PubchemSearchQA (search_pubchem_qa)

Example 3

Input:

representation_name: 'Name'
representation: 'alcohol'
question: 'What properties do this molecule have?'

Text Input (used for the run_text function in the Python calling mode):

representation_name_and_representation_and_question: 'Name: alcohol   Questions: What properties do this molecule have?'

Output:

'This molecule has the following properties: [...]'

Usage

The tool supports both MCP mode and Python calling mode.

Environment Variables

This tool requires the following environment variables:

• LLM_MODEL_NAME: The name of the LLM to use. See LiteLLM for more details.
• Other LLM credentials are required to be set in the env field. See LiteLLM for more details.

MCP Mode

Configure your MCP client following its instructions with something like:

{
    "command": "/ABSTRACT/PATH/TO/uv",  // Use `which uv` to get its path
    "args": ["--directory", "/ABSTRACT/PATH/TO/ChemMCP", "run", "--tools", "PubchemSearchQA"],
    "toolCallTimeoutMillis": 300000,
    "env": {
        "LLM_MODEL_NAME": "VALUE_TO_BE_SET"
        // Add required LLM credentials
        // ...
    }
}

Python Calling Mode

import os
from chemmcp.tools import PubchemSearchQA

# Set the environment variables
os.environ['LLM_MODEL_NAME'] = 'VALUE_TO_BE_SET'
# Also add LLM credentials required by the LLM model, such as `OPENAI_API_KEY`

# Initialize the tool
tool = PubchemSearchQA()

# The tool has two alternative ways to run:
# 1. Run with separate input domains (recommended)
output = tool.run_code(
    representation_name='SMILES'
    representation='CCO'
    question='What properties do this molecule have?'
)
# 2. Run with text-only input
output = tool.run_text(
    representation_name_and_representation_and_question='SMILES: CCO   Questions: What properties do this molecule have?'
)

Each tool in ChemMCP has two ways to run:

• run_code (recommended): The inputs contain one or more domains, each of which can be a str, an int, a float, etc.
• run_text: The inputs are a single string in a specific format. The tool will parse the string to extract the input domains. This is useful in scenarios where an agent framework calls tools only with text input. The output is the same in both cases.

For the input and output domains, please refer to the tool’s signature.

Tool Signature

Input

Used in the MCP mode, as well as the run_code function in the Python calling mode.

Text Input

Used in the run_text function in the Python calling mode.

Output

The output is the same in both input cases.

Envs

Implementation Details

• Implementation Description: Uses the PubchemSearch tool to get the document of a molecule/compound from PubChem, and prompts an LLM to answer the related question.
• Open-source dependencies (code source or required libraries): None
• Hosted services and software (required for running the tool):
  • PubChem
  • Custom LLMs