Skip to main content
Glama
Ollama MCP Server

Ollama MCP Server

by NightTrek

Ollama MCP Server

🚀 A powerful bridge between Ollama and the Model Context Protocol (MCP), enabling seamless integration of Ollama's local LLM capabilities into your MCP-powered applications.

🌟 Features

Complete Ollama Integration

  • Full API Coverage: Access all essential Ollama functionality through a clean MCP interface

  • OpenAI-Compatible Chat: Drop-in replacement for OpenAI's chat completion API

  • Local LLM Power: Run AI models locally with full control and privacy

Core Capabilities

  • 🔄 Model Management

    • Pull models from registries

    • Push models to registries

    • List available models

    • Create custom models from Modelfiles

    • Copy and remove models

  • 🤖 Model Execution

    • Run models with customizable prompts

    • Chat completion API with system/user/assistant roles

    • Configurable parameters (temperature, timeout)

    • Raw mode support for direct responses

  • 🛠 Server Control

    • Start and manage Ollama server

    • View detailed model information

    • Error handling and timeout management

Related MCP server: Ollama MCP Server

🚀 Getting Started

Prerequisites

  • Ollama installed on your system

  • Node.js and npm/pnpm

Installation

  1. Install dependencies:

pnpm install
  1. Build the server:

pnpm run build

Configuration

Add the server to your MCP configuration:

For Claude Desktop:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ollama": {
      "command": "node",
      "args": ["/path/to/ollama-server/build/index.js"],
      "env": {
        "OLLAMA_HOST": "http://127.0.0.1:11434"  // Optional: customize Ollama API endpoint
      }
    }
  }
}

🛠 Usage Examples

Pull and Run a Model

// Pull a model
await mcp.use_mcp_tool({
  server_name: "ollama",
  tool_name: "pull",
  arguments: {
    name: "llama2"
  }
});

// Run the model
await mcp.use_mcp_tool({
  server_name: "ollama",
  tool_name: "run",
  arguments: {
    name: "llama2",
    prompt: "Explain quantum computing in simple terms"
  }
});

The run tool waits for Ollama to finish generation and returns the complete response as MCP text content. It requests stream: false; tokens are not streamed incrementally. Whitespace and empty responses are preserved. Ollama HTTP errors, connection failures, timeouts, and malformed responses are reported as MCP errors.

Chat Completion (OpenAI-compatible)

await mcp.use_mcp_tool({
  server_name: "ollama",
  tool_name: "chat_completion",
  arguments: {
    model: "llama2",
    messages: [
      {
        role: "system",
        content: "You are a helpful assistant."
      },
      {
        role: "user",
        content: "What is the meaning of life?"
      }
    ],
    temperature: 0.7
  }
});

Create Custom Model

await mcp.use_mcp_tool({
  server_name: "ollama",
  tool_name: "create",
  arguments: {
    name: "custom-model",
    modelfile: "./path/to/Modelfile"
  }
});

🔧 Advanced Configuration

  • OLLAMA_HOST: Configure custom Ollama API endpoint (default: http://127.0.0.1:11434)

  • Timeout settings for model execution (default: 60 seconds)

  • Temperature control for response randomness (0-2 range)

🤝 Contributing

Development checks

Run pnpm test to build the server and run the MCP regression tests (Node.js 20 or newer). The tests use a local stand-in executable and a mock Ollama HTTP API; Ollama and downloaded models are not required. CI runs the same checks on Linux and Windows with Node.js 20, 22, and 24.

Model-management arguments

Ollama CLI tools pass model names and Modelfile paths as literal arguments without a shell. Paths containing spaces do not need extra shell quotes. Shell expressions and environment variables in these arguments are not expanded; supply the actual path instead.

Contributions are welcome! Feel free to:

  • Report bugs

  • Suggest new features

  • Submit pull requests

📝 License

MIT License - feel free to use in your own projects!


Built with ❤️ for the MCP ecosystem

Available Tools

10 tools
chat_completionB

OpenAI-compatible chat completion API

Inputs: model (required), messages (required), temperature, timeout.

cpC

Copy a model

Inputs: source (required), destination (required).

createC

Create a model from a Modelfile

Inputs: name (required), modelfile (required).

listC

List models

Inputs: no named parameters.

pullC

Pull a model from a registry

Inputs: name (required).

pushC

Push a model to a registry

Inputs: name (required).

rmC

Remove a model

Inputs: name (required).

runC

Run a model

Inputs: name (required), prompt (required), timeout.

serveB

Start Ollama server

Inputs: no named parameters.

showC

Show information for a model

Inputs: name (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have distinct purposes, such as list, pull, push, rm, and show, which clearly target different operations on models. However, 'run' and 'chat_completion' could be confused, as both involve executing models, though 'chat_completion' is more specific to API interactions. Overall, the descriptions help clarify boundaries, but there is some overlap in execution-related tools.

    Naming Consistency3/5

    The naming is mixed with some inconsistencies: most tools use simple verb forms like list, pull, push, rm, run, and serve, which are consistent. However, 'chat_completion' uses snake_case and is more descriptive, while 'cp' and 'create' are shorter forms that deviate slightly. This creates a readable but not fully uniform pattern across all tools.

    Tool Count5/5

    With 10 tools, the count is well-scoped for managing Ollama models, covering essential operations like listing, creating, pulling, pushing, removing, running, and serving. Each tool serves a clear purpose in the model lifecycle, making the set comprehensive without being overwhelming or too sparse for the domain.

    Completeness5/5

    The tool set provides complete coverage for Ollama model management, including CRUD operations (create, list, rm), lifecycle actions (pull, push, run, serve), and informational tools (show, chat_completion). There are no obvious gaps; agents can perform all core workflows from model acquisition to execution and maintenance seamlessly.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables seamless integration between Ollama's local LLM models and MCP-compatible applications, supporting model management and chat interactions.
      13
      812 npm
      178
      AGPL 3.0
    • A
      license
      C
      quality
      D
      maintenance
      A bridge that integrates Ollama's local LLM capabilities into MCP-powered applications, enabling users to run, manage, and interact with AI models locally with full control and privacy.
      9
      518 npm
      6
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables MCP-compatible clients to access local or cloud LLMs, manage and run models, generate completions and embeddings, chat with tool/function support, and use web search/fetch through Ollama Cloud.
      812 npm
      AGPL 3.0