About ask-llm
Ask LLM is an MCP server that lets coding agents request second opinions on code changes and plans from other model providers. It is aimed at developers and small teams, and supports subscription-based access as well as local Ollama inference.
Key features
- 01Cross-provider code reviews
- 02Plan critique and model comparison
- 03Multiple provider access routes
- 04Opt-in per-edit pairing
- 05Read-only review controls
Use cases
- 01Review staged changes for bugs
- 02Check code for security issues
- 03Challenge a proposed implementation plan
MCP support
The MCP server exposes tools for supported coding assistants to consult providers including Codex, Claude, Grok, Ollama, Gemini, and Antigravity.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @ask-llm/mcpXAI_API_KEYSecretxAI API key for metered Grok requests; Ask LLM never enables billing or creditsASK_GROK_HARNESSExplicit Grok harness: xai-api (default) or grok-cli; no failoverASK_GROK_MODELExact selected-harness model override (API default grok-4.7; CLI default grok-4.7; no fallback)ASK_GROK_REASONING_EFFORTGrok reasoning effort: low, medium, high, or xhigh (default: high)ASK_GROK_MAX_OUTPUT_TOKENSSecretxAI API output-token ceiling to bound accidental spend (default: 16384)ASK_GROK_TIMEOUT_MSTimeout for xAI API requests in milliseconds (default: 600000)CURSOR_API_KEYSecretOptional Cursor CLI credential for ask-cursor-agent; alternative to agent loginASK_CURSOR_TIMEOUT_MSTimeout for model-neutral Cursor Agent harness calls (default: 600000)ASK_CLAUDE_MODELDefault Claude model alias or full model name (default: opus)ASK_CLAUDE_FALLBACK_MODELClaude CLI fallback when Opus is overloaded or unavailable (default: sonnet)ASK_CLAUDE_TIMEOUT_MSTimeout for Claude CLI execution in milliseconds (default: 600000 = 10 minutes)OLLAMA_HOSTOllama server address (default: http://localhost:11434)ASK_ANTIGRAVITY_TIMEOUT_MSTimeout for Antigravity (agy) execution in milliseconds (default: 300000 = 5 minutes)ASK_ANTIGRAVITY_SANDBOXSet to '0' to drop agy's --sandbox flag if it blocks --add-dir context reads (default: sandbox on)GMCPT_TIMEOUT_MSTimeout for CLI execution in milliseconds (default: 300000 = 5 minutes)GMCPT_LOG_LEVELLog verbosity: debug, info, warn, error (default: warn)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
6Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | No | Exact model ID for the selected provider/harness. Usually not needed. |
| prompt | string | Yes | The question, code review request, or analysis task to send |
| harness | enum | No | Execution harness, separate from provider/model. xai-api and grok-cli require provider=grok. Use ask-cursor-agent for Cursor's model-neutral harness. No harness fallback is attempted.provider-default | xai-api | grok-cli |
| sandbox | enum | No | Codex-only sandbox. Defaults to the executor's read-only review contract when omitted. Set workspace-write only for explicit write flows such as image generation. Unsupported on other providers; never silently stripped.read-only | workspace-write |
| provider | enum | Yes | Which LLM provider to use. Available: "gemini" (Gemini, default model: gemini-3.1-pro-preview), "codex" (Codex, default model: gpt-6-astra), "claude" (Claude, default model: opus), "grok" (Grok, default model: grok-4.7), "ollama" (Ollama, default model: qwen3.8:27b), "antigravity" (Antigravity, default model: gemini-3.1-pro)gemini | codex | claude | grok | ollama | antigravity |
| preferred | boolean | No | Codex-only: opt into ASK_CODEX_PREFERRED_MODEL when it differs from the default. Unsupported on other providers; never silently stripped. Leave unset for normal review calls. |
| sessionId | string | No | Optional session ID. For Codex, pass "" on the first call to create a persisted thread, then pass its returned Thread ID to resume; omitting it makes the call ephemeral. For other session-capable providers, pass a prior Session ID to resume. Claude/Gemini use --resume, Codex uses exec resume, and Ollama uses server-side replay. Grok and Antigravity are one-shot. |
| includeDirs | array | No | Relative workspace directories exposed to providers that support additional read roots (Codex, Claude, and Antigravity). Unsupported providers are rejected instead of silently dropping this option; Codex only accepts it on a fresh call (sessionId omitted or ""), never on a resumed thread. |
| reasoningEffort | enum | No | Provider-native reasoning effort. Codex accepts low/medium/high/xhigh/max/ultra; Grok accepts low/medium/high/xhigh. Unsupported provider/effort combinations are rejected, never stripped.low | medium | high | xhigh | max | ultra |
Details
From the project READMEAsk LLM
Second opinions for coding agents.
