pAIchart
AI-native service orchestration platform. Discover MCP services by capability, chain multi-service-workflows at runtime, and authenticate per-user via JWKS/External OAuth. A single pAIchart MCP server needs only 10 tools to access hundreds of registered local or network MCP servers solving the context issue individual MCP server tools impose. Enabled by pAIchart's service_call innovation.
README
pAIchart — MCP Hub Platform
AI Service Orchestration with Per-User Authentication
pAIchart is a MCP service mesh where AI discovers MCP servers, composes & orchestrates multi-service workflows. Users can self-register services and connect agents or AI clients to any MCP service through a single Hub with trust-level authentication, per-user OAuth passthrough, and multi-service workflows.
What pAIchart Does
- Free Service Registration — Comprehensive guides available via "/prompt list" or as MCP resources
- Service Discovery — AI agents find services by capability, not by name
- Multi-Service Workflows — Chain services sequentially, in parallel, or conditionally with variable passing
- Per-User Authentication — Each user's operations run as themselves via External OAuth (validated with Snowflake)
- Trust Level System — 6-tier security model controls token forwarding (INTERNAL → TRUSTED → OWNER → TEAM_MEMBER → SCOPED → ANONYMOUS)
- JWKS Token Validation — RS256 asymmetric cryptography, public key verification, 95/100 security score
How It Works
User (Claude Desktop / ChatGPT) → Authenticates to pAIchart Hub → Discovers services by capability → Hub determines trust level, forwards JWT if authorized → External service validates JWT via JWKS → Operations execute as the authenticated user
Live Services
| Service | Capability | Per-User Auth |
|---|---|---|
| Snowflake | Data warehouse queries | ✅ External OAuth |
| EIA | U.S. energy data analytics | Service account |
| Weather | Real-time weather data | Service account |
| EODHD | Financial market data | Service account |
| Browser Automation | Web scraping, screenshots, PDFs | Service account |
| Notifications | Email, Slack, webhooks | Service account |
Register Your MCP Service
Any MCP service can register with the Hub in one command:
registry(action: "register", { name: "my-service", description: "What your service does", endpoint: "https://my-service.com/mcp", category: "data-services" })
Services that support External OAuth (like Snowflake, Databricks) get per-user authentication automatically.
Links
- Platform: paichart.app
- MCP Endpoint:
https://paichart.app/mcp - JWKS:
https://paichart.app/api/auth/jwks - Documentation: Provided as a resource (or use /prompt list) in AI Clent
Keywords
mcp mcp-hub mcp-server mcp-orchestration model-context-protocol ai-services service-discovery
external-oauth jwks per-user-authentication workflow-orchestration claude-desktop chatgpt snowflake
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。