cosmic-mcp

All servers

ask-llm

io.github.Lykhoyda/ask-llm ยท version 1.3.0

Community listing. Not installed or verified by cosmic-mcp. Read the source and its permissions before you run it.

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

https://github.com/Lykhoyda/ask-llm

Quick facts

  • Listing: Community
  • Published Nov 5, 16:44 UTC
  • Transport: stdio
  • Package: npm @ask-llm/mcp 1.3.0
  • Listed by cosmic-mcp: Nov 9, 04:25 UTC
  • Repository: https://github.com/Lykhoyda/ask-llm
  • npm: https://www.npmjs.com/package/@ask-llm/mcp
  • Needs settings: XAI_API_KEY ASK_GROK_HARNESS ASK_GROK_MODEL ASK_GROK_REASONING_EFFORT ASK_GROK_MAX_OUTPUT_TOKENS ASK_GROK_TIMEOUT_MS CURSOR_API_KEY ASK_CURSOR_TIMEOUT_MS ASK_CLAUDE_MODEL ASK_CLAUDE_FALLBACK_MODEL ASK_CLAUDE_TIMEOUT_MS OLLAMA_HOST ASK_ANTIGRAVITY_TIMEOUT_MS ASK_ANTIGRAVITY_SANDBOX GMCPT_TIMEOUT_MS GMCPT_LOG_LEVEL

AI and LLMs

Setup snippets

Generated from the registry entry. cosmic-mcp has not run or reviewed this server; values in angle brackets are yours to fill in.

Run it locally (npm)

npx -y '@ask-llm/[email protected]'

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "ask-llm": {
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "command": "npx",
      "env": {
        "ASK_ANTIGRAVITY_SANDBOX": "<your ask antigravity sandbox>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ask antigravity timeout ms>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ask claude fallback model>",
        "ASK_CLAUDE_MODEL": "<your ask claude model>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ask claude timeout ms>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ask cursor timeout ms>",
        "ASK_GROK_HARNESS": "<your ask grok harness>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ask grok max output tokens>",
        "ASK_GROK_MODEL": "<your ask grok model>",
        "ASK_GROK_REASONING_EFFORT": "<your ask grok reasoning effort>",
        "ASK_GROK_TIMEOUT_MS": "<your ask grok timeout ms>",
        "CURSOR_API_KEY": "<your cursor api key>",
        "GMCPT_LOG_LEVEL": "<your gmcpt log level>",
        "GMCPT_TIMEOUT_MS": "<your gmcpt timeout ms>",
        "OLLAMA_HOST": "<your ollama host>",
        "XAI_API_KEY": "<your xai api key>"
      }
    }
  }
}

Claude Code

claude mcp add 'ask-llm' -- npx -y '@ask-llm/[email protected]'

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "ask-llm": {
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "command": "npx",
      "env": {
        "ASK_ANTIGRAVITY_SANDBOX": "<your ask antigravity sandbox>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ask antigravity timeout ms>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ask claude fallback model>",
        "ASK_CLAUDE_MODEL": "<your ask claude model>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ask claude timeout ms>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ask cursor timeout ms>",
        "ASK_GROK_HARNESS": "<your ask grok harness>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ask grok max output tokens>",
        "ASK_GROK_MODEL": "<your ask grok model>",
        "ASK_GROK_REASONING_EFFORT": "<your ask grok reasoning effort>",
        "ASK_GROK_TIMEOUT_MS": "<your ask grok timeout ms>",
        "CURSOR_API_KEY": "<your cursor api key>",
        "GMCPT_LOG_LEVEL": "<your gmcpt log level>",
        "GMCPT_TIMEOUT_MS": "<your gmcpt timeout ms>",
        "OLLAMA_HOST": "<your ollama host>",
        "XAI_API_KEY": "<your xai api key>"
      }
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "ask-llm": {
      "args": [
        "-y",
        "@ask-llm/[email protected]"
      ],
      "command": "npx",
      "env": {
        "ASK_ANTIGRAVITY_SANDBOX": "<your ask antigravity sandbox>",
        "ASK_ANTIGRAVITY_TIMEOUT_MS": "<your ask antigravity timeout ms>",
        "ASK_CLAUDE_FALLBACK_MODEL": "<your ask claude fallback model>",
        "ASK_CLAUDE_MODEL": "<your ask claude model>",
        "ASK_CLAUDE_TIMEOUT_MS": "<your ask claude timeout ms>",
        "ASK_CURSOR_TIMEOUT_MS": "<your ask cursor timeout ms>",
        "ASK_GROK_HARNESS": "<your ask grok harness>",
        "ASK_GROK_MAX_OUTPUT_TOKENS": "<your ask grok max output tokens>",
        "ASK_GROK_MODEL": "<your ask grok model>",
        "ASK_GROK_REASONING_EFFORT": "<your ask grok reasoning effort>",
        "ASK_GROK_TIMEOUT_MS": "<your ask grok timeout ms>",
        "CURSOR_API_KEY": "<your cursor api key>",
        "GMCPT_LOG_LEVEL": "<your gmcpt log level>",
        "GMCPT_TIMEOUT_MS": "<your gmcpt timeout ms>",
        "OLLAMA_HOST": "<your ollama host>",
        "XAI_API_KEY": "<your xai api key>"
      },
      "type": "stdio"
    }
  }
}

Related servers

  • Harness Verified domain
    Start Claude Code and Codex agents the person can watch, wait for them and read their answers.
  • docs-mcp Verified domain
    Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.
  • spotdb Verified domain
    Ephemeral data sandbox for AI workflows with guardrails and security
  • Adako: ad ops for AI assistants Verified domain
    Google, Meta, LinkedIn and ChatGPT Ads for AI assistants. Every change needs your approval.
  • Aidoo for Odoo Verified domain
    Query and update your Odoo ERP in plain language, under your own Odoo access rules.
  • EXTREMELY agency Verified domain
    Your agency of AI agents in your AI app: what agents did, approvals, requests, jobs and reports.