Bio-Agents MCP: Integrate Data, Accelerate Discovery

Bio-Agents MCP unlocks life science insights—aggregate PDB, ChemBL, and more into local models, test rapidly via Ollama. (WIP)

Visit Repository

✨ Research And Data

4.1(180 reviews)

270 saves

125 comments

69% of users reported increased productivity after just one week

About Bio-Agents MCP

What is Bio-Agents MCP: Integrate Data, Accelerate Discovery?

Bio-Agents MCP is a modular platform designed to streamline interaction with biological data through natural language interfaces. It combines microservices and clients to connect researchers with critical resources like the Protein Data Bank (PDB) and ChEMBL chemical databases. By leveraging the FastMCP framework and asynchronous processing, it enables seamless querying of structural, chemical, and annotation data to accelerate scientific discovery.

How to Use Bio-Agents MCP: Integrate Data, Accelerate Discovery?

Getting started is straightforward:

Set up the environment: Copy the example configuration file and customize settings.
Launch services: Use Docker Compose to spin up all components with a single command.
Interact via UI or CLI: Access the web interface at localhost:8000 or use terminal commands to query data.

Advanced users can dive into module-specific documentation or extend functionality with custom APIs.

Bio-Agents MCP Features

Key Features of Bio-Agents MCP: Integrate Data, Accelerate Discovery?

Modular Architecture: Independent microservices for PDB, ChEMBL, and natural language processing allow scalable deployment.
Efficient Querying: Asynchronous processing minimizes latency when accessing large datasets.
Flexible Access: Dual interface support (web and CLI) caters to both casual users and script-driven workflows.
Robust Integration: Pre-configured Docker environments simplify deployment while maintaining customization options.

Use Cases for Bio-Agents MCP: Integrate Data, Accelerate Discovery?

Researchers and developers use this platform for:

Rapid analysis of protein structures and ligand interactions
Automated drug discovery workflows with chemical database queries
Building custom dashboards for real-time data visualization
Training machine learning models on standardized biological datasets

Bio-Agents MCP FAQ

FAQ from Bio-Agents MCP: Integrate Data, Accelerate Discovery?

How do I troubleshoot connection issues?: Verify Docker service status and check port mappings in the configuration file. Logs are accessible via docker-compose logs.
Can I add my own data sources?: Absolutely. The modular design allows integrating new APIs by extending the service framework and updating the query parser.
What languages are supported?: Primary support is for English queries, with plans to expand to other scientific terminology-rich languages.
Is there enterprise support?: Community forums are available, and commercial support packages can be arranged for large-scale deployments.

Content

Bio-Agents MCP

A collection of microservices and clients for natural language interaction with biological databases.

Components

LLM Client : Natural language interface with web UI and terminal modes
PDB MCP Server : Protein Data Bank API service
ChEMBL MCP Server : Chemical database API service

Architecture

┌─────────────┐     ┌──────────────┐
│   LLM UI    │     │  Ollama LLM  │
│  (Chainlit) │     │              │
└─────┬───────┘     └───────┬──────┘
      │                     │
┌─────┴─────────────────────┴──────┐
│           LLM Client             │
└─────┬─────────────────────┬──────┘
      │                     │
┌─────┴───────┐     ┌──────┴───────┐
│  PDB MCP    │     │  ChEMBL MCP  │
│   Server    │     │    Server    │
└─────────────┘     └──────────────┘

Quick Start

Configure environment:

cp .env.example .env

Start services:

make build
make up

Launch web interface:

make run-chainlit

Visit http://localhost:8000 to start querying biological data.

Development

Use make help to see available commands
Each service has its own README with detailed documentation
Configuration files are in conf/ directory

Description

This project contains multiple modules that interact with various services and APIs using the FastMCP framework. Each module is designed to perform specific tasks and can be run independently or together using Docker Compose. The primary focus of this project is on bio agents, providing tools and services to interact with biological data sources such as the Protein Data Bank (PDB).

Modules

LLM Client

The llm-client module provides a client that interacts with a Language Model (LLM) server to process queries and utilize available tools. It is built using the FastMCP framework and supports asynchronous operations with aiohttp.

For more details, refer to the LLM Client README.

Protein Data Bank

The protein_data_bank_mcp module provides a server that interacts with the Protein Data Bank (PDB) API to fetch structural assembly descriptions, chemical components, drugbank annotations, branched entities, non-polymer entities, polymer entities, uniprot annotations, structures, pubmed annotations, pdb cluster data aggregation, aggregation group provenance, pdb cluster data aggregation method, and pairwise polymeric interface descriptions. It is built using the FastMCP framework and supports asynchronous operations with aiohttp.

For more details, refer to the Protein Data Bank README.

Docker

Dockerfiles are provided for each module to build Docker images.

Build the Docker image:
```
docker build -t <module-name> .
```

Run the Docker container:

docker run --env-file .env <module-name>

Docker Compose

A docker-compose.yml file is provided to run all services together.

Start all services:
```
docker-compose up -d
```
Stop all services:
```
docker-compose down
```

Makefile

A Makefile is provided to simplify common tasks.

Available targets:
- setup-env: Set up the initial environment.
- build: Build all Docker images.
- up: Start all services using docker-compose.
- down: Stop all services using docker-compose.
- restart: Restart all services using docker-compose.