unichat-ts-mcp-server
This unichat-ts-mcp-server enables interaction with various AI models through the MCP protocol, offering:
AI Model Access: Send chat requests to multiple vendors including OpenAI, MistralAI, Anthropic, xAI, Google AI, and DeepSeek using the
unichattoolPredefined Prompts: Execute specific code-related tasks like review, documentation, explanation, and rework using built-in templates
Communication Options: Support for both STDIO and Server-Sent Events (SSE) transport mechanisms
Configurable Settings: Customize model selection and API keys through environment variables (
UNICHAT_MODEL,UNICHAT_API_KEY)Debugging Support: Includes tools like MCP Inspector for troubleshooting communication issues
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@unichat-ts-mcp-serverexplain how this Python function sorts a list"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Unichat MCP Server in TypeScript
Also available in Python
Send requests to OpenAI, MistralAI, Anthropic, xAI, Google AI or DeepSeek using MCP protocol via tool or predefined prompts. Vendor API key required.
Both STDIO and SSE transport mechanisms supported via arguments.
Tools
The server implements one tool:
unichat: Send a request to unichatTakes "messages" as required string arguments
Returns a response
Prompts
code_reviewReview code for best practices, potential issues, and improvements
Arguments:
code(string, required): The code to review"
document_codeGenerate documentation for code including docstrings and comments
Arguments:
code(string, required): The code to comment"
explain_codeExplain how a piece of code works in detail
Arguments:
code(string, required): The code to explain"
code_reworkApply requested changes to the provided code
Arguments:
changes(string, optional): The changes to apply"code(string, required): The code to rework"
Related MCP server: minimax-llm-mcp
Development
Clean installation from source
Prerequisites: Git, Node.js and npm. Use Node.js 24 to match the repository's publishing workflow; package.json does not declare a supported Node.js version range. Include development dependencies when installing, since the build requires TypeScript.
Clone the repository and restore dependencies from the committed package-lock.json:
git clone https://github.com/amidabuddha/unichat-ts-mcp-server.git
cd unichat-ts-mcp-server
npm cinpm ci automatically runs prepare, which invokes npm run build. That script removes the generated build/ directory, compiles src/ into build/ using tsconfig.json, and marks build/index.js executable. With lifecycle scripts enabled (the default), no separate first build is needed. Keep package-lock.json and install development dependencies; do not use --ignore-scripts or --omit=dev for this workflow.
Before running, set UNICHAT_MODEL and UNICHAT_API_KEY in the process environment, or use the MCP client's env configuration shown under Installing manually. Replace both placeholders with a supported model and its vendor API key. For example, in a POSIX shell:
export UNICHAT_MODEL="YOUR_PREFERRED_MODEL_NAME"
export UNICHAT_API_KEY="YOUR_VENDOR_API_KEY"
node build/index.js --stdioThe server reads the process environment; it does not automatically load .env files. STDIO expects an MCP client to communicate with the process. To run the local build over SSE instead, use node build/index.js --sse (default endpoint: http://localhost:3001/sse). See the SSE host configuration below for remote access.
Normal development
Run all commands from the repository root. For automatic recompilation as source files change:
npm run watchThis runs tsc --watch, which recompiles affected files during the watch session. It does not start or restart the server. After compilation, restart the server or reconnect the MCP client so it launches the updated build, using the environment setup above.
For a one-off build:
npm run buildThis script always recreates build/; use watch mode for incremental recompilation during editing. Ordinary source changes do not require deleting dependencies or reinstalling everything. If dependency manifests and the lockfile change after pulling updates, run npm ci again.
There is no automated test script in package.json. The build performs TypeScript checking; for manual MCP checks after building, run npm run inspector with the required environment variables set, as described under Debugging.
Clean rebuild of an existing checkout
Stop any running watcher and server first. From the repository root, restore locked dependencies and rebuild from scratch:
npm cinpm ci replaces node_modules/ itself, then prepare runs the build script, which deletes and regenerates only build/. This also works when either or both directories have already been removed. No separate deletion or second build command is needed.
If dependencies are already installed and match the lockfile, and only generated output needs a clean rebuild, run:
npm run buildThese workflows preserve src/, configuration, .env files, user data outside the generated directories, and package-lock.json. Keep only generated files in build/. Do not use git clean or clear global npm caches or toolchains for a project rebuild.
Publishing
Publishing is a separate release action. The repository's publishing workflow uses npm publish after installation and building. Local installation, development and clean rebuilds do not require publishing.
Installation
Installing via Smithery
To install Unichat MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install unichat-ts-mcp-server --client claudeInstalling manually
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Run locally:
{
"mcpServers": {
"unichat-ts-mcp-server": {
"command": "node",
"args": [
"{{/path/to}}/unichat-ts-mcp-server/build/index.js"
],
"env": {
"UNICHAT_MODEL": "YOUR_PREFERRED_MODEL_NAME",
"UNICHAT_API_KEY": "YOUR_VENDOR_API_KEY"
}
}
}Run published:
{
"mcpServers": {
"unichat-ts-mcp-server": {
"command": "npx",
"args": [
"-y",
"unichat-ts-mcp-server"
],
"env": {
"UNICHAT_MODEL": "YOUR_PREFERRED_MODEL_NAME",
"UNICHAT_API_KEY": "YOUR_VENDOR_API_KEY"
}
}
}Runs in STDIO by default or with argument
--stdio. To run in SSE add argument--sse
npx -y unichat-ts-mcp-server --sseSSE transport validates the Host header against localhost, 127.0.0.1, and [::1] by default. For remote SSE deployments, set MCP_ALLOWED_HOSTS to a comma-separated list of allowed hostnames.
Supported Models:
A list of currently supported models to be used as
"YOUR_PREFERRED_MODEL_NAME"may be found here. Please make sure to add the relevant vendor API key as"YOUR_VENDOR_API_KEY"
Example:
"env": {
"UNICHAT_MODEL": "gpt-5.4-mini",
"UNICHAT_API_KEY": "YOUR_OPENAI_API_KEY"
}Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
If you experience timeouts during testing in SSE mode change the request URL on the inspector interface to: http://localhost:3001/sse?timeout=600000
This server cannot be deployed
Maintenance
Related MCP Connectors
- QuallaaOAuthcom.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
- craftOAuthio.illumora
Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Related MCP Servers
- AlicenseCqualityCmaintenanceSend requests to OpenAI, MistralAI, Anthropic, xAI, or Google AI using MCP protocol via tool or predefined prompts. Vendor API key required140MIT
- AlicenseAqualityDmaintenanceExposes the MiniMax M3 LLM API to MCP-compatible clients, enabling chat completions, text completions, tool calls, and token counting via stdio or SSE transport.4MIT
- FlicenseNot gradedqualityDmaintenanceEnables interaction with Claude and Gemini command-line tools through the MCP protocol, allowing users to send prompts to either or both LLMs and receive responses.-
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to interact with EDA projects via natural language by wrapping EDI's gRPC interface, CLI tools, and ANSYS HFSS as MCP tools supporting SSE and stdio transports.3MIT
Appeared in Searches
- Using a second LLM to collaborate with a primary LLM for problem-solving and quality improvement
- A list of all remote servers
- A system for task management and integration with AI editors using multiple LLMs
- Tools and Templates for Prompt Management and Workflow Automation
- Information or resources related to 'Prompt'