{"name":"io.github.setheerwagen/mcp-ollama-vllm","slug":"setheerwagen-mcp-ollama-vllm","title":"Ollama / vLLM Bridge","description":"Call your local Ollama or vLLM model over MCP with schema-validated JSON output","url":"https://mcp.market/server/setheerwagen-mcp-ollama-vllm","rating":null,"grade":"B","score":80,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":26,"stars":0,"forks":0,"downloads_week":148,"last_push_at":"2026-10-13T13:11:09.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"pypi","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/setheerwagen/local-ai-mcp-servers","website":null,"version":"1.0.6","remotes":[],"packages":[{"registryType":"pypi","identifier":"mcp-ollama-vllm","version":"1.0.6","transport":{"type":"stdio"},"environmentVariables":[{"description":"Backend to use: ollama, vllm or openai","format":"string","default":"ollama","name":"LOCAL_BACKEND"},{"description":"Model endpoint URL; must be local or on your own network. Required for the openai backend","format":"string","name":"LOCAL_HOST"},{"description":"Optional bearer token, openai backend only; sent as a header, never logged","format":"string","isSecret":true,"name":"LOCAL_API_KEY"},{"description":"Read timeout in seconds","format":"number","default":"600","name":"LOCAL_TIMEOUT"},{"description":"Default embedding model","format":"string","default":"nomic-embed-text","name":"LOCAL_EMBED_MODEL"},{"description":"Optional, openai backend only: embedding endpoint path","format":"string","default":"/v1/embeddings","name":"LOCAL_EMBED_PATH"},{"description":"Optional, openai backend only: auto, response_format or none","format":"string","default":"auto","name":"LOCAL_SCHEMA_MODE"}]}],"tools":[],"scan":null,"grade_history":[],"reviews":[]}