Ask Ollama runs on your own machine — the client starts it, so there is no endpoint to ping. 145 installs a week from npm. Last commit 3 Aug 2026.
Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ask-ollama -- npx -y @ask-llm/ollama-mcp
{
"mcpServers": {
"ask-ollama": {
"args": [
"-y",
"@ask-llm/ollama-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.ask-ollama]
command = "npx"
args = ["-y", "@ask-llm/ollama-mcp"]
{
"mcpServers": {
"ask-ollama": {
"args": [
"-y",
"@ask-llm/ollama-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ask-ollama": {
"args": [
"-y",
"@ask-llm/ollama-mcp"
],
"command": "npx"
}
}
}
Answers built from our own checks of this server.