Ask LLM

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/lykhoyda-ask-llm

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

10 read · 6 write · 0 delete

Secrets

3 (API keys, tokens or passwords)

Install scripts

None found

Runs as

Node.js package

Tools (16)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• ask-antigravityAsk Antigravity (experimental)

  Send a prompt to Google's Antigravity CLI (agy) for a subscription-backed second opinion, code review, or analysis. Refuses execution unless ASK_ANTIGRAVITY_ALLOW_UNISOLATED=1; opted-in runs can modify files, run shell commands, and access the network because read-only isolation is not guaranteed. Requires agy >=1.1.5, installed and logged in once; unsupported versions fail before model invocation. Defaults to the gemini-3.1-pro model at high reasoning effort, falling back to gemini-3.8-flash on a rate limit (override via the ASK_ANTIGRAVITY_MODEL / ASK_ANTIGRAVITY_EFFORT env vars; run `agy mo…

• ask-claudeAsk Clauderead-only

  Description is built at runtime.

• ask-codexAsk Codexread-only

  Deprecated alias for `ask-llm` with provider codex. Consult OpenAI Codex through Ask LLM's canonical executor. Read-only by default; use workspace-write only for an explicit write flow such as codex-image. Displayed text is bounded to Pi's 50KB/2000-line limits.

• ask-codex-editAsk Codex (Edit Mode)read-only

  Send a code edit request to OpenAI Codex CLI and get structured search/replace edit blocks back (via codex --output-schema). Codex reads the existing files (read-only) and proposes precise, applyable changes for Claude to apply. Use this when you want Codex to suggest specific code modifications to existing files rather than just analysis. Mirrors ask-gemini-edit.

• ask-cursor-agentAsk via Cursor Agentread-only

  Use Cursor Agent as a model-neutral read-only harness. Provider (claude, codex, gemini, grok) and exact model ID are separate and must agree; Auto or noncanonical catalog IDs are refused. Prompts above 16KB are piped over stdin. Requires an authenticated Cursor CLI and may consume included usage or on-demand spend; no spend settings or fallback are changed.

• ask-geminiAsk Gemini

  Deprecated alias for `ask-llm` with provider gemini. Consult Gemini through Ask LLM's canonical executor (`gemini-3.1-pro-preview` → `gemini-3.8-flash` on quota), including validation, sessions, and structured response. Displayed text is bounded to Pi's 50KB/2000-line limits.

• ask-gemini-editAsk Gemini (Edit Mode)

  Send a code edit request to Gemini CLI and get structured OLD/NEW edit blocks back. Gemini analyzes the files and returns precise, applicable code changes. Use this when you want Gemini to suggest specific code modifications rather than just analysis.

• ask-grokAsk Grokread-only

  Deprecated alias for `ask-llm` with provider grok. Consult Grok through Ask LLM's canonical xAI API executor. Requires XAI_API_KEY and may incur metered API charges; no billing changes or model fallback are performed. Displayed text is bounded to Pi's 50KB/2000-line limits.

• ask-llmAsk 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. Displayed text is bounded to Pi's 50KB/2000-line limits.

• ask-multi

  Deprecated alias for `multi-llm`, kept because it also accepts per-provider options. Send exactly the same prompt to two to five Ask LLM providers concurrently. Dispatch is deterministic and bounded; results preserve provider input order and report every failure instead of silently dropping it.

• ask-ollamaAsk Ollama

  Deprecated alias for `ask-llm` with provider ollama. Consult the configured local Ollama model through Ask LLM's canonical executor. No external provider data transfer; displayed text is bounded to Pi's 50KB/2000-line limits.

• diagnoseDiagnose Environmentread-only

  Run a self-diagnosis of the MCP server's environment: Node version, resolved PATH, provider CLI presence and versions, key env vars. Returns a structured report and a human-readable summary. Read-only; never spawns LLM calls.

• fetch-chunkFetch Chunkread-only

  Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.

• get-usage-statsGet Usage Statsread-only

  Get the current MCP server's session usage stats: total LLM calls, token totals (input/output/thinking/cached), wall time, and breakdowns per provider and per model. No data leaves your machine — counts are tracked in-memory for the lifetime of the server process. Returns both human-readable markdown and a structured JSON snapshot via outputSchema.

• multi-llmMulti-LLM Parallel Dispatch

  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). Displayed text is bounded to Pi's 50KB/2000-line limits.

Signals

Stars

18

Forks

5

Open issues

5

Weekly downloads

90

Last commit

Oct 14, 2026 (14 days ago)

Last release

Oct 13, 2026 (15 days ago)

Last package publish

Oct 13, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.Lykhoyda/ask-llm

Version

1.2.1

Auth

API key

Packages

npm @ask-llm/mcp

License

MIT

Repository

github.com/Lykhoyda/ask-llm

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql