# OraFabric Medical Ontology Knowledge Base

OraFabric Medical Ontology Knowledge Base is an MCP server for Claude Code that retrieves biomedical research evidence and compares claims about relationships.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: OraFabric
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/OraFabric/medical-ontology-mcp-examples
- Updated: 2026-11-08
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/orafabric-medical-ontology-knowledge-base

## What it does

The server returns structured material from a biomedical graph, including claims, links, paper excerpts and evidence strength. An agent can search for findings on a question, inspect evidence for and against a relationship, explore related concepts, or retrieve the paper behind a finding.

An OraFabric API key is required. Calls to `retrieve_evidence`, `check_relation`, `explore_concept` and `get_paper` cost $0.03 each; `resolve_concept` and `get_coverage` are free. Clients connect to `https://orafabric.com/api/dev/mcp` over HTTP with an `Authorization` header. The graph currently focuses on oncology, so queries outside that area can return sparse or empty results.

This is a retrieval layer, not a chat model; the connected LLM writes the response. Extracted findings can be attributed to the wrong paper content, and the returned source sentence lets the result be checked.

## Requirements
- Remote server: `https://orafabric.com/api/dev/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http orafabric-medical-ontology-knowledge-base https://orafabric.com/api/dev/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add orafabric-medical-ontology-knowledge-base --url https://orafabric.com/api/dev/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "orafabric-medical-ontology-knowledge-base": {
            "url": "https://orafabric.com/api/dev/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "orafabric-medical-ontology-knowledge-base": {
            "type": "http",
            "url": "https://orafabric.com/api/dev/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http orafabric-medical-ontology-knowledge-base https://orafabric.com/api/dev/mcp
```

## When to use it
- retrieve papers and source passages for a biomedical question
- compare evidence supporting and opposing a medical relationship
- trace links between a gene, drug or disease in the graph
- map a concept name to its graph node

## Example prompts
- Find evidence on resistance mechanisms for KRAS G12C inhibitors and show the sources and strength of each finding.
- Check evidence for and against a direct link between lactate and CD8+ T-cell exhaustion.
- Explore graph connections between EGFR and resistance mechanisms.

## Similar
- [Knowledge Base Manager](https://affpapa.org/en/nevibecode/skills/knowledge-base-manager.md) — skill · 443 installs
- [medical-imaging-review](https://affpapa.org/en/nevibecode/skills/medical-imaging-review.md) — skill · 695 installs
- [Scientific Paper Research](https://affpapa.org/en/nevibecode/agents/scientific-paper-research.md) — subagent · ★ 41430 repo stars
- [firecrawl-knowledge-base](https://affpapa.org/en/nevibecode/skills/firecrawl-knowledge-base.md) — skill · 33100 installs
- [Hivebook - The Knowledge Base for AI Agents](https://affpapa.org/en/nevibecode/mcp/hivebook-the-knowledge-base-for-ai-agents.md) — MCP server · 776 installs
- [Psychedelics Knowledge Graph](https://affpapa.org/en/nevibecode/mcp/psychedelics-knowledge-graph.md) — MCP server · ★ 6 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
