Multi LLM Cross-Check MCP Server
A Model Control Protocol (MCP) server that allows cross-checking responses from multiple LLM providers simultaneously. This server integrates with Claude Desktop as an MCP server to provide a unified interface for querying different LLM APIs.
Features
- Query multiple LLM providers in parallel
- Currently supports:
- OpenAI (ChatGPT)
- Anthropic (Claude)
- Perplexity AI
- Google (Gemini)
- Asynchronous parallel processing for faster responses
- Easy integration with Claude Desktop
Prerequisites
- Python 3.8 or higher
- API keys for the LLM providers you want to use
- uv package manager (install with
pip install uv)
Installation
Installing via Smithery
To install Multi LLM Cross-Check Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @lior-ps/multi-llm-cross-check-mcp-server --client claude
Manual Installation
- Clone this repository:
git clone https://github.com/lior-ps/multi-llm-cross-check-mcp-server.git
cd multi-llm-cross-check-mcp-server
- Initialize uv environment and install requirements:
uv venv
uv pip install -r requirements.txt
-
Configure in Claude Desktop: Create a file named
claude_desktop_config.jsonin your Claude Desktop configuration directory with the following content:{ "mcp_servers": [ { "command": "uv", "args": [ "--directory", "/multi-llm-cross-check-mcp-server", "run", "main.py" ], "env": { "OPENAI_API_KEY": "your_openai_key", // Get from https://platform.openai.com/api-keys "ANTHROPIC_API_KEY": "your_anthropic_key", // Get from https://console.anthropic.com/account/keys "PERPLEXITY_API_KEY": "your_perplexity_key", // Get from https://www.perplexity.ai/settings/api "GEMINI_API_KEY": "your_gemini_key" // Get from https://makersuite.google.com/app/apikey } } ] }
Notes:
- You only need to add the API keys for the LLM providers you want to use. The server will skip any providers without configured API keys.
- You may need to put the full path to the uv executable in the command field. You can get this by running
which uvon MacOS/Linux orwhere uvon Windows.
Using the MCP Server
Once configured:
- The server will automatically start when you open Claude Desktop
- You can use the
cross_checktool in your conversations by asking to "cross check with other LLMs" - Provide a prompt, and it will return responses from all configured LLM providers
API Response Format
The server returns a dictionary with responses from each LLM provider:
{
"ChatGPT": { ... },
"Claude": { ... },
"Perplexity": { ... },
"Gemini": { ... }
}
Error Handling
- If an API key is not provided for a specific LLM, that provider will be skipped
- API errors are caught and returned in the response
- Each LLM's response is independent, so errors with one provider won't affect others
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Metadata
Release files for iflow-mcp_lior-ps_multi-llm-cross-check-mcp-server 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0.tar.gz | 5.7 kB | Without provenance | Details for iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0-py3-none-any.whl |
Total release size: 23.9 kB
Release files / iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0.tar.gz
| Download URL | iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0.tar.gz |
|---|---|
| Size | 5.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
18d4a6dcd0c3c78316d9857eec3ce5028472b26e5420c5232e5ed31d7f5345aa
|
|
BLAKE2b-256 checksum How to use checksums |
2a4cd20a8ec6d23ac803376e253e0d9efcbb61ec6237fdc21db755c323d7a28f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.28 {"installer":{"name":"uv","version":"0.9.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0-py3-none-any.whl
| Download URL | iflow_mcp_lior_ps_multi_llm_cross_check_mcp_server-0.1.0-py3-none-any.whl |
|---|---|
| Size | 18.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3fa273d3dcd9b7f020861ab4f27b3df5063659be36b0c9db725b60c8cc01b2d6
|
|
BLAKE2b-256 checksum How to use checksums |
6a52e8bdda943326872c57d03a5f7d12da09e5d5f7c36449130a63217d37fb09
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.28 {"installer":{"name":"uv","version":"0.9.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for iflow-mcp_lior-ps_multi-llm-cross-check-mcp-server 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.