mcp-te-server

mcp-te-server

MCP proxy server for ThinkingEngine with automatic browser-based authentication. Automates the login → token extraction → proxy flow so you never need to manually copy tokens.

Category
Visit Server

README

@zhoujinandrew/mcp-te-server

MCP proxy server for ThinkingEngine with automatic browser-based authentication.

Automates the login → token extraction → proxy flow so you never need to manually copy tokens.

How It Works

┌─────────────┐    stdio     ┌──────────────────┐     SSE      ┌──────────────┐
│ Claude Code  │ ←─────────→ │  mcp-te-server   │ ←──────────→ │ TE MCP Server│
│  (client)    │             │  (local proxy)    │  mcpToken    │  (remote)    │
└─────────────┘             └──────────────────┘              └──────────────┘
                                     │
                                     │ Auto-authentication
                                     ▼
                             ┌──────────────────┐
                             │  Default Browser  │
                             │  (AppleScript)    │──→ Login → Extract token
                             └──────────────────┘
  1. On startup, checks for cached tokens
  2. If no valid token, opens your default browser for login
  3. Extracts the bearer token from localStorage via AppleScript (macOS)
  4. Exchanges it for an mcpToken via the ThinkingEngine API
  5. Proxies all MCP requests transparently
  6. Auto-reconnects and re-authenticates on token expiry or connection errors

Prerequisites

  • Node.js >= 18
  • macOS with Chrome, Brave, Edge, Arc, or Safari
  • Access to a ThinkingEngine system instance

Installation

Via npx (recommended)

No installation needed — just configure your MCP client directly.

From source

git clone https://github.com/zjandrew/mcp-te-server.git
cd mcp-te-server
npm install
npm run build

Configuration

Claude Code

Add to ~/.claude.json:

{
  "mcpServers": {
    "ThinkingEngine": {
      "command": "npx",
      "args": ["-y", "@zhoujinandrew/mcp-te-server@latest"],
      "env": {
        "TE_BASE_URL": "https://your-te-server.example.com",
        "TE_SSE_URL": "https://your-te-server.example.com:18988/mcp/sse"
      }
    }
  }
}

OpenClaw / Other MCP Clients

Same configuration format — use npx with @zhoujinandrew/mcp-te-server@latest.

Environment Variables

Variable Required Description
TE_BASE_URL Yes Base URL of your ThinkingEngine system (e.g., https://your-te-server.example.com)
TE_SSE_URL No Override the MCP SSE endpoint URL. Default: {TE_BASE_URL hostname}:18988/mcp/sse

From source (alternative)

{
  "mcpServers": {
    "ThinkingEngine": {
      "command": "node",
      "args": ["/path/to/mcp-te-server/dist/index.js"],
      "env": {
        "TE_BASE_URL": "https://your-te-server.example.com",
        "TE_SSE_URL": "https://your-te-server.example.com:18988/mcp/sse"
      }
    }
  }
}

Usage

  1. Configure your MCP client as shown above
  2. Start (or restart) the client
  3. On first launch, your default browser opens — log in to ThinkingEngine
  4. Token is extracted automatically after login
  5. Subsequent launches use cached tokens (no login until expiry)

Token Management

Tokens are cached at ~/.mcp-te-server/token.json.

To clear cached tokens:

rm ~/.mcp-te-server/token.json

Development

npm install
npm run build      # Build
npm run dev        # Watch mode
npm start          # Run directly

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured