Ermöglicht es AI Coding Assistants, Zweitmeinungen, Code Reviews und Plan-Kritiken von verschiedenen LLM-Providern einzuholen.
Auch bekannt als Lykhoyda/ask-llm, @ask-llm/codex-mcp
- Stars
- 20
- Tools
- 4
- Downloads, 30 Tage
- 506
- Neueste Version
- 0.9.0
- Letzter Commit
- 13. Nov. 2026
- Lizenz
- MIT
Was ist Ask LLM MCP?
Ermöglicht es AI Coding Assistants, Zweitmeinungen, Code Reviews und Plan-Kritiken von verschiedenen LLM-Providern einzuholen. Er stellt 4 Tools bereit, etwa ask-codex, ask-codex-edit, ping.
Zusammenfassung generiert aus dem README des Projekts
Über Ask LLM MCP server
ask-codex ermöglicht es Entwicklern, eine Zweitmeinung zu Code oder Architekturplänen von einem anderen LLM-Provider einzuholen. Es erlaubt dir, das Modell eines anderen Anbieters zu konsultieren, um Änderungen zu prüfen oder einen Plan zu hinterfragen, ohne Code kopieren und einfügen oder neue API Keys verwalten zu müssen. Stattdessen nutzt es die Model-Subscriptions, die du bereits über bestehende CLI Tools und Accounts hast.
Dieser Server läuft lokal auf Linux oder macOS mit Node.js 24+. Er verbindet verschiedene Hosts wie Claude Code, Cursor oder Gemini CLI mit unterschiedlichen Providern wie Codex, Grok, Antigravity oder Ollama. Während der Assistent, den du gerade nutzt, dein Editor bleibt, fungiert der ausgewählte Provider als Reviewer. Du kannst zum Beispiel Claude Code als deinen primären Assistenten nutzen und ihn bitten, Codex für ein Security Review zu konsultieren.
Das Setup erfolgt über einen Befehl, um die Verbindungen zwischen deinen installierten und angemeldeten Tools zu konfigurieren. Nutzer können ein Per-Edit-Pairing für kontinuierliches Feedback in bestimmten Umgebungen wie Grok Build oder Pi aktivieren. Das System nutzt für die meisten Reviews Read-only-Kontrollen, um sicherzustellen, dass der primäre Assistent die Kontrolle über die Codebase behält.
Was du damit machen kannst
- 1Security- und Bug-ReviewsFrage ein anderes Modell, um deine staged Changes auf Sicherheitslücken oder fehlendes Error Handling zu prüfen.
- 2Architekturpläne hinterfragenFordere eine Kritik eines vorgeschlagenen technischen Plans an, um potenzielle Fehler oder einfachere Alternativen zu identifizieren.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du Ask LLM MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenAsk LLM MCP in Claude Code installieren
$ claude mcp add ask-codex -- npx -y @ask-llm/codex-mcpAsk LLM MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"ask-codex": {
"command": "npx",
"args": [
"-y",
"@ask-llm/codex-mcp"
]
}
}
}Ask LLM MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"ask-codex": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ask-llm/codex-mcp"
]
}
}
}Ask LLM MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"ask-codex","type":"stdio","command":"npx","args":["-y","@ask-llm/codex-mcp"]}'Ask LLM MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"ask-codex": {
"command": "npx",
"args": [
"-y",
"@ask-llm/codex-mcp"
]
}
}
}Ask LLM MCP in Codex installieren
$ codex mcp add ask-codex -- npx -y @ask-llm/codex-mcpAsk LLM MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.ask-codex] command = "npx" args = ["-y", "@ask-llm/codex-mcp"]
Ask LLM MCP in Gemini CLI installieren
$ gemini mcp add -s user ask-codex npx -- -y @ask-llm/codex-mcpAsk LLM MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"ask-codex": {
"command": "npx",
"args": [
"-y",
"@ask-llm/codex-mcp"
]
}
}
}Von HostedMCP gestartet am 16. Nov. 2026
Wir haben diesen Befehl für @ask-llm/codex-mcp 0.9.0 in einem isolierten Container ohne Netzwerk und ohne Schlüssel ausgeführt. Er hat geantwortet und 4 Tools gelistet.
