io.github.sorindecu/vibeshipped

Est-ce que io.github.sorindecu/vibeshipped est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.sorindecu/vibeshipped » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 16 outils

• compare_tools≈ 302 tokens

  Side-by-side facts for 2 to 4 slugs, mixing AI build tools, agent harnesses and Agent Toolbox entries. Use when: the user is choosing between specific tools (e.g. Cursor vs Claude Code vs Lovable). For an open-ended pick based on an idea, use recommend_stack. Behavior: Read-only. For each slug: official pricing with checked date and source, free tier, lowest stated $/mo, apps on Vibe Shipped (count, verified, stated revenue total/median, top apps with links), licence, interface, GitHub stars, and MCP/subagents/headless/sandboxing support. null means not stated. Returns isError (bad_input) if fewer than 2 slugs resolve. Example: {"tools":["claude-code","openai-codex-cli","aider"]}

  Paramètres, retour & exemple (1)

  Paramètres

  • tools · array · requis
    2-4 slugs from list_tools, list_harnesses or list_agent_tools.

  Exemple d'appel

  {"name": "compare_tools", "arguments": {"tools": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_app≈ 184 tokens

  Get full details for one listed app by slug. Use when: you already have an app slug (from search_apps, latest_apps or get_vibe50) and need its source link, website, builder, stack or stated revenue. Behavior: Read-only. Returns the app record, or isError with code not_found if the slug is unknown or not live. Example: {"slug":"stella"}

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    App slug, e.g. "stella".

  Exemple d'appel

  {"name": "get_app", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_harness≈ 198 tokens

  Get full sourced details for one agent harness by slug. Use when: you have a harness slug (from list_harnesses) and need its sources, caveats, pricing or feature evidence. Behavior: Read-only. Returns the harness with source URLs and links to related Vibe Shipped pages, or isError (not_found). Example: {"slug":"openai-codex-cli"}

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Harness slug, e.g. claude-code, openai-codex-cli, aider, langgraph.

  Exemple d'appel

  {"name": "get_harness", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_sponsorship_info≈ 225 tokens

  Get Vibe Shipped sponsorship offers (featured listing, week sponsor, Weekly Top 10 presenting sponsor, month takeover) with prices, what each includes, and Stripe checkout links. Use when: the user asks about advertising or sponsoring on Vibe Shipped. Hand the human the checkout URL; the agent does not pay. Sponsored placements are labeled and rankings are not for sale. Behavior: Read-only, no parameters. Returns offers, a checkout object for the $300 Week Sponsor (one-click Stripe payment link), the contact email and the sponsor page URL. Example: {}

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_sponsorship_info", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_tool≈ 217 tokens

  Get full sourced facts for one slug: an AI build tool, an agent harness or an Agent Toolbox entry. Use when: you need pricing, licence, features or app stats for a single tool. For several at once use compare_tools. Behavior: Read-only. Returns official pricing with checked date and source, app stats and Vibe Shipped links, or isError (not_found) for an unknown slug. Example: {"slug":"lovable"}

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    Tool, harness or Agent Toolbox slug, e.g. cursor, claude-code, cline.

  Exemple d'appel

  {"name": "get_tool", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_vibe50≈ 300 tokens

  Get The Vibe Shipped 50: apps built with AI coding tools ranked by stated, sourced monthly USD revenue. Use when: the user asks how much vibe-coded apps earn, or for the top-earning apps built with a given tool. Always mention that figures are as stated, with the evidence tier. Behavior: Read-only. Each entry has rank, stated revenue, evidence tier (A verified / B documented / C claim), revenue date, stale flag, source link and a rank-card image URL. include_unranked adds notable apps that are not ranked, plus methodology. Example: {"tool":"cursor","limit":10}

  Paramètres, retour & exemple (3)

  Paramètres

  • tool · string · optionnel
    Only apps built with this tool id, e.g. cursor.
  • limit · integer · optionnel
    Number of ranked apps.
  • include_unranked · boolean · optionnel
    Also return the unranked/notable list.

  Exemple d'appel

  {"name": "get_vibe50", "arguments": {"tool": "texte", "limit": 1, "include_unranked": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• latest_apps≈ 184 tokens

  List the most recently added apps built with AI, newest first. Use when: the user asks what was shipped recently, with no filter. To filter by tool or keyword use search_apps; for changes to tools and harnesses too, use whats_new. Behavior: Read-only. Returns app records with source links and Vibe Shipped links. Example: {"limit":5}

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel
    Number of apps.

