list_modelsLABSCO SUMMARY
Three tools, one job: a local second opinion without switching apps.
The useful shape is delegation — ask the local model the part of a task that should not go to a hosted provider, and keep the rest of the conversation where it is. Everything depends on Ollama already running with a model pulled; if list_models comes back empty, that is the thing to fix rather than the server.
What it is
A small MCP server that connects an MCP client to a locally running Ollama installation. It reports the models you have pulled, returns the detail for one of them, and forwards a question to a named model — so a conversation in one client can consult a local model without leaving it.
What you get
- Every downloaded Ollama model listed —
list_models - Detailed information about a specific model —
show_model - A question put to a named model and its answer returned —
ask_model - Nothing leaves the machine: the models it talks to are the ones running in your own Ollama installation
Requirements
Ollama installed and running, with at least one model pulled — the README's example is ollama pull llama2. Python 3.10 or higher. The client runs it as uvx mcp-ollama, so uv needs to be present; the published package is mcp-ollama 0.1.3 with an mcp-ollama entry point over stdio. No account and no key.
Setup effort
One command — uvx mcp-ollama
USE CASES
01
Keeping one question on your own hardware
Send the sensitive part of a task to a local model and keep the rest of the conversation in your usual client.
02
Remembering what you have pulled
List the downloaded models and read the detail of one before deciding which to route work to.
03
Comparing a local answer with a hosted one
Put the same question to a local model and compare it against what the client's own model said, in the same thread.
3 tools
Listed in project docs. Your client may show a different list.
show_modelask_modelBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation. The documentation says four main tools but lists three: list_models, show_model and ask_model.
Requires
- uvx on PATH
- Python 3.10 or later
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mcp-ollamaMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"ollama": {
"command": "uvx",
"args": [
"mcp-ollama"
]
}
}
}
