Multi-Provider MCP Server
Integrates with the OpenAI API to send prompts to models and retrieve responses, enabling side-by-side comparison with other LLM providers.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Multi-Provider MCP Server
A Model Context Protocol server, built on the official Python SDK, whose headline tool asks the same question to Claude, OpenAI, and Gemini and returns the answers side by side. The provider layer is a small adapter interface, so adding a fourth vendor means adding one file.
Tools
Tool | What it does |
| Sends one prompt to every configured provider concurrently and returns each answer keyed by provider. A provider that fails reports its error without hiding the others. |
| Lists the providers that have an API key configured. |
| Fetches a page and returns its title, word count, and a short excerpt. |
| Returns the current time in any IANA timezone. |
Related MCP server: cognition-wheel
Design
Adapter per vendor.
LLMProviderdefines a singlecomplete(prompt)method.ClaudeProvider,OpenAIProvider, andGeminiProvidereach translate that into their vendor's request and response shape.Providers are opt-in.
build_configured_providersregisters only the vendors whose API key is present in the environment. With no keys set, the comparison tool explains what to configure instead of failing.Logic lives outside the MCP layer. Each tool is a thin wrapper over a plain function, so the behavior is tested directly and again through a real MCP client session.
Injectable dependencies.
create_serveraccepts an HTTP client and a provider factory, which is what lets the test suite run without network access or API keys.
Running it
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
export ANTHROPIC_API_KEY=... # set any combination of the three keys
python -m server.mainThe server speaks MCP over stdio. To use it from an MCP client such as Claude Desktop, register it as a stdio server:
{
"mcpServers": {
"multi-llm": {
"command": "python",
"args": ["-m", "server.main"],
"cwd": "/path/to/mcp-multi-llm-server",
"env": { "ANTHROPIC_API_KEY": "...", "OPENAI_API_KEY": "..." }
}
}
}Default models can be overridden with ANTHROPIC_MODEL, OPENAI_MODEL, and GEMINI_MODEL; see .env.example.
Tests
pip install -r requirements-dev.txt
pytestThe suite mocks the HTTP layer, so it needs no network access and no API keys. It covers each adapter's request and response shape, failure isolation in the comparison, and a full client-to-server round trip over the MCP protocol.
Note that the adapters are verified against mocked responses that follow each vendor's documented API, not against the live services.
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Every AI model, inside the app you already use: ask GPT, Claude, Gemini or Grok, and see what paid.
Answers, sources and brand mentions from OpenAI, Perplexity, Gemini, Claude and Grok side by side.
Ask ChatGPT, Gemini, Copilot or Google AI Mode a prompt: full answer + every cited source.
Ask GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceLets Claude Code query multiple AI models (Gemini, Grok, ChatGPT, DeepSeek) for diverse perspectives, code reviews, debates, and more.MIT
- AlicenseAqualityDmaintenanceEnables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.129 npm193MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude to query other LLMs like ChatGPT, Perplexity, and Gemini for verification and comparison, eliminating manual copy-pasting.ISC
- AlicenseNot gradedqualityBmaintenanceFans out queries to multiple independent free LLMs from different providers and returns their answers side by side, enabling sanity-checking of decisions or getting multiple perspectives during coding sessions.GPL 3.0