@bitcoinbenji/mcp
MCP server offering 26 Lightning-paid tools for Bitcoin mempool intelligence and sovereign on-prem AI inference, with no third-party APIs and pay-per-call in sats.
README
@bitcoinbenji/mcp
MCP server for Bitcoin Benji API — 26 Lightning-paid tools for Bitcoin mempool intelligence + sovereign on-prem AI inference.
No third-party APIs. No data leakage. Pay-per-call in sats.
What you get
Mempool intelligence (from a real Bitcoin Core full node):
get_fees— fee estimates with trendget_whales— whale/consolidation alertsget_mempool_state— live mempool stateget_mempool_history— 24h rolling snapshotspredict_fees— EMA-based predictionget_recent_blocks— recent blockstx_status— lookup any txidfee_quote— exact fee for a planned tx
AI inference (Qwen3 on dedicated GPU, no third-party APIs):
ai_summarize,ai_sentiment,ai_translate,ai_grammarai_code_review,ai_code_generate,ai_extract,ai_classifyai_rewrite,ai_explain,ai_agent,ai_scrapeai_embed,ai_vision,ai_ocr,ai_transcribe_tableai_longform(~50K-word docs flat-fee),ai_research(multi-step + cited)
Pricing: 2–100 sats per call. See api.bitcoinbenji.com/pricing.
Install
npm install -g @bitcoinbenji/mcp
Use in Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"bitcoinbenji": {
"command": "bitcoinbenji-mcp"
}
}
}
Restart Claude. Ask: "What are current Bitcoin fees?" — Claude will call get_fees, hit a 402 challenge, return a Lightning invoice. Pay it with any wallet, paste the preimage back, and Claude completes the call.
Use in Cursor / Cline / Continue / Windsurf
Same idea — point your MCP-compatible client at the bitcoinbenji-mcp binary.
Skip the manual payment loop — use an API key
Pre-fund a key once, then every call auto-debits in the background:
# Get a key (one-time): visit https://api.bitcoinbenji.com or curl /api/key/create
# Then:
export BITCOIN_BENJI_API_KEY="bb_live_..."
bitcoinbenji-mcp
Or in Claude Desktop config:
{
"mcpServers": {
"bitcoinbenji": {
"command": "bitcoinbenji-mcp",
"env": { "BITCOIN_BENJI_API_KEY": "bb_live_..." }
}
}
}
Why this exists
Most AI inference APIs require a credit card, an account, and a SaaS subscription. This one runs on a sovereign solar-powered AMD Strix Halo box, accepts payment in sats over Lightning, and never leaks your prompts to OpenAI/Anthropic/Google.
Source
github.com/ocbenji/bitcoinbenji-mcp
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。