mcp-ollama-vllm is an open-source MCP server that connects applications to locally hosted Ollama or vLLM language models. It supports language tasks and validates generated JSON against schemas using a dependency-free validator for developers building self-hosted AI workflows.
In the Frameworks & runtimes space, mcp-ollama-vllm takes a focused approach. It focuses on running local language models through a standardized MCP server while producing schema-validated JSON output. It is built as an open-source project for developers building local AI and MCP integrations. mcp-ollama-vllm is open source under the MIT license. It ships for the command line and API, 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. Among its 8 catalogued features are MCP server, ollama support, and vLLM support. 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