us_statute_section_text |
Full HTML + plain text of a USC or CFR section. | 3 |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
VAQUILL_API_KEY |
Yes | - | API key (vq_key_...) from vaquill.ai |
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:
- "What does 17 CFR 240.10b-5 say about insider trading?"
- "Find USC sections on equal protection under the Fourteenth Amendment"
- "Summarize FRCP Rule 12(b)(6) and recent SDNY case law applying it" (uses deep mode)
- "What are the federal penalties for wire fraud under 18 USC 1343?"
Development
# Clone and install
git clone https://github.com/Vaquill-AI/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 or use the get_pricing tool.
1 credit = $0.10 USD
Data Attribution
US case law is sourced from CourtListener, maintained by the Free Law Project.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。