cfr-compliance-mcp
A production-quality MCP server that exposes the official eCFR API as structured tools for AI-driven contract compliance, enabling retrieval of relevant Code of Federal Regulations by clauses extracted from contracts.
README
cfr-compliance-mcp
A production-quality MCP (Model Context Protocol) server exposing the official eCFR (Electronic Code of Federal Regulations) API as structured tools, built for an AI-driven contract compliance pipeline.
Status: in active development. The MCP server's foundation, client, cache, and parsing layers are complete. Validation models, the 8 MCP tools, and the server entrypoint are still being built. See
HANDOFF/PROJECT_HANDOFF.mdfor the full current status.
What this is
This package is the MCP server component of a larger pipeline:
Contract (PDF/DOCX) → Clause Extraction → Agno Team/Agents → this MCP Server
→ Official eCFR REST API → Relevant CFR Retrieval → Compliance Reasoning
→ Clause-wise Compliance Report
It has no dependency on any third-party MCP server — it talks directly to the official, public, unauthenticated eCFR REST API (https://www.ecfr.gov). See HANDOFF/PROJECT_HANDOFF.md Section 9 and the research addendum for why.
Requirements
- Python 3.12
- uv for dependency management
Setup
git clone <this repo>
cd cfr-compliance-mcp
uv sync
cp .env.example .env # adjust settings if needed; defaults work out of the box
Running (once server.py exists)
uv run cfr-compliance-mcp
Project layout
src/cfr_compliance_mcp/
├── config.py, logging_config.py, exceptions.py, constants.py # foundation
├── clients/ # generic HTTP transport + eCFR-specific API client
├── cache/ # backend-agnostic caching (in-memory today, Redis-ready)
├── parsing/ # raw eCFR XML -> clean text + citation metadata
├── models/ # (pending) Pydantic request/response validation
├── tools/ # (pending) the 8 MCP tools
└── server.py # (pending) FastMCP entrypoint
Full architectural rationale is in HANDOFF/ARCHITECTURE.md. Chronological build history is in HANDOFF/PROJECT_PROGRESS.md. A single authoritative current-state reference (what's built, why, what's next) is HANDOFF/PROJECT_HANDOFF.md — read that first if you're picking this project up.
Testing
uv run pytest
(Test suite is not yet built — see HANDOFF/PROJECT_HANDOFF.md for status.)
Development conventions
- Full type hints,
strictmypy. rufffor linting (uv run ruff check .).- All configuration via
.env/config.Settings— neveros.environdirectly. - All logging via
logging_config.get_logger(__name__)— logs go to stderr only (the MCPstdiotransport uses stdout for the protocol itself; never write there). - See
HANDOFF/PROJECT_HANDOFF.mdSection 17 for the full conventions list.
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。