degoog
Search engine aggregator with a comprehensive plugin/extension system
Degoog is a self-hosted search engine aggregator with an integrated MCP server that exposes search capabilities to AI assistants and LLM clients. The platform queries multiple search engines simultaneously and displays unified results while supporting custom engines, bang commands, and extensible plugins. Its MCP integration allows Claude, Cursor, and other AI clients to perform web searches through the aggregator's infrastructure. Designed as a modular alternative to SearXNG, degoog runs via Docker or natively and includes optional Valkey caching and PostgreSQL backends for high-traffic deployments.
Key Features
Use Cases
- 01Providing AI assistants with privacy-focused web search capabilities through MCP
- 02Running a self-hosted search aggregator for personal or team use without Google dependency
- 03Deploying a public search instance with custom engines and community plugins
- 04Integrating multi-source search results into Claude Code or Cursor workflows
- 05Building custom search transports using FlareSolverr or curl for bypass strategies
- 06Creating specialized search panels and query-triggered sidebar content
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
degoog — FAQ
What is degoog and what does it do?+
Degoog is a self-hosted search aggregator that queries multiple search engines and presents unified results. It includes an MCP server component that exposes search functionality to AI clients like Claude Desktop, Cursor, and llama.cpp.
How do I install degoog with MCP support?+
Use the mcp.yml docker-compose file from the docker-compose-examples directory to run both degoog and degoog-mcp together. Set DEGOOG_SETTINGS_PASSWORDS before exposing the instance publicly, as unlocked instances allow anyone to install code-executing extensions.
Which AI clients work with degoog's MCP server?+
The degoog-mcp server supports Claude Desktop, Cursor, and llama.cpp clients, as documented in the mcp.yml compose configuration. These clients can perform searches through the aggregator's MCP interface.
Do I need API keys to run degoog?+
No external API keys are required for basic operation. However, you should set DEGOOG_SETTINGS_PASSWORDS to protect your instance, especially when deploying publicly or enabling the MCP server.
Is degoog free to use?+
Yes, degoog is open-source software available on GitHub under a free license. You can self-host it using Docker, Podman, or natively with Bun, and several community members also offer public instances.
What backends does degoog support for production use?+
Degoog runs on SQLite by default for personal use. For high-traffic deployments, it supports Valkey for shared caching across replicas and PostgreSQL for scalable indexing with better concurrent write performance.
How do I install degoog?+
Open the source repository on GitHub and follow its README. degoog is a mcp server — MCP Agents Market links you directly to the official repo.
Is degoog free?+
degoog is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.