Ollama MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Server port | 3456 |
| OLLAMA_API | No | Ollama API endpoint | 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 |
|---|---|
| ollama_chatA | Chat with a model using conversation messages. Supports system messages, multi-turn conversations, tool calling, and generation options. |
| ollama_copyC | Copy a model. Creates a duplicate of an existing model with a new name. |
| ollama_createB | Create a new model with structured parameters. Allows customization of model behavior, system prompts, and templates. |
| ollama_deleteB | Delete a model from local storage. Removes the model and frees up disk space. |
| ollama_embedA | Generate embeddings for text input. Returns numerical vector representations. |
| ollama_generateA | Generate completion from a prompt. Simpler than chat, useful for single-turn completions. |
| ollama_listA | List all available Ollama models installed locally. Returns model names, sizes, and modification dates. |
| ollama_psB | List running models. Shows which models are currently loaded in memory. |
| ollama_pullB | Pull a model from the Ollama registry. Downloads the model to make it available locally. |
| ollama_pushB | Push a model to the Ollama registry. Uploads a local model to make it available remotely. |
| ollama_showA | Show detailed information about a specific model including modelfile, parameters, and architecture details. |
| ollama_web_fetchA | Fetch a web page by URL using Ollama's web fetch API. Returns the page title, content, and links. Requires OLLAMA_API_KEY environment variable. |
| ollama_web_searchA | Perform a web search using Ollama's web search API. Augments models with latest information to reduce hallucinations. Requires OLLAMA_API_KEY environment variable. |
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 13 tools
Each tool has a clearly distinct purpose: chat vs generate, list vs ps, copy/create/delete/pull/push for model management, embed for embeddings, show for details, web_fetch and web_search for web operations. No overlapping functionality.
All tools use the 'ollama_' prefix and generally follow a verb_noun pattern (chat, copy, create, etc.). Minor deviations: 'ps' is an abbreviation but standard, and 'web_fetch'/'web_search' place the noun first, but overall consistent.
13 tools is well-scoped for an Ollama server. Covers model management, text generation/chat, embeddings, and web augmentation without being excessive or sparse.
The tool set provides comprehensive CRUD for models, plus chat/generate, embeddings, and web search/fetch. No obvious gaps for the intended functionality.