  Exemple d'appel

  {"name": "latest_apps", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_agent_tools≈ 282 tokens

  List the Agent Toolbox: agentic build tools (Cline, Aider, OpenHands, Codex CLI, Gemini CLI, Devin, Jules, Kiro, Amp, Warp, n8n, Browser Use and more) by category. Use when: the user wants options for an agent of a given kind (CLI, IDE, autonomous SWE, browser, workflow) or only open-source ones. For harness features (MCP, subagents, sandboxing) use list_harnesses. Behavior: Read-only. Per tool: what it is, best use, open-source licence (checked on GitHub) and official pricing with source and date. Example: {"category":"CLI agent","open_source":true}

  Paramètres, retour & exemple (2)

  Paramètres

  • category · string · optionnel · CLI agent | IDE agent | Autonomous SWE agent | Browser agent | Workflow agent
    Agent category.
  • open_source · boolean · optionnel
    true = only open-source tools.

  Exemple d'appel

  {"name": "list_agent_tools", "arguments": {"category": "CLI agent", "open_source": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_harnesses≈ 397 tokens

  List agent harnesses: coding agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, goose, Cline, Aider...) and agent frameworks (Claude Agent SDK, OpenAI Agents SDK, smolagents, Mastra, LangGraph). Use when: the user is choosing a coding agent or agent framework by licence, interface, model support or features. For one harness use get_harness. Behavior: Read-only. Per harness: maker, interface, licence, GitHub stars with date, models, official pricing with source and date, and docs-verified features (MCP, subagents, headless, sandboxing). null means not stated or not verified, never 'no'. Example: {"kind":"coding agent","open_source":true,"mcp":true}

  Paramètres, retour & exemple (6)

  Paramètres

  • q · string · optionnel
    Substring match on name, maker or description.
  • mcp · boolean · optionnel
    true = only harnesses with documented MCP support.
  • kind · string · optionnel · coding agent | framework
    Harness kind.
  • byo_model · boolean · optionnel
    true = only harnesses documented to accept your own model/provider.
  • interface · string · optionnel
    Interface prefix, e.g. CLI, IDE, desktop, SDK.
  • open_source · boolean · optionnel
    true = only open source; false = only not open source.

  Exemple d'appel

  {"name": "list_harnesses", "arguments": {"q": "texte", "mcp": true, "kind": "coding agent", "byo_model": true, "interface": "texte", "open_source": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_tools≈ 214 tokens

  List every AI build tool Vibe Shipped tracks (Cursor, Claude Code, Lovable, Bolt, Replit, v0, Windsurf, Rork, Base44...) with stats. Use when: the user asks which AI build tools exist, or you need tool ids for other calls. For a ranking use top_tools; for 2-4 side by side use compare_tools. Behavior: Read-only, no parameters. Per tool: what it is, best use, official pricing summary with checked date and source URL, number of listed apps, total and median stated monthly revenue of those apps, top apps, and new listings in the last 30 days. Example: {}

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_tools", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recommend_stack≈ 430 tokens

  Rank AI build tools and coding-agent harnesses for an app idea using deterministic, documented scoring (no LLM). Use when: the user describes something they want to build and asks which AI tool to use. If they already named the tools to choose between, use compare_tools instead. Behavior: Read-only. Scores use: number of shipped apps per tool on Vibe Shipped, apps matching the idea, platform (web/mobile), coding experience, budget vs stated official pricing, and a preferred harness. Each result has a score breakdown, pricing with checked date and source, and example apps with links. Example: {"idea":"habit tracker mobile app","platform":"mobile","experience":"beginner","budget_usd_month":25}

  Paramètres, retour & exemple (6)

  Paramètres

  • idea · string · requis
    The app idea in plain text.
  • limit · integer · optionnel
    Number of recommendations.
  • platform · string · optionnel · web | mobile
    Target platform.
  • experience · string · optionnel · beginner | intermediate | experienced
    The user's coding experience.
  • budget_usd_month · number · optionnel
    Monthly tool budget in USD; 0 = free tiers only.
  • preferred_harness · string · optionnel
    Slug or name the user prefers, e.g. claude-code.

