io.github.Lykhoyda/ask-llm

io.github.Lykhoyda/ask-llm

Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity

View repository →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp@1.3.0"
      ],
      "env": {
        "XAI_API_KEY": "<your XAI_API_KEY>",
        "ASK_GROK_HARNESS": "xai-api",
        "ASK_GROK_REASONING_EFFORT": "high",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "16384",
        "ASK_GROK_TIMEOUT_MS": "600000",
        "CURSOR_API_KEY": "<your CURSOR_API_KEY>",
        "ASK_CURSOR_TIMEOUT_MS": "600000",
        "ASK_CLAUDE_MODEL": "opus",
        "ASK_CLAUDE_FALLBACK_MODEL": "sonnet",
        "ASK_CLAUDE_TIMEOUT_MS": "600000",
        "OLLAMA_HOST": "http://localhost:11434",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "300000",
        "ASK_ANTIGRAVITY_SANDBOX": "1",
        "GMCPT_TIMEOUT_MS": "300000",
        "GMCPT_LOG_LEVEL": "warn"
      }
    }
  }
}
Environment variables
  • XAI_API_KEYsecretxAI API key for metered Grok requests; Ask LLM never enables billing or credits
  • ASK_GROK_HARNESSExplicit Grok harness: xai-api (default) or grok-cli; no failover
  • ASK_GROK_REASONING_EFFORTGrok reasoning effort: low, medium, high, or xhigh (default: high)
  • ASK_GROK_MAX_OUTPUT_TOKENSxAI API output-token ceiling to bound accidental spend (default: 16384)
  • ASK_GROK_TIMEOUT_MSTimeout for xAI API requests in milliseconds (default: 600000)
  • CURSOR_API_KEYsecretOptional Cursor CLI credential for ask-cursor-agent; alternative to agent login
  • ASK_CURSOR_TIMEOUT_MSTimeout for model-neutral Cursor Agent harness calls (default: 600000)
  • ASK_CLAUDE_MODELDefault Claude model alias or full model name (default: opus)
  • ASK_CLAUDE_FALLBACK_MODELClaude CLI fallback when Opus is overloaded or unavailable (default: sonnet)
  • ASK_CLAUDE_TIMEOUT_MSTimeout for Claude CLI execution in milliseconds (default: 600000 = 10 minutes)
  • OLLAMA_HOSTOllama server address (default: http://localhost:11434)
  • ASK_ANTIGRAVITY_TIMEOUT_MSTimeout for Antigravity (agy) execution in milliseconds (default: 300000 = 5 minutes)
  • ASK_ANTIGRAVITY_SANDBOXSet to '0' to drop agy's --sandbox flag if it blocks --add-dir context reads (default: sandbox on)
  • GMCPT_TIMEOUT_MSTimeout for CLI execution in milliseconds (default: 300000 = 5 minutes)
  • GMCPT_LOG_LEVELLog verbosity: debug, info, warn, error (default: warn)

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Developer Tools
Version
1.3.0
Registry
active
Published
11/5/2026

More Developer Tools servers

Browse all Developer Tools →

io.github.Lykhoyda/ask-ollama

Lykhoyda

Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local

Developer ToolsAdded 1 month ago

armguard-mcp

Lynn-hh

Safety-first MCP server for ROS 2 robot arms: server-side safety envelope, human approval, audit

Developer ToolsAdded 2 weeks ago

U.S. Government Open Data

lzinga

Open data from 40+ U.S. government APIs: economy, spending, Congress, health, energy, disasters

Developer ToolsAdded 1 month ago

io.github.lzx3in/mcp-aliyun-domain

lzx3in

MCP server for Alibaba Cloud Domain - check availability, query details, list domains, create orders

Developer ToolsAdded 4 months ago

Zektor

m-akcan

Managed Postgres and Valkey hosted in Germany. Agents can create a trial database with no signup.

Developer ToolsAdded 1 month ago

m-dev-tools

m-dev-tools

MCP server wrapping the m-dev-tools catalog: route_intent, describe, verify.

Developer ToolsAdded 6 months ago

Add the badge to your site

Show visitors that io.github.Lykhoyda/ask-llm is listed here — it’s also the link we check for a free listing.

io.github.Lykhoyda/ask-llm — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-lykhoyda-ask-llm?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="io.github.Lykhoyda/ask-llm — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![io.github.Lykhoyda/ask-llm — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-lykhoyda-ask-llm?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.