Marrvel Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Marrvel Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- mcp-name: io.github.hyunhwan-bcm/marrvel-mcp -->
A Model Context Protocol (MCP) server for MARRVEL - enabling AI agents to access genetics databases and variant analysis tools for rare disease research.
Try out MARRVEL-MCP in action:
git clone https://github.com/hyunhwan-bcm/MARRVEL_MCP.git
cd MARRVEL_MCP
# Using uv (recommended)
uv sync # core MCP server only
uv sync --extra eval # include evaluation framework dependencies
# Or using pip
pip install . # core MCP server only
pip install ".[eval]" # include evaluation framework dependenciesTo use MARRVEL-MCP with Claude Desktop, LM Studio, or other MCP-compatible clients, add the following to your client's MCP configuration:
{
"mcpServers": {
"marrvel-mcp": {
"command": "/path/to/your/.venv/bin/python",
"args": ["/path/to/MARRVEL_MCP/server.py"]
}
}
}Replace the paths with the actual locations of your Python virtual environment and the cloned repository.
Ask your AI assistant natural language questions about genes, variants, diseases, orthologs, and literature. For example test cases, see mcp_llm_test/test_cases.yaml.
MARRVEL-MCP provides 35+ MCP tools for genetics research:
See docs/TOOL_RELATIONSHIPS.md for a visual diagram of tool chains and workflows.
| Document | Description |
|---|---|
mcp_llm_test/README.md | Evaluation framework for benchmarking LLMs with MARRVEL-MCP |
docs/TOOL_RELATIONSHIPS.md | Tool relationship graph and common analysis chains |
marrvel_mcp/README.md | Package API reference for the marrvel_mcp module |
tests/README.md | Test suite overview and instructions |
# Install with dev dependencies
uv sync --group dev --extra eval
# Run tests
pytest tests/
# Format code
black .Wang J, et al. (2017) MARRVEL: Integration of Human and Model Organism Genetic Resources to Facilitate Functional Annotation of the Human Genome. Am J Hum Genet 100(6):843-853.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.