Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
Connect Runs on your machine
claude mcp add ask-ollama -e OLLAMA_HOST=<OLLAMA_HOST> -e GMCPT_TIMEOUT_MS=<GMCPT_TIMEOUT_MS> -e GMCPT_LOG_LEVEL=<GMCPT_LOG_LEVEL> -- npx -y @ask-llm/[email protected]{
"mcpServers": {
"ask-ollama": {
"command": "npx",
"args": [
"-y",
"@ask-llm/[email protected]"
],
"env": {
"OLLAMA_HOST": "<OLLAMA_HOST>",
"GMCPT_TIMEOUT_MS": "<GMCPT_TIMEOUT_MS>",
"GMCPT_LOG_LEVEL": "<GMCPT_LOG_LEVEL>"
}
}
}
}{
"mcpServers": {
"ask-ollama": {
"command": "npx",
"args": [
"-y",
"@ask-llm/[email protected]"
],
"env": {
"OLLAMA_HOST": "<OLLAMA_HOST>",
"GMCPT_TIMEOUT_MS": "<GMCPT_TIMEOUT_MS>",
"GMCPT_LOG_LEVEL": "<GMCPT_LOG_LEVEL>"
}
}
}
}{
"servers": {
"ask-ollama": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ask-llm/[email protected]"
],
"env": {
"OLLAMA_HOST": "<OLLAMA_HOST>",
"GMCPT_TIMEOUT_MS": "<GMCPT_TIMEOUT_MS>",
"GMCPT_LOG_LEVEL": "<GMCPT_LOG_LEVEL>"
}
}
}
}Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
OLLAMA_HOSTOptional | Ollama server address (default: http://localhost:11434) |
GMCPT_TIMEOUT_MSOptional | Timeout for Ollama execution in milliseconds (default: 300000 = 5 minutes) |
GMCPT_LOG_LEVELOptional | Log verbosity: debug, info, warn, error (default: warn) |
Details
| Package | @ask-llm/[email protected] (NPM, stdio) |
| First published | 27 Sep 2026 |
| Last updated | 27 Sep 2026 |
| Registry name | io.github.Lykhoyda/ask-ollama |
More other servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.