通过工具或预定义提示，使用 MCP 协议向 OpenAI、MistralAI、Anthropic、xAI、Google AI、DeepSeek、Alibaba、Inception 发送请求。需要供应商 API 密钥
服务器实现了一个工具：
unichat ：向 unichat 发送请求
将“消息”作为必需的字符串参数
返回响应
code_review
审查代码以获得最佳实践、潜在问题和改进
参数：
code （字符串，必需）：要审查的代码”
document_code
生成代码文档，包括文档字符串和注释
参数：
code （字符串，必需）：要评论的代码”
explain_code
详细解释一段代码是如何工作的
参数：
code （字符串，必需）：要解释的代码”
code_rework
将请求的更改应用到提供的代码
参数：
changes （字符串，可选）：要应用的更改”
code （字符串，必需）：需要重新处理的代码”
Related MCP server: MCP AI Gateway
在 MacOS 上： ~/Library/Application\ Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
支持的型号：
当前支持的可用作
"SELECTED_UNICHAT_MODEL"的模型列表可在此处找到。请务必将相关供应商 API 密钥添加为"YOUR_UNICHAT_API_KEY"
例子：
"env": {
"UNICHAT_MODEL": "gpt-4o-mini",
"UNICHAT_API_KEY": "YOUR_OPENAI_API_KEY"
}开发/未发布的服务器配置
"mcpServers": {
"unichat-mcp-server": {
"command": "uv",
"args": [
"--directory",
"{{your source code local directory}}/unichat-mcp-server",
"run",
"unichat-mcp-server"
],
"env": {
"UNICHAT_MODEL": "SELECTED_UNICHAT_MODEL",
"UNICHAT_API_KEY": "YOUR_UNICHAT_API_KEY"
}
}
}已发布的服务器配置
"mcpServers": {
"unichat-mcp-server": {
"command": "uvx",
"args": [
"unichat-mcp-server"
],
"env": {
"UNICHAT_MODEL": "SELECTED_UNICHAT_MODEL",
"UNICHAT_API_KEY": "YOUR_UNICHAT_API_KEY"
}
}
}要通过Smithery自动为 Claude Desktop 安装 Unichat：
npx -y @smithery/cli install unichat-mcp-server --client claude准备分发包：
删除旧版本：
rm -rf dist同步依赖项并更新锁文件：
uv sync构建软件包分发版：
uv build这将在dist/目录中创建源和轮子分布。
发布到 PyPI：
uv publish --token {{YOUR_PYPI_API_TOKEN}}由于 MCP 服务器通过 stdio 运行，调试起来可能比较困难。为了获得最佳调试体验，我们强烈建议使用MCP Inspector 。
您可以使用以下命令通过npm启动 MCP Inspector：
npx @modelcontextprotocol/inspector uv --directory {{your source code local directory}}/unichat-mcp-server run unichat-mcp-server启动后，检查器将显示一个 URL，您可以在浏览器中访问该 URL 以开始调试。
Chat with an assistant. Example tool use message: Ask the unichat to review and evaluate your proposal.
| Name | Required | Description | Default |
|---|---|---|---|
| messages | Yes | Array of exactly two messages: first a system message defining the task, then a user message with the specific query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions nothing about behavioral traits like whether this is a read-only operation, if it requires authentication, rate limits, or what kind of responses to expect. The example hints at evaluation tasks but doesn't disclose operational characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief but includes an example that adds some value. However, the formatting with extra whitespace is awkward, and the example could be integrated more cleanly. It's not excessively verbose, but the structure could be improved for better front-loading of information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a chat tool with no annotations and no output schema, the description is insufficient. It doesn't explain what the assistant does, what domains it covers, what format responses take, or any limitations. The example provides minimal context but doesn't compensate for the lack of structured information about this interactive tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents the single parameter (messages array with exactly two messages). The description adds no parameter information beyond what's in the schema, not even mentioning the two-message requirement. Baseline 3 is appropriate when schema does all the work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Chat with an assistant' which indicates the basic function, but it's vague about what this assistant does or what domain it operates in. The example tool use message adds some context about reviewing proposals, but doesn't make the purpose specific or distinguish it from other chat tools. It's not tautological but lacks clear differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives is provided. The example suggests it can be used for reviewing proposals, but there's no mention of prerequisites, limitations, or when not to use it. With no sibling tools, the bar is lower, but still lacks basic usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
unichatScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'unichat' has a clear and distinct purpose of chatting with an assistant.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'unichat' follows a simple, readable pattern without any conflicting conventions.
A single tool is too few for most server purposes, as it severely limits functionality and scope. While it might be appropriate for a minimal chat interface, it feels thin and lacks the depth expected for a typical MCP server, which usually requires multiple tools to handle different operations or resources.
For a chat assistant domain, the single tool 'unichat' covers the core action of chatting, but there are notable gaps. It lacks operations for managing chat history, configuring settings, or handling multiple sessions, which are common in chat systems. However, the basic functionality is present, allowing agents to perform the primary task.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
