Ask Ollama runs on your own machine — the client starts it, so there is no endpoint to ping. 608 installs a week from npm. Last commit 16 Sep 2026.
Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
We read the source, 21 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const childProcess = spawn(command, safeArgs, {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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"
}
}
}
This one needs environment variables set before it will start:
OLLAMA_HOST (Ollama server address (default: http://localhost:11434)), GMCPT_TIMEOUT_MS (Timeout for Ollama execution in milliseconds (default: 300000 = 5 minutes)), GMCPT_LOG_LEVEL (Log verbosity: debug, info, warn, error (default: warn)).
The author declared them in the registry entry; get the values from the project itself.
Bridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
AI Linux & Windows server management with Claude MCP and fully private agents using local AI
Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.
Figma MCP server with full read/write access via plugin bridge — no API token or rate limits.
MacWhisper transcription for Claude Desktop. Fully local, no cloud, audio stays on your Mac.
Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.
Answers built from our own checks of this server.