Ollama MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| listB | List all models in Ollama |
| showC | Show information for a model |
| createB | Create a model from a base model (remote only, no Modelfile support) |
| pullC | Pull a model from a registry |
| pushC | Push a model to a registry |
| cpD | Copy a model |
| rmD | Remove a model |
| runC | Run a model with a prompt. Optionally accepts an image file path for vision/multimodal models and a temperature parameter. |
| chat_completionC | OpenAI-compatible chat completion API. Supports optional images per message for vision/multimodal models. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have distinct purposes, but 'chat_completion' and 'run' could cause confusion as both involve generating responses from models. 'chat_completion' is for OpenAI-compatible API calls with optional images, while 'run' is for simpler prompts with temperature control, but the overlap in functionality might lead to misselection in some scenarios.
Naming is inconsistent with a mix of styles: 'chat_completion' uses snake_case, while others like 'cp', 'rm', and 'run' are abbreviated or single words, and 'list', 'pull', 'push', 'create', 'show' are simple verbs. There's no uniform pattern, making it harder to predict or remember tool names.
With 9 tools, the count is well-scoped for managing Ollama models, covering operations like listing, creating, copying, running, and removing models, as well as registry interactions. Each tool serves a clear purpose without bloat, fitting the server's domain effectively.
The tool set provides good coverage for model management, including CRUD-like operations (create, list, rm), registry actions (pull, push), and usage (run, chat_completion, show). A minor gap is the lack of update or modify tools for existing models, but agents can work around this by recreating or using other methods.