MCP MCP Server

Model Context Protocol server that proxies local Ollama to MCP clients like Windsurf and VS Code

Local serverstdioPython

What is the MCP MCP server?

MCP MCP server exists for a simple reason — assistants are far more useful when they can act on MCP directly instead of describing what you should do. Model Context Protocol server that proxies local Ollama to MCP clients like Windsurf and VS Code.

What you get

You can also wire this server into any MCP client (Windsurf, Cursor, Claude Desktop, etc.) without the extension — see Quick Start below.

What the assistant can call

Once MCP is connected, these are the calls the assistant has available:

  • DocsFull documentation
  • PyPImcp-ollama-python
  • ollama_chat — Chat with any local model (multi-turn, tool-calling)
  • ollama_generate — Generate text completions
  • ollama_embed — Create vector embeddings
  • ollama_list — List installed models
  • ollama_show — Inspect model details
  • ollama_pull — Download new models
  • ollama_delete — Remove models
  • ollama_ps — List running models
  • Guide — Description
  • Project — Role

Setting it up

The server ships on PyPI as mcp-ollama-python, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

You will need 2 environment variables: OLLAMA_HOST, OLLAMA_ALLOW_REMOTE_HOST. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP's toolset — Docs, PyPI, ollama_chat and 9 more — is a fair guide to whether it matches your workflow. It is maintained by Pedja Blagojevic; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
Docs[Full documentation](https://pblagoje.github.io/mcp-ollama-python/)
PyPI[mcp-ollama-python](https://pypi.org/project/mcp-ollama-python/)
ollama_chatChat with any local model (multi-turn, tool-calling)
ollama_generateGenerate text completions
ollama_embedCreate vector embeddings
ollama_listList installed models
ollama_showInspect model details
ollama_pullDownload new models
ollama_deleteRemove models
ollama_psList running models
GuideDescription
ProjectRole

How to install the MCP MCP server

{
  "mcpServers": {
    "ollama-python": {
      "command": "uvx",
      "args": ["mcp-ollama-python"],
      "env": {
        "OLLAMA_HOST": "your-value",
        "OLLAMA_ALLOW_REMOTE_HOST": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OLLAMA_HOSTEndpoint or connection string the server talks to.Optional
OLLAMA_ALLOW_REMOTE_HOSTEndpoint or connection string the server talks to.Optional

Example prompts to try

  • Use MCP to Docs.
  • Use MCP to PyPI.
  • Use MCP to ollama chat.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (Docs, PyPI, ollama_chat, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.