cyanheads/protein-mcp-server

🛠️ Tools Overview & Roadmap

This server provides a powerful suite of tools for accessing and analyzing protein structure data.

protein_search_structures

Search and discover protein structures from the Protein Data Bank (PDB) using a wide range of criteria.

Key Features:

• Free-text search for protein names, keywords, or PDB IDs.
• Filter by source organism, experimental method, and resolution.
• Pagination support for navigating large result sets.
• Returns rich metadata including title, organism, method, and resolution.

Example Use Cases:

• "Find all human kinase structures with resolution better than 2.0 Å"
• "Show me all cryo-EM structures of the SARS-CoV-2 spike protein"
• "List structures of hemoglobin from Escherichia coli"

protein_get_structure

Retrieve detailed information for specific protein structures by their PDB ID.

Key Features:

• Fetch single or multiple structures by their 4-character PDB ID.
• Choose between different data formats: mmCIF (default), PDB, PDBML, or JSON.
• Selectively include or exclude 3D coordinates, experimental data, and functional annotations.
• Provides access to atomic coordinates, chain information, and experimental details like R-factors and unit cell parameters.

Example Use Cases:

• "Get the full structure data for PDB ID 1ABC in mmCIF format"
• "Show me the metadata and chain information for 2GBP, but exclude the coordinates"
• "What were the experimental method and resolution for structure 6M0J?"

protein_compare_structures

Compare and contrast multiple protein structures to analyze conformational changes and structural relationships.

Key Features:

• Side-by-side comparison of 2 to 10 structures.
• Utilizes standard alignment algorithms like CEAlign and TM-Align.
• Calculates key metrics including RMSD, TM-score, and sequence identity.
• Can optionally generate a visualization script for PyMOL or ChimeraX.

Example Use Cases:

• "Compare the active site conformations of HIV protease in structures 1HVR and 1HVS"
• "Align structures 2GBP and 3AXO and report the RMSD"
• "Analyze the conformational differences between the open and closed states of a protein"

protein_find_similar

Discover structurally or sequentially related proteins based on a query.

Key Features:

• Similarity search by sequence (like BLAST) or structure (like DALI).
• Use a PDB ID, a FASTA sequence, or raw structure data as the query.
• Set thresholds for sequence identity, E-value, TM-score, or RMSD to refine results.
• Identifies homologous proteins, recognizes structural folds, and supports evolutionary analysis.

Example Use Cases:

• "Find proteins structurally similar to PDB ID 1ABC"
• "What proteins have a sequence identity greater than 90% to this FASTA sequence?"
• "Discover other proteins with a similar fold to my query structure"

protein_track_ligands

Identify protein structures that bind to specific small molecules, such as drugs, inhibitors, or cofactors.

Key Features:

• Search for ligands by common name, chemical ID, or SMILES string.
• Filter results by the bound protein's name, organism, or experimental method.
• Optionally include details of the binding site, including interacting residues.
• Essential for drug discovery, pharmacology, and molecular docking workflows.

Example Use Cases:

• "Find all human protein structures that bind to ATP"
• "Show me structures of Cyclin-dependent kinase 2 in complex with an inhibitor"
• "What are the binding site residues for glucose in hexokinase?"

protein_analyze_collection

Perform statistical analysis on the entire Protein Data Bank to uncover trends and distributions.

Key Features:

• Aggregate data based on fold classification, function, organism, or experimental method.
• Apply filters to narrow the analysis to specific subsets of the database.
• Group results by a secondary dimension (e.g., year) to visualize trends over time.

Example Use Cases:

• "What are the most common structural folds found in membrane proteins?"
• "Show a yearly trend of the number of structures determined by cryo-EM"
• "Which organisms are most represented in the PDB for the years 2020-2023?"

✨ Features

This server is built on the mcp-ts-template and inherits its rich feature set:

• Declarative Tools: Define agent capabilities in single, self-contained files. The framework handles registration, validation, and execution.
• Robust Error Handling: A unified McpError system ensures consistent, structured error responses.
• Pluggable Authentication: Secure your server with zero-fuss support for none, jwt, or oauth modes.
• Abstracted Storage: Swap storage backends (in-memory, filesystem, Supabase, Cloudflare KV/R2) without changing business logic.
• Full-Stack Observability: Deep insights with structured logging (Pino) and optional, auto-instrumented OpenTelemetry for traces and metrics.
• Dependency Injection: Built with tsyringe for a clean, decoupled, and testable architecture.
• Edge-Ready: Write code once and run it seamlessly on your local machine or at the edge on Cloudflare Workers.

🚀 Getting Started

MCP Client Settings/Configuration

Add the following to your MCP Client configuration file (e.g., cline_mcp_settings.json).

{
  "mcpServers": {
    "protein-mcp-server": {
      "command": "bunx",
      "args": ["protein-mcp-server@latest"],
      "env": {
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Prerequisites

• Bun v1.2.0 or higher.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/protein-mcp-server.git

2. Navigate into the directory:

cd protein-mcp-server

3. Install dependencies:

bun install

⚙️ Configuration

All configuration is centralized and validated at startup in src/config/index.ts. Key environment variables in your .env file include:

▶️ Running the Server

Local Development

• Build and run the production version:

  # One-time build
  bun rebuild
  
  # Run the built server
  bun start:http
  # or
  bun start:stdio
  

• Run checks and tests:

  bun devcheck # Lints, formats, type-checks, and more
  bun test # Runs the test suite
  

Cloudflare Workers

1. Build the Worker bundle:

bun build:worker

2. Run locally with Wrangler:

bun deploy:dev

3. Deploy to Cloudflare: sh bun deploy:prod > Note: The wrangler.toml file is pre-configured to enable nodejs_compat for best results.

📂 Project Structure

🧑‍💻 Agent Development Guide

For a strict set of rules when using this template with an AI agent, please refer to AGENTS.md. Key principles include:

• Logic Throws, Handlers Catch: Never use try/catch in your tool/resource logic. Throw an McpError instead.
• Use Elicitation for Missing Input: If a tool requires user input that wasn't provided, use the elicitInput function from the SdkContext to ask the user for it.
• Pass the Context: Always pass the RequestContext object through your call stack.
• Use the Barrel Exports: Register new tools and resources only in the index.ts barrel files.

🤝 Contributing

Issues and pull requests are welcome! If you plan to contribute, please run the local checks and tests before submitting your PR.

bun run devcheck
bun test

📜 License

This project is licensed under the Apache 2.0 License. See the file for details.