Pro Se Engine

Pro Se Engine

Pro Se Engine is an MCP server that provides 39 legal research tools across 6 government APIs, enabling AI agents to access case law, SEC filings, federal legislation, regulations, government contracts, and document processing workflows.

Category
访问服务器

README

Pro Se Engine

A powerful MCP (Model Context Protocol) server providing 39 legal research tools across 6 government APIs — designed for use with Pickaxe AI agents.

Built by ProjectCues.


🏛️ What It Does

Pro Se Engine gives AI agents access to:

API Tools Auth
CourtListener 16 API token
SEC EDGAR 4 User-Agent header
Federal Register 3 None
Congress.gov 4 API key (free)
Regulations.gov 3 API key (free)
USAspending.gov 3 None
Document Tools 4
Legal Workflows 2 (13 templates)

Tool Categories

  • Case Law — Search opinions, read full text, verify citations
  • SEC Filings — Full-text search, company filings, XBRL financials
  • Federal Legislation — Bills, bill text, Congress members
  • Regulations — Federal Register rules, regulatory dockets, public comments
  • Government Contracts — USAspending awards, contractor profiles
  • Documents — Generate DOCX, extract text from PDF/DOCX, tracked changes editing
  • Workflows — 13 structured legal analysis templates (M&A due diligence, lease abstracts, litigation assessment, etc.)

🚀 Quick Start

1. Install dependencies

npm install

2. Configure environment

cp .env.example .env
# Edit .env with your API keys

3. Run in development

npm run dev

4. Build for production

npm run build
node dist/index.js

The server starts on http://localhost:3001/mcp.


🔑 API Keys

Variable Required How to Get
COURTLISTENER_API_TOKEN Yes courtlistener.com/help/api
CONGRESS_API_KEY Yes api.data.gov/signup (free)
REGULATIONS_API_KEY Yes Same key from api.data.gov
SEC_USER_AGENT Yes Any string: "YourApp your@email.com"
MCP_AUTH_TOKEN Optional Set to require bearer auth on the MCP endpoint

SEC EDGAR, Federal Register, and USAspending.gov require no API keys.


🔗 Connecting to Pickaxe

  1. Deploy this server to a public URL (e.g., Hostinger VPS)
  2. In Pickaxe Agent Builder, add an MCP server
  3. Set the endpoint URL to https://your-domain.com/mcp
  4. If MCP_AUTH_TOKEN is set, configure the bearer token in Pickaxe

📋 13 Legal Workflow Templates

ID Template
cp-checklist Conditions Precedent Checklist
credit-agreement-summary Credit Agreement Summary (21 sections)
shareholder-agreement-summary Shareholder Agreement Summary (15 sections)
ma-due-diligence M&A Due Diligence Checklist (10 categories)
commercial-lease-abstract Commercial Lease Abstract (18 points)
employment-agreement-review Employment Agreement Review (15 sections)
ip-assignment-review IP Assignment/License Review (12 sections)
litigation-case-assessment Litigation Case Assessment (12 sections)
regulatory-compliance-review Regulatory Compliance Review (10 sections)
power-of-attorney-review Power of Attorney Review (11 sections)
corporate-bylaws-review Corporate Bylaws Review (12 sections)
settlement-agreement-review Settlement Agreement Review (14 sections)
partnership-agreement-review Partnership Agreement Review (15 sections)

🏗️ Architecture

  • Runtime: Node.js 20+
  • Language: TypeScript (strict mode)
  • Transport: Streamable HTTP (stateless — each request is independent)
  • Framework: Express + @modelcontextprotocol/sdk

📄 License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选