Connapse: MCP server, setup and security

What Connapse does

According to its repository: “Self-hosted knowledge backend for agents with hybrid vector and keyword search and container-isolated indexes.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Connapse is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #143 by stars.

Topics declared by the repository: blazor, dotnet, embeddings, hybrid-search, knowledge-management, ollama.

Installing and connecting Connapse

Distribution modes declared in the official MCP registry:

• Docker (OCI) image

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: C#. Listed systems: macOS, Windows, Linux.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Connapse. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on February 4, 2026, the Destrayon/Connapse repository has 21 stars and 6 forks, with 134 open issues. It has more stars than 39% of the servers in the directory. It received changes this month. Version published in the registry: 0.3.2 (March 14, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.