Ask LLM MCP tools 4
Vom Server mit tools/list gelesenask-codexNur lesendSend a prompt to OpenAI Codex CLI (defaults to gpt-6-astra with automatic fallback on quota errors). Use for code review, second opinions, analysis, and AI-to-AI collaboration. Do not override the model parameter unless the user explicitly asks. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema. Calls are ephemeral by default; pass sessionId: "" on the first call to persist its Codex thread_id, then pass the returned sessionId on follow-up calls to continue the conversation.
ask-codex-editNur lesendSend 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.
pingNur lesendTest connectivity with the MCP server
get-usage-statsNur lesendGet 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.
| ask-codex | Send a prompt to OpenAI Codex CLI (defaults to gpt-6-astra with automatic fallback on quota errors). Use for code review, second opinions, analysis, and AI-to-AI collaboration. Do not override the model parameter unless the user explicitly asks. Returns both human-readable text and a structured response (provider, model, sessionId, usage) via outputSchema. Calls are ephemeral by default; pass sessionId: "" on the first call to persist its Codex thread_id, then pass the returned sessionId on follow-up calls to continue the conversation. | Nur lesend |
| ask-codex-edit | 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. | Nur lesend |
| ping | Test connectivity with the MCP server | Nur lesend |
| get-usage-stats | 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. | Nur lesend |
Konfiguration
GMCPT_LOG_LEVELLog verbosity: debug, info, warn, error (default: warn)
GMCPT_TIMEOUT_MSTimeout for Codex CLI execution in milliseconds (default: 300000 = 5 minutes)
| Name | Beschreibung | Typ |
|---|---|---|
| GMCPT_LOG_LEVEL | Log verbosity: debug, info, warn, error (default: warn) | |
| GMCPT_TIMEOUT_MS | Timeout for Codex CLI execution in milliseconds (default: 300000 = 5 minutes) |
Automatisierte Checks
Geluften am 16. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarlykhoyda/ask-llm is public and reachablegithub.com/lykhoyda/ask-llm ↗Bestanden
- Paket nennt dieses Repository als Quelle@ask-llm/codex-mcp names lykhoyda/ask-llm as sourcenpmjs.com/package/@ask-llm/codex-mcp ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)No build attestation published for this releaseNicht geprüft
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-13github.com/lykhoyda/ask-llm ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from @ask-llm/codex-mcpBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten99 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell4 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenAsk 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. Grok CLI supports a per-edit hook with Codex Sol by default or Claude Opus 5.5 via reviewer: claude; shell reviews cover command text only.
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, Gemini CLI | Tools and portable workflows; pairing on demand |
| Grok Build | Tools and portable workflows; opt-in per-edit pairing |
| 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.
Ask LLM MCP Fragen
Wie füge ich Ask LLM MCP zu Claude Code hinzu?
Führe claude mcp add ask-codex -- npx -y @ask-llm/codex-mcp in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich Ask LLM MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet Ask LLM MCP?
Er stellt 4 Tools bereit, darunter ask-codex, ask-codex-edit, ping, get-usage-stats.
Wie installiere ich Ask LLM?
Du kannst es via npm mit dem Befehl npm i -g @ask-llm/mcp && ask-llm setup auf Linux oder macOS mit Node.js 24+ installieren.
Stellt Ask LLM eigene API Keys bereit?
Nein, es nutzt die Model-Subscriptions und authentifizierten CLI Tools, die du bereits auf deinem Rechner installiert hast.
Kostet die Nutzung dieses Services extra?
Die Aufrufe verbrauchen das Kontingent deines bestehenden Provider-Plans oder werden über die Abrechnung dieses Accounts abgerechnet.