WebSearch (search_web)

Example

Input:

query: 'What is the boiling point of water?'

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

query: 'What is the boiling point of water?'

Output:

'The boiling point of water at sea level is 100°C (212°F).'

Usage

The tool supports both MCP mode and Python calling mode.

Environment Variables

This tool requires the following environment variables:

• TAVILY_API_KEY: The API key for Tavily.

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", "WebSearch"],
    "toolCallTimeoutMillis": 300000,
    "env": {
        "TAVILY_API_KEY": "VALUE_TO_BE_SET"
    }
}

Python Calling Mode

import os
from chemmcp.tools import WebSearch

# Set the environment variables
os.environ['TAVILY_API_KEY'] = 'VALUE_TO_BE_SET'

# Initialize the tool
tool = WebSearch()

# The tool has two alternative ways to run:
# 1. Run with separate input domains (recommended)
output = tool.run_code(
    query='What is the boiling point of water?'
)
# 2. Run with text-only input
output = tool.run_text(
    query='What is the boiling point of water?'
)

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 Tavily API to search the web for any questions and knowledge and obtain a concise answer based on the search results.
• Open-source dependencies (code source or required libraries): None
• Hosted services and software (required for running the tool):
  • Tavily