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
Basic information
Example of a MCP implementation using TypeScript and OAuth.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Comments