Get a second opinion on your code or plan, inside your coding assistant, using the model subscriptions you already have.
For individual developers and small teams who already use a coding assistant and pay for another model subscription: ask a different vendor's model to review your changes or challenge your plan, without API keys, copy-paste, or leaving the session.
You: ask codex to review src/auth.ts for security issues
Codex: ⚠ verifyToken() compares tokens with === — not timing-safe (line 42)
⚠ the session cookie is missing a SameSite attribute
Claude: Good catches — applying both fixes to src/auth.ts.
Install
You need Node.js 24+ on Linux or macOS. Before your first review, both your coding assistant (for example Claude Code) and the provider you will consult (for example Codex) must be installed and signed in. Ask LLM configures the connection; it does not install providers or sign you in. If a provider CLI such as Codex has never been signed in on this machine, sign in first and rerun setup.
npm i -g @ask-llm/mcp && ask-llm setup
Setup asks you to confirm each detected host and workflow. Inspect the preview, confirm your assistant's registration and workflows, decline the others, then follow any printed manual steps. Restart your assistant or start a new session in your project.
Your first review
With both Claude Code and Codex installed and signed in, open Claude Code in your project and ask:
Ask Codex to review my staged changes for bugs and missing error handling. Check each finding against the source before proposing fixes.
Working in Codex with a Claude subscription? Ask Claude instead. Choose a provider from a different vendor than your current assistant. A successful review names the reviewer and model, cites relevant code, and reports findings or says it found none. Your assistant applies changes after you decide what to accept. If the request fails, run ask-llm doctor and follow the troubleshooting guide for your selected assistant and reviewer. Warnings about providers you do not use do not require installing them or adding API keys.
For plans, try: “Ask Claude to challenge this plan: what assumptions could fail, and what simpler approach would fit our constraints?”
After an on-demand review, pair review can add ongoing feedback. Pairing requires explicit opt-in; setup leaves it off.
Supported hosts
A host is the assistant you work in; a provider is the model you consult.
| Host | Experience |
|---|---|
| Claude Code | Reviews, plan critique, comparisons; isolated reviewers and opt-in per-edit pairing |
| Codex, Cursor, Grok Build, Gemini CLI | Tools and portable workflows; pairing on demand |
| Antigravity | Tools; setup prints a manual step for workflows |
| Pi 0.83.0+ | Native tools and portable workflows; opt-in per-edit pairing |
| Claude Desktop | Tools only |
| OpenCode | Tools and portable workflows; setup verified with fixtures only |
See host compatibility for the complete matrix and manual setup limits, including existing Codex registrations.
Supported providers
| Provider | Access |
|---|---|
| Codex | Your authenticated Codex CLI/account |
| Claude | Your authenticated Claude Code account; consult it from a host other than Claude Code |
| Grok | Authenticated Grok Build, an exact Cursor model, or the explicit metered xAI API option |
| Antigravity | Your authenticated agy subscription; execution is off by default, and opt-in has no read-only guarantee |
| Ollama | Local models on your machine |
| Gemini | An eligible Gemini Code Assist Standard/Enterprise seat |
Cursor Agent can also consult exact models from your Cursor catalog. It is a connection route, with usage governed by your Cursor plan.
Trust and cost
Review runs use read-only provider controls; the assistant you work in remains the editor. Antigravity refuses execution until explicitly enabled and cannot guarantee read-only access after opt-in. Review only material you are allowed to share with the selected provider.
Calls consume your existing provider plan's quota or follow that account's billing. Grok's xAI API is a separate, metered option requiring an API key; Ask LLM never enables billing or overage for you. Ollama supports local inference. Ask LLM sends no telemetry; provider and host data policies still apply.
Agreement between models is not proof of correctness. Validate findings against the code, tests, and your requirements. See data flow and costs and fallbacks.
Migrating from @ask-llm/*
Follow the migration guide before retiring earlier registrations.
Upgrade or remove · Troubleshooting · Documentation
Contributions: CONTRIBUTING.md. Licensed under MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.