This simple Model Context Protocol (MCP) client demonstrates the use of MCP server tools by LangChain ReAct Agent.

It leverages a utility function convertMcpToLangchainTools() from @h1deya/langchain-mcp-tools.
This function handles parallel initialization of specified multiple MCP servers and converts their available tools into an array of LangChain-compatible tools (StructuredTool[]). It also performs LLM provider-specific schema transformations to prevent schema compatibility issues

Google GenAI's gemini-2.5-flash is used as the LLM. For convenience, code for OpenAI's and Anthropic's LLMs are also included and commented out.

A bit more realistic (conversational) MCP Client is available here

A python equivalent of this app is available here

• Node.js 18+
• npm 8+ (npx) to run Node.js-based MCP servers
• [optional] uv (uvx) installed to run Python-based MCP servers
• LLM API keys from OpenAI, Anthropic, and/or Google GenAI as needed

1. Install dependencies:

   npm install

2. Setup API key:

   cp .env.template .env

   • Update .env as needed.
   • .gitignore is configured to ignore .env to prevent accidental commits of the credentials.

3. Run the app:

   npm start

A simple example of showing how to implement an OAuth client provider and use it with the langchain-mcp-tools library can be found in src/streamable-http-auth-test-client.ts.

For testing purposes, a sample MCP server with OAuth authentication support that works with the above client is provided in src/streamable-http-auth-test-server.ts.

You can run the server with npm run test:streamable:server and the client with npm run test:streamable:client.