Manifest
    by Manifold
    Back to Results
    0.3.0

    io.github.Lykhoyda/ask-grok

    Consult Grok through xAI's metered API with exact model selection and no fallback

    ai›ai-agents
    Rank#800
    Lykhoydamcp-registryMulti service aggregatorLast scanned Nov 2, 2026, 04:51 PMhttps://github.com/Lykhoyda/ask-llm
    Created
    9 months ago
    Last commit
    last week
    Latest release
    @ask-llm/mcp@1.2.13 weeks ago

    Security Findings

    Tools out of server's stated scope3×

    MaliciousScanner

    ask-llm: Server is described narrowly as consulting Grok via xAI's metered API, but this tool dispatches prompts to Codex, Claude, Antigravity, Ollama, and Gemini CLIs — providers entirely outside the stated Grok/xAI domain.

    ask-cursor-agent: Server's stated purpose is Grok consultation via xAI's API, but this tool shells out to the Cursor Agent CLI (`agent --print --mode ask`), a different product and provider surface entirely.

    multi-llm: Server states a narrow Grok/xAI consultation purpose, but this tool fans a prompt out to multiple non-Grok providers (Codex, Claude, Antigravity, Ollama, Gemini) in parallel.

    Missing permission declaration

    SuspiciousScanner

    Server declares no permissions across 4 tools

    Tools

    4 tools exposed by this MCP server

    3 high risk1 clean

    ask-cursor-agent

    Use Cursor Agent as a model-neutral, read-only consultation harness. The provider and exact Cursor catalog model ID are separate required fields. Runs `agent --print --mode ask` without --force/--trust, never changes spend settings, and never falls back to another model or provider.

    High Risk
    packages/llm-mcp/src/index.ts

    ask-llm

    Send a prompt to an LLM provider (Codex, Claude, Grok, Antigravity, Ollama, Gemini). Specify which provider to use. Provider-specific fallback behavior is reported truthfully; Grok never substitutes or falls back from the requested model. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema.

    High Risk
    packages/llm-mcp/src/index.ts

    multi-llm

    Dispatch the same prompt to multiple LLM providers in parallel and return all responses in one structured payload. Use when you want to compare answers across Codex, Claude, Grok, Antigravity, Ollama, and Gemini, or when you want a multi-provider sanity check on a question. Returns per-provider success/failure, response text, model, sessionId, and token usage. Each call is fresh — no session continuity (use ask-llm for individual session-bearing calls).

    High Risk
    packages/llm-mcp/src/index.ts

    ping

    Test connectivity with the MCP server

    Clean
    packages/llm-mcp/src/index.ts

    Versions

    2
    • 0.3.0
      Scanned Nov 2, 2026, 04:51 PMHigh
    • 0.1.5
      Scanned Sep 20, 2026, 09:10 PMNone known