gdelt-mcp
by ledgerW
Overview
Model Context Protocol server providing AI agents with access to GDELT 2.0 (Global Database of Events, Language, and Tone) via Google BigQuery for cost-optimized querying.
Installation
uv run python server.pyEnvironment Variables
- GCP_PROJECT_ID
- GCP_PRIVATE_KEY
- GCP_CLIENT_EMAIL
Security Notes
The server directly interpolates user-provided `where_clause` and `select_fields` parameters into BigQuery SQL queries without explicit sanitization or parameterization. This creates a significant SQL Injection vulnerability. While the server is designed to use client-provided BigQuery credentials (limiting direct harm to the server operator's own project if they are not used), if the server falls back to environment variable credentials, a malicious client could exploit this to execute arbitrary BigQuery SQL against the server's configured GCP project. This makes the server unsafe to run in environments with untrusted inputs.
Similar Servers
mcp-servers
An MCP server for managing files in Google Cloud Storage, supporting CRUD operations (save, get, search, delete) and exposing files as resources.
google-maps-mcp-server
Empower AI agents with real-time Google Maps location intelligence (directions, places, geocoding, traffic, roads, elevation, safety) through a standardized Model Context Protocol (MCP) interface.
mcp
Integrate Google Gemini API features (text generation, chat, image analysis, web search, embeddings, image/video generation) into a Model Context Protocol (MCP) server for local or remote AI client applications.
gcal-mcp
Serves as a Model Context Protocol (MCP) server for Google Calendar to query upcoming, date-specific, and searchable events.