Skip to main content
Glama
timscodebase

Ollama MCP Server

by timscodebase
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_HOSTNoOllama server URL (default: http://localhost:11434)http://localhost:11434
OLLAMA_API_KEYNoRequired for cloud models and web search/fetch functionality

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
web_searchA
    Perform a web search using Ollama's hosted search API.
    
    Requires OLLAMA_API_KEY environment variable to be set.

    Args:
        query: The search query to run.
        max_results: Maximum results to return (default: 3, max: 20).

    Returns:
        JSON-serializable dict with search results including titles, URLs, and content snippets.
web_fetchA
    Fetch the content of a web page for the provided URL.
    
    Requires OLLAMA_API_KEY environment variable to be set.

    Args:
        url: The absolute URL to fetch.

    Returns:
        JSON-serializable dict with page title, content, and links.
chat_completionB
    Generate a chat completion using Qwen3-coder (cloud preferred, local fallback).

    Args:
        messages: List of message objects with 'role' and 'content' keys.
        model: Optional model override (default: auto-selected best available).
        temperature: Sampling temperature (0.0 to 2.0, default: 0.7).
        max_tokens: Maximum tokens to generate.
        **kwargs: Additional parameters for the chat API.

    Returns:
        JSON-serializable dict with the model response.
get_available_modelsA
    Get information about available models and current configuration.

    Returns:
        JSON-serializable dict with model availability information.
search_and_chatA
    Perform web search and then generate a response based on the search results.
    
    This is a convenience tool that combines web_search and chat_completion.
    Requires OLLAMA_API_KEY environment variable to be set for web search.

    Args:
        query: The search query and question to answer.
        search_results: Number of search results to include (default: 3).
        model: Optional model override.
        temperature: Sampling temperature for chat completion.

    Returns:
        JSON-serializable dict with search results and AI response.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation4/5

Most tools have clear boundaries: web_search finds pages, web_fetch retrieves a specific URL, chat_completion generates responses, and search_and_chat explicitly combines search and chat. The main ambiguity is between chat_completion and search_and_chat, but their descriptions make the distinction clear.

Naming Consistency3/5

Naming is readable and consistent in style (snake_case), but lacks a unifed verb_noun pattern: web_search/web_fetch share a prefixed verb, get_available_models uses get_, chat_completion is a bare noun phrase, and search_and_chat is a compound verb. This is mixed but not chaotic.

Tool Count5/5

Five tools is a well-scoped size for a search-and-chat helper. Each tool has a discernible purpose and none feels redundant.

Completeness4/5

The core workflows—web search, page fetching, listing models, plain chat, and search-grounded chat—are all covered. Missing Ollama-specific operations like embedding generation or model management, but those feel like minor gaps given the server's apparent focus.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources