Knowledgebase
BioContextAI Knowledgebase MCP server for biomedical agentic AI
What is Knowledgebase?
Knowledgebase is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to biocontextai knowledgebase mcp server for biomedical agentic ai
BioContextAI Knowledgebase MCP server for biomedical agentic AI
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- BioContextAI Knowledgebase MCP server for biomedical agentic
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx knowledgebaseConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Knowledgebase
The BioContextAI Knowledgebase MCP server connects AI assistants to over 14 verified biomedical knowledge sources including bioRxiv, EuropePMC, Ensembl, AlphaFold DB, Reactome, STRING, and OpenTargets. It lets researchers ask natural language questions that are answered with data drawn directly from authoritative databases for genes, proteins, pathways, literature, and disease associations. This server is built for biomedical researchers and bioinformaticians who want AI agents that can reliably cite and retrieve scientific facts rather than hallucinate them.
Prerequisites
- Python 3.12 recommended (set via UV_PYTHON=3.12)
- uv package manager installed (https://docs.astral.sh/uv/)
- An MCP-compatible client such as Claude Desktop or VS Code with MCP support
- Internet access to reach the external biomedical APIs (KEGG is local-only for licensing reasons)
Install uv if not already present
The server is distributed as a Python package installable via uv. Install uv first.
curl -LsSf https://astral.sh/uv/install.sh | shAdd the server to Claude Desktop config
Edit your Claude Desktop configuration file to register the biocontext_kb server. On macOS this file is at ~/Library/Application Support/Claude/claude_desktop_config.json.
{
"mcpServers": {
"biocontext_kb": {
"command": "uvx",
"args": ["biocontext_kb@latest"],
"env": {
"UV_PYTHON": "3.12"
}
}
}
}Restart Claude Desktop
Quit and reopen Claude Desktop so it picks up the new MCP server entry.
Run in development mode (stdio) for testing
For local testing without a client, run in DEVELOPMENT mode over stdio.
export MCP_ENVIRONMENT=DEVELOPMENT
uvx biocontext_kbRun in production mode (HTTP) for remote access
Start the server in HTTP mode for integration with remote clients or Docker deployments.
export MCP_ENVIRONMENT=PRODUCTION
export PORT=8000
uvx biocontext_kbKnowledgebase Examples
Client configuration
Minimal Claude Desktop config to connect to the BioContextAI Knowledgebase MCP server using uvx.
{
"mcpServers": {
"biocontext_kb": {
"command": "uvx",
"args": ["biocontext_kb@latest"],
"env": {
"UV_PYTHON": "3.12"
}
}
}
}Prompts to try
Example research questions you can ask once the server is connected.
- "Search EuropePMC for recent papers on CRISPR base editing in 2024"
- "Fetch the AlphaFold structure prediction confidence for human TP53"
- "What pathways does BRCA1 participate in according to Reactome?"
- "Find STRING protein-protein interactions for EGFR"
- "Search bioRxiv for preprints on single-cell RNA sequencing pancreatic beta cells"Troubleshooting Knowledgebase
Rate limit errors from external APIs
Run the server locally rather than hosting it remotely. The README explicitly warns that remote hosting increases rate-limit risk and some sources like KEGG prohibit remote commercial hosting.
UV_PYTHON version mismatch causing install failure
Ensure Python 3.12 is available on your system or let uv install it automatically. Set UV_PYTHON=3.12 in the env block of your MCP config as shown in the installation guide.
KEGG data not accessible
KEGG integration is restricted to local use only due to licensing. If you need KEGG data, run the server locally. Commercial use or remote hosting of KEGG data is prohibited under their license terms.
Frequently Asked Questions about Knowledgebase
What is Knowledgebase?
Knowledgebase is a Model Context Protocol (MCP) server that biocontextai knowledgebase mcp server for biomedical agentic ai It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Knowledgebase?
Follow the installation instructions on the Knowledgebase GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Knowledgebase?
Knowledgebase works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Knowledgebase free to use?
Yes, Knowledgebase is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Knowledgebase Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Knowledgebase? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Knowledgebase in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Knowledgebase?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.