mcp-modelmanager is an open-source MCP server for managing local Ollama and vLLM model machines through a secured two-channel SSH link. It exposes a closed catalog of remote operations for developers operating self-hosted AI infrastructure.
In the Frameworks & runtimes space, mcp-modelmanager takes a focused approach. It focuses on managing local Ollama or vLLM model machines securely without exposing unrestricted remote operations. mcp-modelmanager is an open-source project aimed at developers running self-hosted local AI infrastructure. mcp-modelmanager is open source under the MIT license. mcp-modelmanager is available on the command line, and it can be self-hosted.
It is developed by setheerwagen, and it first shipped in 2026. The project is developed in the open on GitHub with 2 commits in the last 90 days. Key capabilities include MCP server, ollama management, and vLLM management. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do