drio
Open app

ollama-MCP-server

Source

Catalog onlyCatalog onlySTDIO

Overview

The ollama-MCP-server is a Model Context Protocol (MCP) server that facilitates seamless integration between local Ollama LLM instances and MCP-compatible applications, providing advanced task decomposition, evaluation, and workflow management.

To use the ollama-MCP-server, install it via pip, configure your environment variables, and run the server. You can then interact with it using various tools to manage tasks and evaluate results.

  • Task decomposition for complex problems - Result evaluation and validation - Management and execution of Ollama models - Standardized communication via MCP protocol - Advanced error handling with detailed messages - Performance optimizations like connection pooling and LRU caching
  1. Decomposing complex tasks into manageable subtasks.
  2. Evaluating task results against specified criteria.
  3. Running queries on Ollama models for various applications.

Add to your AI client

Use these steps to connect ollama-MCP-server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "ollama-mcp-server-newaitees": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ollama-mcp-server-newaitees"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "ollama-mcp-server-newaitees": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ollama-mcp-server-newaitees"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "ollama-mcp-server-newaitees": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ollama-mcp-server-newaitees"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "ollama-mcp-server-newaitees": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ollama-mcp-server-newaitees"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ollama-mcp-server-newaitees": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ollama-mcp-server-newaitees"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "ollama-mcp-server-newaitees": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-ollama-mcp-server-newaitees"
      ]
    }
  }
}

FAQ

What is the purpose of the ollama-MCP-server?

It serves as a bridge between local Ollama LLM instances and applications using the MCP protocol, enhancing task management and evaluation.

How do I install the ollama-MCP-server?

You can install it using pip with the command `pip install ollama-mcp-server`.

Can I customize the server settings?

Yes, you can adjust performance-related settings in the `config.py` file.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":1859,"uuid":"8c4d221b-913b-473b-8c7f-176d024517b2","name":"ollama-MCP-server","title":"ollama-MCP-server","description":"","avatar_url":"https://avatars.githubusercontent.com/u/200696569?v=4","created_at":"2025-03-05T05:43:56.980Z","updated_at":"2025-03-12T10:21:16.561Z","status":"created","author_name":"NewAITees","author_avatar_url":"https://avatars.githubusercontent.com/u/200696569?v=4","tags":"ollama,MCP,server","category":"developer-tools","is_featured":false,"sort":1,"url":"https://github.com/NewAITees/ollama-MCP-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"0\",\"license\":\"\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-03-03 08:19:44\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

ollama-MCP-server — MCP Registry