mcp-pixabay
MCP server from zhangzhenfei/mcp-pixabay-server
claude mcp add --transport stdio zhangzhenfei-mcp-pixabay-server npx -y @sadais/mcp-pixabay-server \ --env PIXABAY_API_KEY="your_api_key_here"
How to use
The MCP Pixabay Server implements the Pixabay API as an MCP-compatible service, enabling AI models that support MCP to search and retrieve Pixabay images and videos. It exposes two core tools: search_images for querying image resources and search_videos for querying video resources. To start using it, run the MCP server (for example via the provided CLI) and then configure your MCP-aware model to call this service when it needs Pixabay results. The server expects a Pixabay API key, provided via the PIXABAY_API_KEY environment variable, and supports a range of search parameters such as keywords, image_type/orientation/category/colors, safesearch, and pagination for images; and video_type/category/safesearch for videos. When integrated, your model can request rich metadata including URLs, resolutions, and tags for matching resources.
How to install
Prerequisites:
- Node.js (LTS) and npm installed on your system
- Access to a Pixabay API key
Installation options:
- Global CLI installation (recommended for quick start)
npm install -g @sadais/mcp-pixabay-server
- Local project installation (for embedding in a project)
mkdir my-mcp-project
cd my-mcp-project
npm init -y
npm install @sadais/mcp-pixabay-server --save
Configure API key (example):
export PIXABAY_API_KEY=your_api_key_here
Run the server (CLI):
mcp-pixabay-server
Alternative invocation using npx (no global install):
npx -y @sadais/mcp-pixabay-server
Additional notes
Notes and tips:
- The server requires a valid Pixabay API key supplied via PIXABAY_API_KEY. Without it, requests will fail.
- When integrating with MCP-enabled AI models, you can reference the Pixabay endpoints in your mcp.json as shown in the README example to route search requests to this service.
- The MCP protocol uses stdio for communication during debugging. If you run into issues, consider using MCP Inspector tooling for debugging and monitoring.
- Ensure your environment has network access to Pixabay and that the API key has not exceeded rate limits.
- If you update to a newer version, re-check the environment variable names or any breaking changes in the MCP server's API surface.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.