Ollama / vLLM Bridge
Call your local Ollama or vLLM model over MCP with schema-validated JSON output
Open the source (opens github.com) https://github.com/setheerwagen/local-ai-mcp-servers
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: LOCAL_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.setheerwagen.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
mcp-ollama-vllm@1.0.6
From the server's entry in the official MCP Registry
Settings it asks for
LOCAL_BACKEND· Backend to use: ollama, vllm or openaiLOCAL_HOST· Model endpoint URL; must be local or on your own network. Required for the openai backendLOCAL_API_KEYsecret · Optional bearer token, openai backend only; sent as a header, never loggedLOCAL_TIMEOUT· Read timeout in secondsLOCAL_EMBED_MODEL· Default embedding modelLOCAL_EMBED_PATH· Optional, openai backend only: embedding endpoint pathLOCAL_SCHEMA_MODE· Optional, openai backend only: auto, response_format or none
Related
-
docker-android
MCP serversAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent
git clone https://github.com/budtmo/docker-android.git -
Deskdrop
MCP serversAndroid keyboard with local AI (Ollama, Whisper, MCP) or cloud (Gemini, Groq, OpenAI)
git clone https://github.com/SvReenen/Deskdrop.git -
ask-ollama
MCP serversBridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
@ask-llm/ollama-mcp@0.7.0 -
fish-bridge — Session Knowledge Graph
MCP serversCompresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
fish-bridge-mcp@0.1.3 -
cli-bridge-mcp
MCP serversOther AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.
cli-bridge-mcp@0.3.0 -
qsp-mcp
MCP serversQSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
qsp-mcp@0.1.1