Destrayon/Connapse
by Various
Open-source, self-hosted knowledge backend for AI agents — hybrid search (vector + keyword), MCP server, 5 connectors, Docker-ready
MCP
Destrayon/Connapse
Added 1 June 2026
Overview
Destrayon/Connapse is an open-source, self-hosted knowledge backend for AI agents. It provides hybrid search combining vector and keyword methods, includes an MCP server, and comes with five connectors. The project is Docker-ready and written in C#.
Best for
Best for
Developers seeking a lightweight, self-hosted knowledge backend for AI agents with hybrid search capabilities
Use cases
- Deploy a self-hosted knowledge base for AI agents with hybrid search
- Integrate with MCP-compatible agents for retrieval-augmented generation
- Run a private document retrieval system using Docker
How to use
Install
docker-compose up -d Tools exposed
container_createcontainer_listcontainer_deletecontainer_statsupload_filebulk_uploadlist_filesget_documentdelete_filebulk_deletesearch_knowledge
Tested with
Claude Code, Claude Desktop, VS Code, Cursor
Example client config
{\n "mcpServers": {\n "connapse": {\n "transport": "streamable-http",\n "url": "http://localhost:5001/mcp",\n "headers": {\n "X-Agent-Api-Key": "YOUR_API_KEY"\n }\n }\n }\n} Notes
Destrayon/Connapse is an open-source, self-hosted knowledge backend for AI agents. It provides hybrid search combining vector and keyword methods, includes an MCP server, and comes with five connectors. The project is Docker-ready and written in C#.
13 stars on GitHub. Last updated 2026-05-30. Licensed MIT.
Use cases
- Deploy a self-hosted knowledge base for AI agents with hybrid search
- Integrate with MCP-compatible agents for retrieval-augmented generation
- Run a private document retrieval system using Docker
Pros
- Self-hosted ensures data privacy and control
- Hybrid search (vector + keyword) improves retrieval accuracy
- Docker-ready simplifies deployment and scaling
Cons
- Very small community with only 13 GitHub stars, limited support
- C# codebase may reduce contributor pool compared to Python or JavaScript
- Unclear documentation and feature completeness given early-stage project
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Self-hosted ensures data privacy and control
- Hybrid search (vector + keyword) improves retrieval accuracy
- Docker-ready simplifies deployment and scaling
Cons
- Very small community with only 13 GitHub stars, limited support
- C# codebase may reduce contributor pool compared to Python or JavaScript
- Unclear documentation and feature completeness given early-stage project
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.