MCP Chat Studio
A powerful MCP testing tool with multi-provider LLM support (Ollama, OpenAI, Claude, Gemini). Test, debug, and develop MCP servers with a modern UI.
What is MCP Chat Studio?
MCP Chat Studio is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to powerful mcp testing tool with multi-provider llm support (ollama, openai, claude, gemini). test, debug, and develop mcp servers with a modern ui.
A powerful MCP testing tool with multi-provider LLM support (Ollama, OpenAI, Claude, Gemini). Test, debug, and develop MCP servers with a modern UI.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A powerful MCP testing tool with multi-provider LLM support
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-chat-studioConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Chat Studio
MCP Chat Studio is a browser-based testing and development environment for MCP servers, supporting nine LLM providers including Ollama (local, free), OpenAI, Claude, Gemini, Azure, Groq, Together AI, and OpenRouter. It provides one-click tool testing, a breakpoint debugger, JSON-RPC protocol inspection, schema validation with drift detection, bulk testing with latency heatmaps, cross-server comparison matrices, and an AI workflow builder — making it the most complete workbench available for developing and debugging MCP server integrations.
Prerequisites
- Node.js installed (for npm-based setup)
- Docker and Docker Compose (for container-based setup)
- At least one LLM provider: Ollama running locally (free, no API key needed) or an API key for OpenAI, Anthropic, Google, Groq, Azure, Together AI, or OpenRouter
- An MCP server to test (your own or any publicly available server)
Clone the repository and install dependencies
Clone the MCP Chat Studio repository and install Node.js dependencies.
git clone https://github.com/JoeCastrom/mcp-chat-studio.git
cd mcp-chat-studio
npm installCopy the environment template and configure providers
Copy the .env.example file to .env and add API keys for any cloud LLM providers you want to use. Ollama works immediately without any API key if it's running locally.
cp .env.example .env
# Edit .env with your API keys:
# ANTHROPIC_API_KEY=sk-ant-your-key
# OPENAI_API_KEY=sk-your-key
# GOOGLE_API_KEY=your-google-ai-keyStart the development server
Start the MCP Chat Studio development server. It runs on port 3082 by default.
npm run devOpen the application and add an MCP server
Open http://localhost:3082 in your browser. Add your MCP server by configuring it in the config.yaml file with its type (stdio or SSE), command, and any required environment variables.
# config.yaml example
mcpServers:
my-server:
type: stdio
command: npx
args:
- -y
- my-mcp-server
env:
API_KEY: '${API_KEY}'
startup: trueRun automated tests on all tools
Use the 'Test ALL tools automatically' button in the UI to run the entire test suite against your MCP server. Review results in the latency heatmap and diff view.
MCP Chat Studio Examples
Client configuration (config.yaml)
Full configuration example for MCP Chat Studio connecting to an Ollama LLM and a stdio MCP server.
{
"llm": {
"provider": "ollama",
"model": "llama3.2"
},
"mcpServers": {
"my-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "my-mcp-server"],
"env": {
"API_KEY": "your-api-key"
},
"startup": true
}
}
}Prompts to try
Prompts for using MCP Chat Studio's AI workflow builder and testing capabilities.
- "Create a workflow that fetches user data from the API, validates the response schema, and logs results"
- "Test all tools and show me which ones have response time over 500ms"
- "Compare the outputs of tool X across two different MCP server versions"
- "Export this workflow as a Python script"
- "Generate a mock server for this MCP schema"Troubleshooting MCP Chat Studio
No LLM providers appear in the provider dropdown
Check that your .env file contains at least one valid API key (e.g., ANTHROPIC_API_KEY or OPENAI_API_KEY), or that Ollama is running locally on port 11434. Restart the dev server after editing .env.
MCP server tools are not loading in the UI
Verify your config.yaml syntax is correct YAML (not JSON). Set 'startup: true' for the server so it connects automatically on launch. Check the server logs in the JSON-RPC inspector tab for connection errors.
Docker Compose fails to start with Ollama profile
The Ollama service in the with-ollama profile requires enough RAM for model loading (typically 4GB+ for small models). Run 'docker-compose --profile with-ollama up' and check container logs if startup times out.
Frequently Asked Questions about MCP Chat Studio
What is MCP Chat Studio?
MCP Chat Studio is a Model Context Protocol (MCP) server that powerful mcp testing tool with multi-provider llm support (ollama, openai, claude, gemini). test, debug, and develop mcp servers with a modern ui. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Chat Studio?
Follow the installation instructions on the MCP Chat Studio GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Chat Studio?
MCP Chat Studio works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Chat Studio free to use?
Yes, MCP Chat Studio is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Chat Studio Alternatives — Similar Developer Tools Servers
Looking for alternatives to MCP Chat Studio? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Chat Studio in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Chat Studio?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.