Ask LLM MCP Server

by lykhoydaio.github.Lykhoyda/ask-llmv1.1.0

Unified MCP server for multi-LLM consultation — routes Gemini, Codex, Claude, Grok, Ollama, and Antigravity behind runtime availability checks

18Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active2d ago

Install Ask LLM MCP server

claude mcp add ask-llm -e XAI_API_KEY='<xai-api-key>' -e CURSOR_API_KEY='<cursor-api-key>' -- npx -y @ask-llm/mcp

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<xai-api-key>",
        "CURSOR_API_KEY": "<cursor-api-key>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<xai-api-key>",
        "CURSOR_API_KEY": "<cursor-api-key>"
      }
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "ask-llm": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<xai-api-key>",
        "CURSOR_API_KEY": "<cursor-api-key>"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "ask-llm": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/mcp"
      ],
      "env": {
        "XAI_API_KEY": "<xai-api-key>",
        "CURSOR_API_KEY": "<cursor-api-key>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
XAI_API_KEY	—	yes	xAI API key for metered Grok requests; Ask LLM never enables billing or credits
ASK_GROK_HARNESS	—	—	Explicit Grok harness: xai-api (default) or grok-cli; no failover
ASK_GROK_MODEL	—	—	Exact selected-harness model override (API default grok-4.7; CLI default grok-4.7; no fallback)
ASK_GROK_REASONING_EFFORT	—	—	Grok reasoning effort: low, medium, high, or xhigh (default: high)
ASK_GROK_MAX_OUTPUT_TOKENS	—	—	xAI API output-token ceiling to bound accidental spend (default: 16384)
ASK_GROK_TIMEOUT_MS	—	—	Timeout for xAI API requests in milliseconds (default: 600000)
CURSOR_API_KEY	—	yes	Optional Cursor CLI credential for ask-cursor-agent; alternative to agent login
ASK_CURSOR_TIMEOUT_MS	—	—	Timeout for model-neutral Cursor Agent harness calls (default: 600000)
ASK_CLAUDE_MODEL	—	—	Default Claude model alias or full model name (default: opus)
ASK_CLAUDE_FALLBACK_MODEL	—	—	Claude CLI fallback when Opus is overloaded or unavailable (default: sonnet)
ASK_CLAUDE_TIMEOUT_MS	—	—	Timeout for Claude CLI execution in milliseconds (default: 600000 = 10 minutes)
OLLAMA_HOST	—	—	Ollama server address (default: http://localhost:11434)
ASK_ANTIGRAVITY_TIMEOUT_MS	—	—	Timeout for Antigravity (agy) execution in milliseconds (default: 300000 = 5 minutes)
ASK_ANTIGRAVITY_SANDBOX	—	—	Set to '0' to drop agy's --sandbox flag if it blocks --add-dir context reads (default: sandbox on)
GMCPT_TIMEOUT_MS	—	—	Timeout for CLI execution in milliseconds (default: 300000 = 5 minutes)
GMCPT_LOG_LEVEL	—	—	Log verbosity: debug, info, warn, error (default: warn)

Freshness

Active — last maintenance signal 2d ago. The newest of the signals below sets the band.

Last commit (default branch)
2026-10-07 · 2d ago · GitHub
Latest release
2026-09-29 · 10d ago · GitHub · @ask-llm/mcp@1.1.0
Package published
no data · npm/PyPI
Registry entry updated
2026-09-29 · 10d ago · official registry · v1.1.0

FAQ

›How do I install the Ask LLM MCP server in Claude Code?

Run: claude mcp add ask-llm -e XAI_API_KEY='<xai-api-key>' -e CURSOR_API_KEY='<cursor-api-key>' -- npx -y @ask-llm/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Ask LLM require an API key?

Yes. It expects XAI_API_KEY, CURSOR_API_KEY, of which 2 are secrets.

›Can I use Ask LLM as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Ask LLM in the official MCP registry?

Yes, as io.github.Lykhoyda/ask-llm.