Ollama / vLLM Bridge MCP Server

by setheerwagenio.github.setheerwagen/mcp-ollama-vllmv1.0.2

Call your local Ollama or vLLM model over MCP with schema-validated JSON output

0Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active31d ago

Install Ollama / vLLM Bridge MCP server

claude mcp add ollama-vllm -e LOCAL_API_KEY='<local-api-key>' -- uvx mcp-ollama-vllm

{
  "mcpServers": {
    "ollama-vllm": {
      "command": "uvx",
      "args": [
        "mcp-ollama-vllm"
      ],
      "env": {
        "LOCAL_API_KEY": "<local-api-key>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "ollama-vllm": {
      "command": "uvx",
      "args": [
        "mcp-ollama-vllm"
      ],
      "env": {
        "LOCAL_API_KEY": "<local-api-key>"
      }
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "ollama-vllm": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-ollama-vllm"
      ],
      "env": {
        "LOCAL_API_KEY": "<local-api-key>"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "ollama-vllm": {
      "command": "uvx",
      "args": [
        "mcp-ollama-vllm"
      ],
      "env": {
        "LOCAL_API_KEY": "<local-api-key>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
LOCAL_BACKEND	—	—	Backend to use: ollama, vllm or openai
LOCAL_HOST	—	—	Model endpoint URL; must be local or on your own network. Required for the openai backend
LOCAL_API_KEY	—	yes	Optional bearer token, openai backend only; sent as a header, never logged
LOCAL_TIMEOUT	—	—	Read timeout in seconds
LOCAL_EMBED_MODEL	—	—	Default embedding model
LOCAL_EMBED_PATH	—	—	Optional, openai backend only: embedding endpoint path
LOCAL_SCHEMA_MODE	—	—	Optional, openai backend only: auto, response_format or none

Freshness

Active — last maintenance signal 31d ago. The newest of the signals below sets the band.

Last commit (default branch)
2026-09-08 · 31d ago · GitHub
Latest release
2026-09-08 · 31d ago · GitHub · v1.0.2
Package published
no data · npm/PyPI
Registry entry updated
2026-09-08 · 31d ago · official registry · v1.0.2

FAQ

›How do I install the Ollama / vLLM Bridge MCP server in Claude Code?

Run: claude mcp add ollama-vllm -e LOCAL_API_KEY='<local-api-key>' -- uvx mcp-ollama-vllm. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Ollama / vLLM Bridge require an API key?

Yes. It expects LOCAL_API_KEY, of which 1 is a secret.

›Can I use Ollama / vLLM Bridge as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Ollama / vLLM Bridge in the official MCP registry?

Yes, as io.github.setheerwagen/mcp-ollama-vllm.