any-chat-completions-mcp MCP Server

What does “any-chat-completions-mcp” MCP Server do?

The any-chat-completions-mcp MCP Server acts as a bridge between AI assistants and any OpenAI SDK-compatible Chat Completion API, such as OpenAI, Perplexity, Groq, xAI, and PyroPrompts. By adhering to the Model Context Protocol (MCP), it enables seamless integration of external LLM providers into development workflows. Its primary function is to relay chat-based questions to a configured AI chat provider, allowing developers to utilize various LLMs as tools within their preferred environments. This makes tasks like switching between providers or scaling LLM usage straightforward, fostering flexibility and efficiency in AI-powered applications.

List of Prompts

No prompt templates are mentioned in the repository or documentation.

List of Resources

No explicit MCP resources are documented in the repository or README.

List of Tools

• chat: Relays a question to a configured AI Chat Provider. This is the main (and only) tool exposed by the server, allowing LLMs or clients to send chat-based queries to any OpenAI-compatible API endpoint.

Use Cases of this MCP Server

• Unified LLM Integration: Developers can use a single MCP server to access multiple LLM providers without changing their client code, simplifying provider management.
• Provider Switching: Easily switch between OpenAI, PyroPrompts, Perplexity, and others by updating environment variables, useful for cost optimization or fallback strategies.
• Custom Desktop AI Agents: Integrate advanced chat-based LLMs into desktop applications (e.g., Claude Desktop) to power enhanced assistant features.
• Experimentation and Benchmarking: Rapidly compare outputs from different LLMs in a standardized way for research, QA, or product development.
• API Gateway for LLMs: Acts as a lightweight gateway for securely routing chat messages to various LLM APIs, centralizing API key and endpoint management.

How to set it up

Windsurf

No platform-specific instructions are provided for Windsurf in the repository or documentation.

Claude

1. Prerequisite: Ensure Node.js and npx are installed.
2. Locate Config File: Edit claude_desktop_config.json (on MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows: %APPDATA%/Claude/claude_desktop_config.json).
3. Add MCP Server: Add the MCP server configuration under the mcpServers object.
4. Set Environment Variables: Place provider API keys and other info in the env object.
5. Save and Restart: Save the file and restart Claude Desktop to apply changes.

JSON Example:

{
  "mcpServers": {
    "chat-openai": {
      "command": "npx",
      "args": [
        "@pyroprompts/any-chat-completions-mcp"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "v1/chat/completions"
      }
    }
  }
}

Securing API Keys (using environment variables):

"env": {
  "AI_CHAT_KEY": "YOUR_PROVIDER_KEY"
}

Cursor

No platform-specific instructions are provided for Cursor in the repository or documentation.

Cline

No platform-specific instructions are provided for Cline in the repository or documentation.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "MCP-name": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “MCP-name” to whatever the actual name of your MCP server is (e.g., “github-mcp”, “weather-api”, etc.) and replace the URL with your own MCP server URL.

Overview

Based on the above, any-chat-completions-mcp is a focused, streamlined MCP server ideal for adding generic OpenAI-compatible chat APIs as tools. Its main strength is simplicity and broad compatibility, though it lacks resource and prompt abstractions. For routine LLM integration, it’s robust, but power users may want more features. Overall, I would rate this MCP at 6/10 for general-purpose usage.

MCP Score