ask-llm

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.Lykhoyda/ask-llm",
  "description": "Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity",
  "repository": {
    "url": "https://github.com/Lykhoyda/ask-llm",
    "source": "github"
  },
  "version": "1.1.0",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@ask-llm/mcp",
      "version": "1.1.0",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "xAI API key for metered Grok requests; Ask LLM never enables billing or credits",
          "format": "string",
          "isSecret": true,
          "name": "XAI_API_KEY"
        },
        {
          "description": "Explicit Grok harness: xai-api (default) or grok-cli; no failover",
          "format": "string",
          "default": "xai-api",
          "name": "ASK_GROK_HARNESS"
        },
        {
          "description": "Exact selected-harness model override (API default grok-4.7; CLI default grok-4.7; no fallback)",
          "format": "string",
          "name": "ASK_GROK_MODEL"
        },
        {
          "description": "Grok reasoning effort: low, medium, high, or xhigh (default: high)",
          "format": "string",
          "default": "high",
          "name": "ASK_GROK_REASONING_EFFORT"
        },
        {
          "description": "xAI API output-token ceiling to bound accidental spend (default: 16384)",
          "format": "string",
          "default": "16384",
          "name": "ASK_GROK_MAX_OUTPUT_TOKENS"
        },
        {
          "description": "Timeout for xAI API requests in milliseconds (default: 600000)",
          "format": "string",
          "default": "600000",
          "name": "ASK_GROK_TIMEOUT_MS"
        },
        {
          "description": "Optional Cursor CLI credential for ask-cursor-agent; alternative to agent login",
          "format": "string",
          "isSecret": true,
          "name": "CURSOR_API_KEY"
        },
        {
          "description": "Timeout for model-neutral Cursor Agent harness calls (default: 600000)",
          "format": "string",
          "default": "600000",
          "name": "ASK_CURSOR_TIMEOUT_MS"
        },
        {
          "description": "Default Claude model alias or full model name (default: opus)",
          "format": "string",
          "default": "opus",
          "name": "ASK_CLAUDE_MODEL"
        },
        {
          "description": "Claude CLI fallback when Opus is overloaded or unavailable (default: sonnet)",
          "format": "string",
          "default": "sonnet",
          "name": "ASK_CLAUDE_FALLBACK_MODEL"
        },
        {
          "description": "Timeout for Claude CLI execution in milliseconds (default: 600000 = 10 minutes)",
          "format": "string",
          "default": "600000",
          "name": "ASK_CLAUDE_TIMEOUT_MS"
        },
        {
          "description": "Ollama server address (default: http://localhost:11434)",
          "format": "string",
          "default": "http://localhost:11434",
          "name": "OLLAMA_HOST"
        },
        {
          "description": "Timeout for Antigravity (agy) execution in milliseconds (default: 300000 = 5 minutes)",
          "format": "string",
          "default": "300000",
          "name": "ASK_ANTIGRAVITY_TIMEOUT_MS"
        },
        {
          "description": "Set to '0' to drop agy's --sandbox flag if it blocks --add-dir context reads (default: sandbox on)",
          "format": "string",
          "default": "1",
          "name": "ASK_ANTIGRAVITY_SANDBOX"
        },
        {
          "description": "Timeout for CLI execution in milliseconds (default: 300000 = 5 minutes)",
          "format": "string",
          "default": "300000",
          "name": "GMCPT_TIMEOUT_MS"
        },
        {
          "description": "Log verbosity: debug, info, warn, error (default: warn)",
          "format": "string",
          "default": "warn",
          "name": "GMCPT_LOG_LEVEL"
        }
      ]
    }
  ]
}