Skip to main content
Glama

Gen3 MCP Server

A Model Context Protocol (MCP) server for interacting with Gen3 data commons, with GraphQL query validation to reduce hallucinations.

Install and Configure

These instructions are for using the server in a chat client. For development, see Development.

# Clone the repository
git clone <repository-url>

# Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh

Create Gen3 credentials file

Create a file credentials.json containing your Gen3 API key:

{
  "api_key": "xxxx",
  "key_id": "xxxx"
}

Configure chat client

Example for Claude Desktop ~/.config/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gen3-mcp-server": {
      "command": "uvx",
      "args": [
        "--from", "/path/to/gen3-mcp",
        "gen3-mcp"
      ],
      "env": {
        "GEN3_CREDENTIALS_FILE": "/path/to/credentials.json",
        "GEN3_BASE_URL": "https://gen3.datacommons.io/",
        "GEN3_LOG_LEVEL": "INFO"
      }
    }
  }
}

Example Usage in chat client

Screenshot of Claude chat

Available Tools

The MCP server provides the following tools:

Schema Discovery Tools

  • get_schema_summary() - Get annotated overview of all entities and their relationships

  • get_schema_entity(entity) - Get detailed schema info about a specific entity including all fields

Query Building Tools

  • generate_query_template(entity_name, include_relationships=True, max_fields=20) - Generate safe query templates with validated fields

  • validate_query(query) - Validate GraphQL query syntax and field names against schema

Query Execution Tool

  • execute_graphql(query) - Execute validated GraphQL queries against the Gen3 data commons

Acknowledgments

Built with MCP (Model Context Protocol) and designed for Gen3 Data Commons.

Install Server
A
license - permissive license
A
quality
C
maintenance

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/delocalizer/gen3-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server