MCP Chat with Claude
@jiangyan
About MCP Chat with Claude
A typescript example for web app as the host connecting node mcp server
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Chat with Claude?
MCP Chat with Claude is a full-stack application that demonstrates the integration of the Model Context Protocol (MCP) with Anthropic’s Claude LLM. It provides an interactive chat interface where Claude can discover and use tools from multiple MCP servers. This project is aimed at developers exploring MCP‑enabled agent architectures.
How to use MCP Chat with Claude?
After cloning the repository, install dependencies in both server/ and client/ directories with npm install. Create .env files for the client (with ANTHROPIC_API_KEY, MCP_SERVER_TODOPLAN_URL, MCP_SERVER_PROJECT_URL, PORT) and the server (with MCP_SERVER_TODOPLAN_PORT, MCP_SERVER_PROJECT_PORT). Start the TodoPlan and Project MCP servers using npm run start:todoplan and npm run start:project from the server/ folder. Then start the host app from client/ with npm start and navigate to http://localhost:3000.
Key features of MCP Chat with Claude
- Interactive chat interface with Claude AI
- Two‑panel UI showing conversation and tool execution details
- Dynamic tool discovery from multiple MCP servers
- Support for specialized tools from each server
- Proper handling of Claude’s tool use via MCP
- Standalone MCP client example for programmatic access
Use cases of MCP Chat with Claude
- Query project details using the Project MCP server (e.g., “Tell me about project Earth”)
- Retrieve todo items for specific categories through the TodoPlan MCP server
- Combine insights from multiple servers, such as finding a todo and related projects
- Test and develop new MCP tools with a ready‑made web interface
FAQ from MCP Chat with Claude
What MCP servers are included?
Two servers are provided: the TodoPlan MCP server (tools: get-todo, get-plan) and the Project MCP server (tool: get-project-details).
What are the runtime requirements?
Node.js 17 or higher, npm or yarn, and an Anthropic API key are required.
How do I add a new tool to an MCP server?
Open the relevant server file (e.g., mcp-server-todoplan.ts), add a tool definition following the existing pattern, then rebuild and restart the server.
Why do I get a “tool not found” error?
Ensure both MCP servers are running and that tool names match exactly (server‑prefixed names like todoplan-server_get-todo are used).
How do I connect programmatically without the web UI?
A standalone MCP client example (mcp-client-example.ts) is included; run it with npm run client from the client/ directory.
More AI & Agents MCP servers
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
Model Context Protocol Server for Home Assistant
tevonsbA MCP server for Home Assistant
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
Comments