# LLM Completions

> Use this tool when you need to integrate multiple AI providers into a single interface, or switch between different AI services without changing the core integration. It solves the problem of vendor lock-in and allows experimentation with various AI models, providing a standardized interface for chat completions. The LLM Completions tool takes in questions and returns responses, enabling seamless interaction with OpenAI, Perplexity, Groq, xAI, and PyroPrompts through a single 'chat' tool.

Canonical page: https://skillsregistry.net/skills/pyroprompts-llm-completions-mcp  
JSON: https://api.skillsregistry.net/v1/skills/pyroprompts-llm-completions-mcp

## Description

This MCP server, developed by pyroprompts, enables AI assistants to interact with any OpenAI SDK-compatible chat completion API, including OpenAI, Perplexity, Groq, xAI, and PyroPrompts. It provides a single 'chat' tool that relays questions to the configured AI provider and returns responses. Built in TypeScript, the implementation offers a flexible way to integrate various AI models into Claude Desktop through a standardized MCP interface. By abstracting away provider-specific details, this server allows easy switching between different AI services without changing the core integration. It is particularly useful for users who want to leverage multiple AI providers within Claude, experiment with different models, or avoid vendor lock-in while maintaining a consistent interaction pattern.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pyroprompts-llm-completions-mcp)
- **Repository:** <https://github.com/pyroprompts/any-chat-completions-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "pyroprompts-llm-completions-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pyroprompts-llm-completions-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pyroprompts-llm-completions-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt