Demo
https://github.com/user-attachments/assets/02129685-5ba5-4b90-89e7-9d4a39986210
Watch full video here:
Setup
Prerequisites
- uv or Docker
- Claude Desktop (for MCP integration)
Setup Guides
For detailed setup instructions, refer to the following documentation:
-
NANDA Host Setup
Seedocs/nanda-server-setup.mdfor backend configuration and local registration of the NANDA Server. -
Claude Desktop Setup
Seedocs/claude-desktop-setup.mdfor guidance on configuring the local development environment and MCP integration.
These guides include all required steps, environment configurations, and usage notes to get up and running.
Tool List
search_clinical_evidence: A MCP tool for querying clinical evidence data that returns formatted reports.
Input Schema
The tool accepts the following optional parameters:
disease_name(str): Filter by disease (e.g., "Lung Non-small Cell Carcinoma").therapy_name(str): Filter by therapy or drug (e.g., "Cetuximab").molecular_profile_name(str): Filter by gene or variant (e.g., "EGFR L858R").phenotype_name(str): Filter by phenotype (e.g., "Chest Pain").evidence_type(str): Filter by evidence type (e.g., "PREDICTIVE", "DIAGNOSTIC").evidence_direction(str): Filter by evidence direction (e.g., "SUPPORTS").filter_strong_evidence(bool): IfTrue, only includes evidence with a rating > 3 (max 5).
Output
The tool returns a formatted string with four sections:
- Summary Statistics:
- Total evidence items
- Average evidence rating
- Top 3 diseases, genes, variants, therapies, and phenotypes (with counts)
- Top 10 Evidence Entries:
- Lists the highest-rated evidence items with details like disease, phenotype, gene/variant, therapy, description, type, direction, and rating.
- Sources & Citations:
- Citations and URLs for the sources of the top 10 evidence entries.
- Disclaimer:
- A note stating the tool is for research purposes only, not medical advice.
Sample Usage
- "Find predictive evidence for colorectal cancer therapies involving KRAS mutations."
- "Are there studies on Imatinib for leukemia?"
- "What therapies are linked to pancreatic cancer evidence?"
Acknowledgements
- Model Context Protocol
- NANDA: The Internet of AI Agents
- CIViC - Clinical Interpretation of Variants in Cancer
License
This project is licensed under the MIT License - see the LICENSE file for details.
Disclaimer
⚠️ This tool is intended exclusively for research purposes. It is not a substitute for professional medical advice, diagnosis, or treatment.
Contributors
- Obada Qasem (@obadaqasem), Nexgene AI
- Kutsal Ozkurt (@Goodsea), Nexgene AI