Nexonco MCP Server

@Nexgene-Research

Basic information

About Nexonco MCP Server

An advanced MCP Server for accessing and analyzing clinical evidence data, with flexible search options to support precision medicine and oncology research.

#ai #mcp #health

Nexonco MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "nexonco": {
      "command": "uv",
      "args": [
        "--directory",
        "/full/path/to/nexonco/nexonco",
        "run",
        "server.py"
      ]
    }
  }
}

Nexonco MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Nexonco Mcp?

Nexonco Mcp is an MCP server for accessing clinical evidence from the CIViC (Clinical Interpretation of Variants in Cancer) database. It enables fast, flexible search across variants, diseases, drugs, and phenotypes to support precision oncology.

How to use Nexonco Mcp?

Install and run using uv or Docker. For MCP integration, you need Claude Desktop. Refer to docs/nanda-server-setup.md and docs/claude-desktop-setup.md for full configuration. Invoke the single tool search_clinical_evidence with optional search filters.

Key features of Nexonco Mcp

Single tool search_clinical_evidence for querying clinical evidence.
Returns a formatted report with summary statistics, top evidence, citations, and disclaimer.
Filter by disease, therapy, molecular profile, phenotype, evidence type, and direction.
Option to filter only strong evidence (rating > 3).
Sources and citations included for top evidence entries.
Designed for research purposes only, not medical advice.

Use cases of Nexonco Mcp

Find predictive evidence for colorectal cancer therapies involving KRAS mutations.
Search for studies on Imatinib for leukemia.
Discover what therapies are linked to pancreatic cancer evidence.
Quickly retrieve high-rated clinical evidence for precision oncology research.

Frequently asked questions

What database does Nexonco Mcp query?

It queries the CIViC (Clinical Interpretation of Variants in Cancer) database.

Is Nexonco Mcp a substitute for professional medical advice?

No. The tool is intended exclusively for research purposes and is not a substitute for professional medical advice, diagnosis, or treatment.

What are the prerequisites for running Nexonco Mcp?

You need either uv or Docker installed, and Claude Desktop for MCP integration.

What parameters does the search tool accept?

The tool accepts optional filters: disease_name, therapy_name, molecular_profile_name, phenotype_name, evidence_type, evidence_direction, and a Boolean filter_strong_evidence.

Does Nexonco Mcp provide citations for its results?

Yes. The output includes a "Sources & Citations" section with citations and URLs for the top 10 evidence entries.

Comments

More Data & Analytics MCP servers

Midpoint Card Prices

I Lov Guitars Inc.

Trading-card market prices and grading ROI as MCP tools. Read-only, no auth. Powers the Midpoint Card Prices plugin in ChatGPT; works with Claude, Cursor and any MCP client.

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

Statiko

Live public-Telegram data for AI agents: trending topics, channel profiles and metrics, similar channels, and full post history including edits and deletions. 10 read-only tools; every result links back to its statiko.io

Goldsky

Goldsky docs: Edge RPC, Feeds APIs, Subgraphs, Turbo, x402 pay-per-request. Hyperliquid, Elysium.

Instagram MCP Server

HasData

Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.