Tollbooth Authority — North America
MCP server for the DPYC ecosystem that certifies North American operators using the Lightning network, enabling regional certification and audit trails with low latency.
README
Tollbooth Authority — North America
<p align="center"> <img src="https://raw.githubusercontent.com/lonniev/tollbooth-dpyc/main/docs/tollbooth-hero.png" alt="Milo drives the Lightning Turnpike — Don't Pester Your Customer" width="800"> </p>
The North American on-ramp to the Lightning turnpike.
Identity:
npub1zummm5awn88kw2hz6deeyjprpw0fzuv9rvzrxf3vu453yyqzvdss49xd2tParent: DPYC Prime Authority (npub1l94pd…mq8pf) Peer Authorities under Prime:tollbooth-authority(Lonnie-Authority) Sub-Authority:tollbooth-authority-newenglandService:https://tollbooth-authority-northamerica.fastmcp.app/mcpNeon region:aws-us-west-2(Oregon)
A peer-level Authority under DPYC Prime, serving North American operators. Operators may choose this Authority to keep certification latency and audit trails in-region.
The metaphors in this project are drawn with admiration from The Phantom Tollbooth by Norton Juster, illustrated by Jules Feiffer (1961). We just built the payment infrastructure.
Architecture
This repository is a thin consumer of the tollbooth-dpyc wheel's tollbooth.authority extension (wheel ≥ 0.22.1). The entire deployable surface lives in src/tollbooth_authority/server.py (~90 lines): a FastMCP instance, an OperatorRuntime, and two register_*_tools(mcp, runtime) calls. Onboarding state machine, Schnorr signer, replay tracker, Neon tenant provisioning, and the 16 Authority @tool definitions are wheel-resident and shared with every other Authority MCP in the ecosystem.
For the protocol semantics, certificate format (Schnorr/NIP-33 kind 30079), fee cascade, registry enforcement, and tool catalog, see the canonical tollbooth-authority README — this repo is identical in behavior, distinct only in identity, region, and Neon tenant.
Deploy
Two secrets required by Horizon:
| Env var | Value |
|---|---|
TOLLBOOTH_NOSTR_OPERATOR_NSEC |
This Authority's nsec |
NEON_DATABASE_URL |
A pooled Neon connection string in aws-us-west-2 |
Everything else — BTCPay credentials for the cashier, operator credential templates — arrives via Secure Courier post-deploy (see docs/how-to-add-authority.md in the community repo).
The DPYC Ecosystem
DPYC is a federation of independent, SSE-based MCP servers sharing one Lightning-funded economy. This Authority certifies operators across the network. Sibling repos:
Core & governance
tollbooth-dpyc— shared Python SDK (crypto, vault, auth, pricing, audit)dpyc-community— governance registry (members, rulebook, CI validation)dpyc-oracle— free community concierge (membership, onboarding, tax-rate questions)tollbooth-authority— canonical certification Authoritytollbooth-sample— reference Operator implementationtollbooth-pricing-studio— native pricing editor (Swift/iOS)
Operators (paid MCP services)
cypher-mcp— monetized graph answers via named Cypher templates over Neo4j/AuraDB (certified under this Authority)schwab-mcp— Charles Schwab brokerage datathebrain-mcp— TheBrain knowledge-graph accessexcalibur-mcp— X/Twitter postingtaxsort-mcp— tax classification + Cloudflare Pages UIoptionality-mcp— options analytics
Utilities & advocates
tollbooth-oauth2-collector— shared OAuth2 callback collectortollbooth-shortlinks— URL shortener
License
Apache-2.0
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。