-
securityF
license-
qualityThis MCP server provides tools to interact with the Salesforce Agentforce API, allowing authentication, session creation, and message exchange with Salesforce agents.
Last updated -
11
The Explorium AgentSource MCP Server enables AI assistants to access Explorium's extensive business and prospects databases, providing accurate, up-to-date information directly in chat interfaces.
Key capabilities:
Business Intelligence: Find and match businesses by name, domain, or filter by size, revenue, location, industry, tech stack, and other criteria
Business Enrichment: Access detailed firmographics, technographics, financial metrics, funding history, strategic insights, competitive landscape, and workforce trends
Prospect Discovery: Find individuals by email, name, company, LinkedIn profile, phone number, job level, title, department, location, and experience
Prospect Enrichment: Retrieve contact information, work history, education details, and LinkedIn posts
Event Tracking: Monitor business events (funding rounds, IPOs, partnerships, office changes) and prospect events (role changes, company transitions, work anniversaries)
Analytics: Access business statistics with aggregated insights by industry, revenue, employee count, and geography
Search Assistance: Autocomplete available values for search filters before performing searches
Provides repository access for cloning the project code
Supports deploying the package to PyPI for distribution
Explorium API MCP Server
The Explorium MCP Server is a Model Context Protocol server used to interact with the Explorium API. It enables AI assistants to access Explorium's business and prospect data lookup capabilities.
📋 Table of Contents
Overview
The Explorium MCP Server allows AI assistants to access the extensive business and prospects databases from Explorium. This enables AI tools to provide accurate, up-to-date information about companies, industries, and professionals directly in chat interfaces.
Installation
Install the Explorium MCP Server from PyPI:
pip install explorium-mcp-server
The package requires Python 3.10 or later.
Setup for Development
Clone the repository:
git clone https://github.com/explorium-ai/mcp-explorium.git
cd mcp-explorium
Set up the development environment using
uv:
# Install uv if you don't have it
pip install uv
# Create and activate the virtual environment with all development dependencies
uv sync --group dev
Create a
.envfile in the root directory with your Explorium API key:
EXPLORIUM_API_KEY=your_api_key_here
To obtain an API key, follow the instructions in the Explorium API documentation.
Running Locally
mcp dev local_dev_server.py
Usage with AI Assistants
Usage with Claude Desktop
Follow the official Model Context Protocol guide to install Claude Desktop and set it up to use MCP servers.
Add this entry to your
claude_desktop_config.jsonfile:
{
"mcpServers": {
"Explorium": {
"command": "<PATH_TO_UVX>",
"args": [
"explorium-mcp-server"
],
"env": {
"EXPLORIUM_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
For development, you can use this configuration instead:
{
"mcpServers": {
"Explorium": {
"command": "<UV_INSTALL_PATH>",
"args": [
"run",
"--directory",
"<REPOSITORY_PATH>",
"mcp",
"run",
"local_dev_server.py"
],
"env": {
"EXPLORIUM_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
Replace all placeholders with your actual paths and API key.
Usage with Cursor
Cursor has built-in support for MCP servers.
To configure it to use the Explorium MCP server:
Go to
Cursor > Settings > Cursor Settings > MCPAdd an "Explorium" entry with this command:
For development, use:
uv run --directory <repo_path> mcp run local_dev_server.py
You may turn on "Yolo mode" in Cursor settings to use tools without confirming under
Cursor > Settings > Cursor Settings > Features > Chat > Enable Yolo mode.
Project Structure
mcp-explorium/
├── .github/workflows/ # CI/CD configuration
│ └── ci.yml # Main CI workflow
├── src/ # Source code
│ └── explorium_mcp_server/
│ ├── __init__.py # Package initialization
│ ├── __main__.py # Entry point for direct execution
│ ├── models/ # Data models and schemas
│ └── tools/ # MCP tools implementation
├── tests/ # Test suite
├── .env # Local environment variables (not in repo)
├── local_dev_server.py # Development server script
├── Makefile # Development shortcuts
├── pyproject.toml # Project metadata and dependencies
└── README.md # Project documentation
Development Workflow
Set up the environment as described in Setup for Development
Make your changes to the codebase
Format your code:
make format
Run linting checks:
make lint
Run tests:
make test
Continuous Integration
The project uses GitHub Actions for CI/CD. The workflow defined in .github/workflows/ci.yml does the following:
Version Check: Ensures the version in
pyproject.tomlis incremented before merging to mainLinting: Runs code style and formatting checks using
ruffTesting: Runs the test suite with coverage reporting
Deployment: Tags the repo with the version from
pyproject.tomlwhen merged to main
Building and Publishing
Building the Package
To build the package for distribution:
Update the version in
pyproject.toml(required for every new release)Run the build command:
uv build
This creates a dist/ directory with the built package.
Publishing to PyPI
To publish the package to PyPI:
Ensure you have
twineinstalled:
uv pip install twine
Upload the built package to PyPI:
twine upload dist/*
You'll need to provide your PyPI credentials or configure them in a .pypirc file.
Automatic Versioning and Tagging
When changes are merged to the main branch, the CI workflow automatically:
Tags the repository with the version from
pyproject.tomlPushes the tag to GitHub
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Explorium AgentSource MCP Server empowers every agent to become an AI-driven, Go-To-Market specialized agent! With over 20 specialized endpoints designed for prospecting, sales, and lead generation, agents can effortlessly generate and enrich accounts and prospects, access deep business insights, an
- 📋 Table of Contents
- Overview
- Installation
- Setup for Development
- Running Locally
- Usage with AI Assistants
- Project Structure
- Development Workflow
- Continuous Integration
- Building and Publishing
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityProfessional Gemini API integration for Claude and MCP-compatible hosts with intelligent model selection and advanced file handling capabilities.Last updated -43MIT License
- -securityFlicense-qualityAn MCP server that allows agents to interact with Meilisearch, a powerful open-source search engine, through its API using natural language.Last updated -
AgentOps MCPofficial
AsecurityFlicenseAqualityThe AgentOps MCP server provides access to observability and tracing data for debugging complex AI agent runs. This adds crucial context about where the AI agent succeeds or fails.Last updated -4186