Pubchem MCP Server

What does “Pubchem” MCP Server do?

The Pubchem MCP (Model Context Protocol) Server acts as a bridge between AI assistants and the PubChem API, enabling seamless extraction of basic chemical information about drugs. By integrating with this server, AI systems can automatically retrieve molecular details, synonyms, identifiers, and related metadata for chemical compounds directly from PubChem. This capability enhances development workflows in areas such as drug discovery, bioinformatics, and chemical informatics by automating data retrieval, reducing manual lookup efforts, and enabling advanced data-driven interactions within AI-powered environments. The server is designed for easy integration and can be used within various platforms and tools that support the MCP standard.

List of Prompts

No specific prompt templates are mentioned in the repository.

List of Resources

No explicit resources are listed in the repository.

List of Tools

No explicit tools are detailed in the repository’s server.py or visible documentation.

Use Cases of this MCP Server

• Automated Chemical Data Retrieval: Instantly fetch chemical properties, identifiers, and structural data for any drug or compound, streamlining research and development processes.
• Drug Information Lookup: Provide end-users or researchers with comprehensive details about known drugs, including synonyms, molecular formula, and links to PubChem entries.
• Integration into Bioinformatics Pipelines: Allow AI-driven pipelines to enhance their data context with authoritative chemical information for tasks such as drug repurposing or interaction analysis.
• Support for Educational Tools: Enable educational platforms to offer rich, real-time chemical information for teaching and demonstrations.
• API-Driven Applications: Back-end support for web or mobile applications that require up-to-date chemical data without manual API handling.

How to set it up

Windsurf

1. Prerequisites: Ensure Python 3.10 and dependencies (python-dotenv, requests, mcp, uvicorn) are installed.
2. Clone and Install:

   git clone https://github.com/sssjiang/pubchem_mcp_server.git
   cd pubchem_mcp_server
   pip install .
   

3. Edit Configuration: Open your Windsurf configuration and add the Pubchem MCP server:

   {
     "mcpServers": {
       "pubchem": {
         "command": "uvx",
         "args": ["pubchem_mcp_server"]
       }
     }
   }
   

4. Save and Restart: Save your changes and restart Windsurf.
5. Verify: Test by querying for a known drug.

Claude

1. Prerequisites: Install Python 3.10 and required packages.
2. Clone and Install:

   git clone https://github.com/sssjiang/pubchem_mcp_server.git
   cd pubchem_mcp_server
   pip install .
   

3. Configure Claude: Add to your Claude Desktop servers_config.json:

   {
     "mcpServers": {
       "pubchem": {
         "command": "uvx",
         "args": ["pubchem_mcp_server"]
       }
     }
   }
   

4. Restart Claude.
5. Verify: Query for a drug to confirm setup.

Cursor

1. Prerequisites: Python 3.10 and dependencies installed.
2. Clone and Install:

   git clone https://github.com/sssjiang/pubchem_mcp_server.git
   cd pubchem_mcp_server
   pip install .
   

3. Add MCP Server: Update Cursor’s configuration file:

   {
     "mcpServers": {
       "pubchem": {
         "command": "uvx",
         "args": ["pubchem_mcp_server"]
       }
     }
   }
   

4. Restart Cursor.
5. Test: Search for a known compound.

Cline

1. Prerequisites: Install Python 3.10 and dependencies.
2. Clone and Install:

   git clone https://github.com/sssjiang/pubchem_mcp_server.git
   cd pubchem_mcp_server
   pip install .
   

3. Edit Configuration: Add the following to your servers_config.json:

   {
     "mcpServers": {
       "pubchem": {
         "command": "uvx",
         "args": ["pubchem_mcp_server"]
       }
     }
   }
   

4. Restart Cline.
5. Verify Setup: Confirm by running a sample query.

Securing API Keys

No API keys are required for PubChem API access in the current setup. If needed, environment variables can be set as follows:

{
  "env": {
    "PUBCHEM_API_KEY": "your_api_key"
  },
  "inputs": {}
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "pubchem": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “pubchem” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the above, the Pubchem MCP Server is very focused on a specific domain (chemical/drug info), is easy to install, and integrates with MCP clients, but lacks documentation on prompts, resources, or advanced features like sampling or roots.

Our opinion

This MCP server is straightforward and functional for its intended purpose, but lacks broader MCP features and documentation that would make it more versatile for advanced users. Rating: 3/10.

MCP Score