MCP server for Claude Code — parallel multi-model queries, smart routing, image/video gen across OpenAI (GPT-5, GPT Image), Gemini (Imagen 4, Veo)
MCP server for Claude Code — parallel multi-model queries, smart routing, image/video gen across OpenAI (GPT-5, GPT Image), Gemini (Imagen 4, Veo), DeepSeek, Kimi & 12+ providers. The mcp multi model mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.
One MCP server. All the models you need. Zero tab-switching.
Everything the assistant can do here goes through one of these:
ask_ai — Query any model — unified entry with temperature / top_p controlask_deepseek — Query DeepSeek directlyask_gemini — Query Gemini directlyask_kimi — Query Kimi directlyask_all — Query all models in parallel, compare resultsask_both — Query any two models in paralleldelegate — Smart routing — auto-picks the best model for the taskgenerate_image — Text → image via Gemini Imagengenerate_video — Text → video via Gemini Veotranslate — CN ↔ EN translationresearch — Deep research with web searchcheck_health — Ping all models, report status and latencyInstallation goes through your MCP client rather than a global install: point it at mcp-multi-model on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
You will need 3 environment variables: DEEPSEEK_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP Multi Model's toolset — ask_ai, ask_deepseek, ask_gemini and 11 more — is a fair guide to whether it matches your workflow. It is maintained by K1vin1906; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| ask_ai | Query any model — unified entry with temperature / top_p control |
| ask_deepseek | Query DeepSeek directly |
| ask_gemini | Query Gemini directly |
| ask_kimi | Query Kimi directly |
| ask_all | Query all models in parallel, compare results |
| ask_both | Query any two models in parallel |
| delegate | Smart routing — auto-picks the best model for the task |
| generate_image | Text → image via Gemini Imagen |
| generate_video | Text → video via Gemini Veo |
| translate | CN ↔ EN translation |
| research | Deep research with web search |
| check_health | Ping all models, report status and latency |
| imagen-4-fast | :predict |
| imagen-4-ultra | :predict |
{
"mcpServers": {
"multi-model": {
"command": "npx",
"args": ["-y", "mcp-multi-model"],
"env": {
"DEEPSEEK_API_KEY": "sk-...",
"GEMINI_API_KEY": "AI..."
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| DEEPSEEK_API_KEY | Credential the server authenticates with. | Yes |
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.