Skip to main content
Glama
MCP Ollama Server

MCP Ollama Server

by emgeee

MCP Ollama

Un servidor de Protocolo de Contexto de Modelo (MCP) para integrar Ollama con Claude Desktop u otros clientes MCP.

Requisitos

  • Python 3.10 o superior

  • Ollama instalado y funcionando ( https://ollama.com/download )

  • Al menos un modelo extraído con Ollama (por ejemplo, ollama pull llama2 )

Configurar Claude Desktop

Agregue a su configuración de Claude Desktop ( ~/Library/Application Support/Claude/claude_desktop_config.json en macOS, %APPDATA%\Claude\claude_desktop_config.json en Windows):

{
  "mcpServers": {
    "ollama": {
      "command": "uvx",
      "args": [
        "mcp-ollama"
      ]
    }
  }
}

Desarrollo

Instalar en modo de desarrollo:

git clone https://github.com/yourusername/mcp-ollama.git
cd mcp-ollama
uv sync

Prueba con MCP Inspector:

mcp dev src/mcp_ollama/server.py

Related MCP server: MCP Ollama

Características

El servidor proporciona cuatro herramientas principales:

  • list_models - Lista todos los modelos de Ollama descargados

  • show_model - Obtener información detallada sobre un modelo específico

  • ask_model - Haz una pregunta a un modelo específico

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

3 tools
ask_modelA

Ask a question to a specific Ollama model

Args:
    model: Name of the model to use (e.g., 'llama2')
    question: The question to ask the model

Inputs: model (required), question (required).

list_modelsA

List all downloaded Ollama models

Inputs: no named parameters.

show_modelA

Get detailed information about a specific model

Args:
    name: Name of the model to show information about

Inputs: name (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap. 'ask_model' queries a model, 'list_models' enumerates available models, and 'show_model' provides metadata about a specific model. An agent can easily distinguish between these three distinct operations.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using snake_case. 'ask_model', 'list_models', and 'show_model' maintain perfect naming consistency throughout the set, making them predictable and readable.

    Tool Count3/5

    With only 3 tools, the server feels somewhat thin for interacting with Ollama models. While the tools cover basic operations, additional functionality like model management (e.g., pull, delete) or conversation history would be expected for a more complete surface.

    Completeness4/5

    The tools provide good coverage for core Ollama interactions: querying models, listing them, and getting details. However, there are minor gaps in model management operations (e.g., pulling new models, deleting models) that agents might need to work around for full lifecycle coverage.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables seamless integration between Ollama's local LLM models and MCP-compatible applications, supporting model management and chat interactions.
      13
      817 npm
      180
      AGPL 3.0
    • 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.
      817 npm
      AGPL 3.0