Ask Ollama

lykhoyda/ask-llm

Runs local Ollama models through MCP's ask_ollama tool, giving Claude a private, offline second opinion without API costs or data leaving your machine. Returns structured responses with provider metadata and supports multi-turn conversations via sessionId for maintaining context across prompts. Part of a broader ask-llm suite that includes Gemini and Codex bridges, but this package strips out the cloud dependencies. Reach for it when you want code reviews, architecture feedback, or brainstorming from models like qwen2.5-coder running on your own hardware. Includes get_usage_stats for tracking token counts and a diagnose tool that verifies your Ollama installation and model availability.

GitHub stars: 19
transport: STDIO
env vars: 3
last updated: Sep 27, 2026

View on GitHub

Configuration

OLLAMA_HOSTdefault: http://localhost:11434

Ollama server address (default: http://localhost:11434)

GMCPT_TIMEOUT_MSdefault: 300000

Timeout for Ollama execution in milliseconds (default: 300000 = 5 minutes)

GMCPT_LOG_LEVELdefault: warn

Log verbosity: debug, info, warn, error (default: warn)

Readme

Ask LLM

Second opinions for coding agents.

Get a second opinion on your code or plan, inside your coding assistant, using the model subscriptions you already have.

For individual developers and small teams who already use a coding assistant and pay for another model subscription: ask a different vendor's model to review your changes or challenge your plan, without API keys, copy-paste, or leaving the session.

You:    ask codex to review src/auth.ts for security issues
Codex:  ⚠ verifyToken() compares tokens with === — not timing-safe (line 42)
        ⚠ the session cookie is missing a SameSite attribute
Claude: Good catches — applying both fixes to src/auth.ts.

Install

You need Node.js 24+ on Linux or macOS. Before your first review, both your coding assistant (for example Claude Code) and the provider you will consult (for example Codex) must be installed and signed in. Ask LLM configures the connection; it does not install providers or sign you in. If a provider CLI such as Codex has never been signed in on this machine, sign in first and rerun setup.

npm i -g @ask-llm/mcp && ask-llm setup

View the full README on GitHub

Details

Repository: github.com/lykhoyda/ask-llm
Category: AI & LLM Tools
Package: @ask-llm/ollama-mcp
Transport: STDIO
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Basic Memorybasicmachines-co/basic-memoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.4.5Kstars

Agentrinadelph/agent-mcpAgent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The sys1.2Kstars

Agent Security Scanner Mcpsinewaveai/agent-security-scanner-mcpSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.110stars

Awesome Agent Skillsshadowrootdev/awesome-agent-skills-mcpMCP server with 100+ AI agent skills from Anthropic, Vercel, Trail of Bits, Hugging Face & more.23stars

Agent Knowledgekeshrath/agent-knowledgeCross-session memory for AI agents - knowledge graph, scoring, semantic search19stars

Neurodivergent Memoryjmeyer1980/neurodivergent-memoryPersistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.12stars