Tooluniverse MCP Server

What the code does

We read the source, 20 h ago · rules 3dff92dd89df

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

            masks = model.eval(img, diameter=diameter, channels=channels)[0]

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

            result = subprocess.run(

            output_file = os.path.join(output_dir, filename)

            cache_data = pickle.load(f)

            exec(source_code, module.__dict__)

        "sequence": "NNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNN…

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add tooluniverse -- uvx tooluniverse

{
  "mcpServers": {
    "tooluniverse": {
      "args": [
        "tooluniverse"
      ],
      "command": "uvx"
    }
  }
}

[mcp_servers.tooluniverse]
command = "uvx"
args = ["tooluniverse"]

{
  "mcpServers": {
    "tooluniverse": {
      "args": [
        "tooluniverse"
      ],
      "command": "uvx"
    }
  }
}

{
  "mcpServers": {
    "tooluniverse": {
      "args": [
        "tooluniverse"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: OPENAI_API_KEY (OpenAI API key for LLM-based tool finding and embedding features), ANTHROPIC_API_KEY (Anthropic API key for Claude-based features), GEMINI_API_KEY (Google Gemini API key for Gemini-based features), OPENROUTER_API_KEY (OpenRouter API key for accessing 100+ LLM models), AZURE_OPENAI_API_KEY (Azure OpenAI API key (alternative to OpenAI)), HF_TOKEN (HuggingFace token for accessing models and datasets), NCBI_API_KEY (NCBI/PubMed API key for higher rate limits (10 req/sec vs 3 req/sec). Register at https://www.ncbi.nlm.nih.gov/account/), SEMANTIC_SCHOLAR_API_KEY (Semantic Scholar API key for higher rate limits (100 req/sec vs 1 req/sec). Register at https://www.semanticscholar.org/product/api), BIOGRID_API_KEY (BioGRID API key for protein-protein interaction queries. Register free at https://webservice.thebiogrid.org/), DISGENET_API_KEY (DisGeNET API key for gene-disease association data. Register free at https://www.disgenet.org/), OMIM_API_KEY (OMIM API key for Mendelian disease data. Register at https://omim.org/api), ONCOKB_API_TOKEN (OncoKB API token for precision oncology annotations. Register at https://www.oncokb.org/apiAccess), NVIDIA_API_KEY (NVIDIA NIM API key for AlphaFold2 structure prediction, molecular docking, and genomics tools. Get key at https://build.nvidia.com), USPTO_API_KEY (USPTO API key for patent data access. Register at https://developer.uspto.gov/), UMLS_API_KEY (UMLS API key for medical terminology and concept mapping. Register at https://uts.nlm.nih.gov/uts/), BRENDA_EMAIL (BRENDA enzyme database login email. Register at https://www.brenda-enzymes.org/), BRENDA_PASSWORD (BRENDA enzyme database login password). The author declared them in the registry entry; get the values from the project itself.