  Exemple d'appel

  {"name": "recommend_stack", "arguments": {"idea": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_apps≈ 362 tokens

  Search real, sourced apps that people shipped with AI coding tools (Cursor, Claude Code, Lovable, Bolt, Replit, v0, Windsurf, Rork, Base44). Use when: the user wants real examples of apps built with a given AI tool, in a category, or matching keywords. Use get_app for one known slug; use latest_apps for the newest without a filter. Behavior: Read-only. Keyword match (all words must appear) over title, one-liner, category, builder, tools and stack. Each result has title, one_liner, tools, category, stated revenue (as published, not audited), source_url and a Vibe Shipped link to cite. Returns total and up to limit results. Example: {"tool":"lovable","q":"saas","limit":5}

  Paramètres, retour & exemple (4)

  Paramètres

  • q · string · optionnel
    Keywords; every word must match.
  • tool · string · optionnel
    Tool id: cursor, claude-code, lovable, bolt, replit, v0, windsurf, rork, base44, grok-bot, other.
  • limit · integer · optionnel
    Max results.
  • category · string · optionnel
    Category id as listed by the site, e.g. consumer, saas, dev-tools, mobile-app.

  Exemple d'appel

  {"name": "search_apps", "arguments": {"q": "texte", "tool": "texte", "limit": 1, "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• submit_app≈ 382 tokens

  Submit an app built with AI to the Vibe Shipped review queue. Use when: the user explicitly asks to list their app on Vibe Shipped and can give a public source (post, launch page or interview) showing which AI tool built it. Do not submit apps on someone else's behalf without their request. Behavior: Write: stores a pending submission for human review; nothing is published automatically. Not destructive. Returns status pending, or isError with the validation message. Example: {"title":"Habitly","url":"https://habitly.app","source_url":"https://x.com/maker/status/123","one_liner":"Habit tracker","tools":["lovable"],"builder_name":"Ana"}

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · requis
    App website.
  • title · string · requis
    App name.
  • tools · array · optionnel
    Tool ids used, e.g. ["cursor"].
  • one_liner · string · optionnel
    One-sentence description.
  • source_url · string · requis
    Public post proving it was built with AI.
  • builder_name · string · optionnel
    Maker's name or handle.

  Exemple d'appel

  {"name": "submit_app", "arguments": {"url": "texte", "title": "texte", "source_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• subscribe_newsletter≈ 279 tokens

  Subscribe an email address to a Vibe Shipped newsletter: "daily" (the Daily Ship: new apps built with AI) or "agent-brief" (weekly Agent Brief on AI coding tools and harnesses). Use when: only when the user explicitly asks to subscribe and gives their own email address. Never subscribe an address the user did not provide. Behavior: Write: stores the subscription and returns a receipt that can be used to unsubscribe (DELETE /api/subscribe). Idempotent for the same email and list. Example: {"email":"me@example.com","list":"agent-brief"}

  Paramètres, retour & exemple (2)

  Paramètres

  • list · string · optionnel · daily | agent-brief
    Which newsletter.
  • email · string · requis
    The user's own email address.

  Exemple d'appel

  {"name": "subscribe_newsletter", "arguments": {"email": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• top_tools≈ 252 tokens

  Rank AI build tools by a single metric from Vibe Shipped listings. Use when: the user asks which AI tool has the most shipped apps, the most stated revenue, or is trending. For full stats without ranking use list_tools. Behavior: Read-only. by = count (listed apps), revenue (total stated monthly USD), median (median stated monthly USD) or trending (new listings in the last 30 days). Revenue is as stated by makers, not audited. Example: {"by":"revenue","limit":5}

  Paramètres, retour & exemple (2)

  Paramètres

  • by · string · optionnel · count | revenue | median | trending
    Ranking metric.
  • limit · integer · optionnel
    Number of tools.

  Exemple d'appel

  {"name": "top_tools", "arguments": {"by": "count", "limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• whats_new≈ 340 tokens

  List dated additions and updates to the Vibe Shipped directory (apps built with AI, AI build tools, Agent Toolbox entries, agent harnesses), newest first. Use when: you need to know what changed recently in AI coding tools, or to refresh a cached view since a date. Not for searching; use search_apps, list_tools or list_harnesses for that. Behavior: Read-only. Each item has type, slug, name, change (added/updated), date, a url to cite, source and date_basis. since filters to changes on or after a date; type filters by entry type; limit caps results (default 50). Example: {"since":"2026-10-15","type":"harness,agent-tool","limit":20}

  Paramètres, retour & exemple (3)

  Paramètres

  • type · string · optionnel
    Entry type filter: app, tool, agent-tool or harness. Comma-separate several, e.g. "harness,agent-tool".
  • limit · integer · optionnel
    Max items to return.
  • since · string · optionnel
    Only changes on or after this date, format YYYY-MM-DD.

  Exemple d'appel

  {"name": "whats_new", "arguments": {"type": "texte", "limit": 1, "since": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://vibeshipped.io/api/mcp