Ollama MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_BASE_URL | No | Base URL for your Ollama instance | http://localhost:11434 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsA | List all available Ollama models |
| get_model_infoA | Get information about a specific model |
| chatC | Chat with an Ollama model |
| generateC | Generate text using an Ollama model |
| pull_modelB | Pull/download a model from Ollama |
| delete_modelB | Delete a model from Ollama |
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 6 tools
Tools are mostly distinct: model management (list, info, pull, delete) is clearly separated from inference (chat, generate). The only potential overlap is chat vs. generate, but chat is for multi-turn conversations while generate is for single completions, which is a standard distinction.
Most tools follow a verb_noun pattern (list_models, get_model_info, pull_model, delete_model), but chat and generate are single verbs without a noun object. This is a noticeable deviation, though the naming remains readable and understandable.
Six tools is well-scoped for an Ollama server, covering both model management and inference without unnecessary overlap or bloat. Each tool serves a clear purpose.
The toolset covers core lifecycle (list, info, pull, delete) and both chat and text generation. It lacks advanced features like model creation, copying, or embeddings, but these are not essential for basic Ollama interactions and can be added later.