Is this a production-ready server?
No. This demo is NOT a production-ready, plug-and-play server. It omits specific business logic and assumes a pre-existing OAuth Authorization Server.
@portal-labs-infrastructure
基本信息
Example of a MCP implementation using TypeScript and OAuth.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This repository provides a stripped-down, illustrative implementation of a Model Context Protocol (MCP) server that showcases architectural patterns, security considerations (OAuth 2.0), and development practices (TypeScript, Firestore, Zod). It is intended as a learning resource for developers building secure, multi-tenant MCP resource servers.
Clone the repository, install dependencies with npm install, copy .env.example to .env and configure the required values (Firestore project ID, OAuth issuer URL, base URL). Run in development mode with npm run dev or build and start with npm run build then npm start. The server typically starts on http://localhost:8080.
workspace_id.No. This demo is NOT a production-ready, plug-and-play server. It omits specific business logic and assumes a pre-existing OAuth Authorization Server.
Node.js v18.x or later, npm or yarn, a Google Cloud Project with Firestore enabled (or Firestore Emulator), and an existing OAuth 2.0 Authorization Server.
The server acts as the MCP Resource Server and expects OAuth 2.0 Bearer tokens issued by a separate Authorization Server. It validates tokens using the MCP SDK middleware and the `withWorkspaceAccess` Higher-Order Component.
The client sends HTTPS requests with a Bearer token to this Node.js/TypeScript server. The MCP SDK middleware extracts the token, the `withWorkspaceAccess` HOC validates workspace access using the userId, and then the tool handler interacts with Firestore.
Install and configure the Google Cloud SDK, start the emulator with `gcloud emulators firestore start --host-port=localhost:8081`, and run the server. The server connects to the emulator automatically based on environment variables or gcloud configuration.


Zyte MCP is a remote MCP server available at https://mcp.zyte.com/v1/mcp/, that lets an agent use Zyte on your behalf: to get web pages, to extract data from them, to search the web, and to work with your Scrapy Cloud pr

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark
Open-source MCP server for Google Play developer workflows. Runs locally with your own credentials.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
评论