Exa Websets

Model Context Protocol (MCP) server for Exa's Websets API - create and manage AI-powered web search collections

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "adamanz-exa-websets-mcp": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "EXA_API_KEY": "your-exa-api-key-here"
      }
    }
  }
}

You have an MCP server that lets you create and manage Exa Websets for AI-powered web search and data collection. It exposes a simple local or HTTP interface you can connect to with MCP clients, enabling rapid webset creation, retrieval, and templated setups.

How to use

Start by running the server locally. It uses STDIO transport by default for interactions from your local tools, and you can switch to HTTP transport for web deployments.

To run locally with STDIO transport, use the Python entry point and point MCP clients at the standard input/output streams.

python server.py

To run with HTTP transport so your MCP client can reach it over HTTP, start the server withexplicit transport and port settings.

python server.py --transport http --port 8000

Once the server is running, you can perform actions such as creating a new webset, retrieving a webset by its ID, or listing all websets using your MCP client. The server exposes a straightforward set of endpoints for these operations and supports predefined templates for common webset types.

How to install

Prerequisites you need before installing are a Python environment and a working Exa API key. Install the required dependencies and prepare your environment, then start the server.

# 1) Install Python if you do not have it
# 2) Clone or download the MCP server package
# 3) Install dependencies
pip install -r requirements.txt
# 4) Set your Exa API key as an environment variable
export EXA_API_KEY="your-exa-api-key-here"

Run the server after installing dependencies and setting your API key.

Configuration and run notes

Environment variables are used to configure access to Exa’s Websets API. At minimum, you need to provide your API key.

export EXA_API_KEY="your-exa-api-key-here"

To run in local development with STDIO transport, start the server with the standard Python command. For web deployments, switch to HTTP transport and specify a port.

Tools and capabilities

The MCP server provides tools to manage Exa Websets, including creating new websets, retrieving specific websets, listing all websets, and quick templates for common webset types.

Security and notes

Keep your API key secure. Do not expose it in public logs or shared configuration. Use environment variable management practices to protect keys in production.

Troubleshooting

If the server fails to start, ensure you have Python installed, dependencies are installed, and EXA_API_KEY is set correctly. Check that the chosen port is not in use when using HTTP transport.

Available tools

create_webset

Create a new webset with a custom search query and optional parameters such as count, entity type, external_id, and metadata.

get_webset

Retrieve information about a specific webset by its unique ID.

list_websets

List all websets available in your account.

create_marketing_agencies_webset

Quick template to create a webset for marketing agencies with location, focus, and count defaults.

create_tech_companies_webset

Quick template to create a webset for tech companies with location, stage, and count defaults.