What it does

Bridge to a locally running Ollama or vLLM instance for pure language processing (writing, summarizing, classifying, structured extraction), without giving the calling agent tools or file access. pip install mcp-ollama-vllm

Local connectionPricing not confirmedv1.0.6

Connection manifest

Public connection metadata from the source. Follow the provider’s setup guide for authentication, permissions, and required variables.

{
  "name": "io.github.setheerwagen/mcp-ollama-vllm",
  "version": "1.0.6",
  "repository": {
    "url": "https://github.com/setheerwagen/local-ai-mcp-servers"
  },
  "remotes": [],
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "mcp-ollama-vllm",
      "version": "1.0.6",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "name": "LOCAL_BACKEND",
          "isRequired": false
        },
        {
          "name": "LOCAL_HOST",
          "isRequired": false
        },
        {
          "name": "LOCAL_API_KEY",
          "isRequired": false
        },
        {
          "name": "LOCAL_TIMEOUT",
          "isRequired": false
        },
        {
          "name": "LOCAL_EMBED_MODEL",
          "isRequired": false
        },
        {
          "name": "LOCAL_EMBED_PATH",
          "isRequired": false
        },
        {
          "name": "LOCAL_SCHEMA_MODE",
          "isRequired": false
        }
      ]
    }
  ]
}

Metadata reviewed for listing. Server code, permissions, and runtime behavior have not been security-audited. Directory access is free; individual providers may charge.