广告合作
MCP.so
登录

Unichat MCP Server in TypeScript

@amidabuddha

代码仓库

基本信息

分类

其他

许可证

MIT

传输方式

stdio

作者

amidabuddha

关于 Unichat MCP Server in TypeScript

暂无概览

Unichat MCP Server in TypeScript 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "unichat-ts-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "unichat-ts-mcp-server",
        "--client",
        "claude"
      ]
    }
  }
}

Unichat MCP Server in TypeScript 工具

1

Send a request to unichat

概览

What is Unichat MCP Server in TypeScript?

Unichat MCP Server in TypeScript is an MCP server that sends chat requests to AI vendors—OpenAI, MistralAI, Anthropic, xAI, Google AI, and DeepSeek—via a single tool or predefined prompts. It requires a vendor-specific API key and is intended for developers using the MCP protocol.

How to use Unichat MCP Server in TypeScript?

Install automatically via Smithery (npx @smithery/cli install unichat-ts-mcp-server --client claude) or manually by adding the server configuration to Claude Desktop’s JSON file. Set UNICHAT_MODEL and UNICHAT_API_KEY environment variables. Run locally with node build/index.js or published with npx -y unichat-ts-mcp-server. Use --sse for SSE transport (default is STDIO). For remote SSE, set MCP_ALLOWED_HOSTS to a comma-separated list of allowed hostnames.

Key features of Unichat MCP Server in TypeScript

  • One tool: unichat for sending chat requests
  • Four predefined prompts: code review, document code, explain code, code rework
  • Supports STDIO and SSE transport mechanisms
  • Works with multiple AI vendors (OpenAI, MistralAI, Anthropic, xAI, Google AI, DeepSeek)
  • Available as an npm package and via Smithery

Use cases of Unichat MCP Server in TypeScript

  • Review code for best practices and potential issues
  • Generate code documentation including docstrings and comments
  • Explain code functionality in detail
  • Apply requested changes to existing code

常见问题

1

Which AI vendors are supported?

OpenAI, MistralAI, Anthropic, xAI, Google AI, and DeepSeek are supported. You must provide the corresponding vendor API key.

2

How do I choose the model to use?

Set the `UNICHAT_MODEL` environment variable to your preferred model name (e.g., `gpt-5.4-mini`). A full list of supported model names is available in the [models.ts file](https://github.com/amidabuddha/unichat-ts/blob/main/src/models.ts).

3

What transport modes are available?

The server supports both STDIO (default) and SSE. To run in SSE mode, add the `--sse` argument when starting the server. SSE transport validates the `Host` header against `localhost`, `127.0.0.1`, and `[::1]` by default; for remote deployments, set `MCP_ALLOWED_HOSTS`.

4

Where is the Claude Desktop configuration file?

On macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`. On Windows: `%APPDATA%/Claude/claude_desktop_config.json`.

5

What dependencies are required?

Node.js and npm are required. Install dependencies with `npm install`, then build with `npm run build`. For development, use `npm run watch` for auto-rebuild.

评论

其他 分类下的更多 MCP 服务器

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

der die das – German noun genders (Lingviko)

Lingviko

The article (der, die, das) of 90,000 German nouns, compounds included, plus a checker that finds wrong articles in German text (“mit der Zug” → dem). Uses dictionary data, not AI guessing. Free, no login.

广告合作