Name: Cross LLM MCP
Author: JamesANZ

LABSCO SUMMARY

Nine model APIs behind one set of tools.

The value is comparison: put a question to every provider in one call and read the answers next to each other instead of pasting between tabs. Tag preferences and the flagship-versus-cheap switch decide which model each provider actually serves it to.

What it is

An MCP server that puts nine large-language-model APIs behind one set of tools inside a coding client, so a prompt can go to one provider or to every provider at once.

What you get

One tool per provider: call-chatgpt, call-claude, call-gemini, call-grok, call-deepseek, call-kimi, call-perplexity, call-mistral and call-huggingface
The same prompt sent to every provider in a single call, so the answers land side by side
Tag-based model preferences across coding, business, reasoning, math, creative and general work
A cost preference that decides whether a provider serves its flagship model or a cheaper one
Hugging Face Inference Router access, which brings OpenAI-compatible Hub models under the same call shape
Prompt logging with history and statistics

Requirements

Node. Install with npm install -g cross-llm-mcp, from source, or through the one-click install link for Cursor.

Setup effort

Build from source — git clone https://github.com/JamesANZ/cross-llm-mcp.git

See installation options

USE CASES

01

Getting a second opinion on an answer

Put the same question to a different provider and see whether the two agree.

call-chatgptcall-claude

02

Choosing a model for a job before you commit to it

Send one prompt to several providers and read the replies side by side.

call-geminicall-grokcall-mistral

03

Sending work to the model that is better at it

Route reasoning or maths to the provider you tagged for it rather than to whatever your client defaults to.

call-deepseekcall-perplexity

04

Reaching open models without a second integration

Hub models come through the Hugging Face Inference Router in the same call shape as the hosted providers.

call-huggingface

18 tools

Listed in project docs. Your client may show a different list.

call-chatgpt

call-claude

call-deepseek

call-gemini

call-grok

call-kimi

call-perplexity

call-mistral

call-huggingface

call-all-llms

call-llm

get-user-preferences

set-user-preferences

get-models-by-tag

get-prompt-history

BEFORE YOU INSTALL

What to know first

Tools you get

18 tools named in the project's documentation.

Requires

npm on PATH
OPENAI_API_KEY in your environment
ANTHROPIC_API_KEY in your environment
DEEPSEEK_API_KEY in your environment
GEMINI_API_KEY in your environment
XAI_API_KEY in your environment
KIMI_API_KEY in your environment
PERPLEXITY_API_KEY in your environment
MISTRAL_API_KEY in your environment
HF_TOKEN in your environment

INSTALLATION

Connect your client

Server setup

TERMINAL

# Clone and build
git clone https://github.com/JamesANZ/cross-llm-mcp.git
cd cross-llm-mcp
npm install
npm run build

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "cross-llm-mcp": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_CROSS_LLM_MCP>/build/index.js"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>",
        "GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>",
        "KIMI_API_KEY": "<YOUR_KIMI_API_KEY>",
        "PERPLEXITY_API_KEY": "<YOUR_PERPLEXITY_API_KEY>",
        "MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>",
        "HF_TOKEN": "<YOUR_HF_TOKEN>"
      }
    }
  }
}

Cursor

CURSOR

cursor://anysphere.cursor-deeplink/mcp/install?name=cross-llm-mcp&config=eyJjcm9zcy1sbG0tbWNwIjp7ImNvbW1hbmQiOiJucHgiLCJhcmdzIjpbIi15IiwiY3Jvc3MtbGxtLW1jcCJdfX0=

Cross LLM MCP