Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "compare_tools", "get_app", "get_harness" and 13 more
Side-by-side facts for2-42 to 4 slugs, mixing AI build tools, agent harnesses and Agent Toolbox entries. Use when: the user is choosing between specific tools (cursor,e.g.lovable,Cursorbolt...vs Claude Code vs Lovable),.agentForharnessesan(claude-code,open-endedopenai-codex-clipick based on an idea,cline...)useandrecommend_stack. Behavior:AgentRead-only.ToolboxForentrieseach slug: official pricing with checked date and source, ⟨17 unchanged words⟩ links), licence, interface, GitHub stars,MCP/subagents/headless/sandboxing.andAllMCP/subagents/headless/sandboxingvaluessupport.fromnullVibemeansShippednotdata;stated.nullReturns=isErrornot(bad_input)stated.if fewer than 2 slugs resolve. Example: {"tools":["claude-code","openai-codex-cli","aider"]}
{"additionalProperties":false,"properties":{"tools":{"description":"Slugs,2-4e.g.slugs[\"cursor\",\"claude-code\"from list_tools,\"lovable\"]list_harnesses or list_agent_tools.","items":{"type":"string"}, ⟨10 unchanged words⟩
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Compare tools"}
Get full details for one listed app by slug. Use when: you already have an app slug (from search_apps,includinglatest_appssourceor get_vibe50) andVibeneedShippeditslink.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"}
{"additionalProperties":false,"properties":{"slug":{"description":"App slug, e.g. \"stella\".","minLength":1,"type":"string"}},"required":[" ⟨3 unchanged words⟩
FullGet full sourced details for one agent harness by slug. Use when: you have a harness slug (e.g.fromclaude-code,list_harnesses)openai-codex-cli,andgrok-build,needhermes-agent,itsmuse-codesources,langgraph)caveats, pricing or feature evidence. Behavior: Read-only. Returns the harness with source URLs and links to related Vibe Shippedtoolpages,andorAgent
Sponsorship offers, prices andpricescheckout links
Get Vibe Shipped sponsorship offers (featured listing, week ⟨7 unchanged words⟩ takeover) with prices, what each includes, and Stripepaymentcheckoutlinkslinks. Usewherewhen:available,theanduser asks about advertising or sponsoring on Vibe Shipped. Hand thecontacthuman
FullGet full sourced facts for one slug: an AI build tool(cursor,lovable, bolt, replit, v0...),an agent harness or an Agent Toolboxentryentry. Use when: you need pricing,withlicence, features or app stats for a single tool. For several at once use compare_tools. Behavior: Read-only. Returns official pricingandwith checked date and source, app stats and Vibe Shippedlinks.links, or isError (not_found) for an unknown slug. Example: {"slug":"lovable"}
{"additionalProperties":false,"properties":{"slug":{"description":"Tool, harness or Agent Toolbox slug, e.g. cursor, claude-code, cline.","minLength":1,
⟨10 unchanged words⟩ tools ranked by stated, sourced monthly USDrevenuerevenue. 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, staleflagsflag, sourcelinkslink andshareablea rank-card imageURLs.URL.Optionallyinclude_unrankedincludeaddsthenotableunranked/notableappslist
MostList the most recently added apps built withAI.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}
{"additionalProperties":false,"properties":{"limit":{"default":10,"description":"Number of apps.","maximum":50,"minimum":1,"type" ⟨3 unchanged words⟩
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Latest apps"}
List the Agent Toolbox: agentic build tools (Cline, Aider ⟨9 unchanged words⟩ Warp, n8n, Browser Use and more)groupedbycategorycategory. Use(CLIwhen: the user wants options for an agent of a given kind (CLI, IDEagent,Autonomousautonomous SWE,agentbrowser,Browserworkflow)agentor only open-source ones. For harness features (MCP,Workflowsubagents,agentsandboxing),
AgentList agent harnesses: coding agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, goose, Cline,Grok Build, Hermes Agent, Muse Code and moreAider...) and agent frameworks (Claude Agent SDK, OpenAI Agents SDK, smolagents, Mastra, LangGraph). UseEachwhen:hasthe 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 ⟨13 unchanged words⟩ sandboxing). null means not stated or notverified.verified, never 'no'. Example: {"kind":"coding agent","open_source":true,"mcp":true}
{"additionalProperties":false,"properties":{"byo_model":{"description":"
List every AI buildtools tracked bytool Vibe Shipped tracks (Cursor, Claude Code, Lovable, Bolt, Replit, v0, Windsurf,Rork...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: whateachit is, best use, official pricing summary with checked date and source URL,appnumbercountsof listed apps,total/mediantotal and median stated monthly revenue oflistedthose apps, top apps, and new listings in the last 30 days. Example: {}
Rank AI build tools and coding-agent harnesses for an app idea,withusing 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 Shippedper tool, apps matching the idea, platform (web/mobile), coding experience, budget vs stated official pricing(with checked dates and source links), and a preferred harness. Each result has a score breakdown, pricing with checked date and source, and example apps withVibelinks. Example:Shipped{"idea":"habitlinks.tracker mobile app","platform":"mobile","experience":"beginner","budget_usd_month":25}
⟨14 unchanged words⟩ 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 resultincludeshas title, one_liner, tools, category, stated revenue (as published, not audited), source_url and a Vibe Shippedpagelink to cite. Returns total and up to limit results. Example: {"tool":"lovable","q":"saas","limit":5}
{"additionalProperties":false,"properties":{"category":{"description":"Category id as listed by the site, e.g. consumer, saas, dev-tools, mobile-app.","type":"string"},"limit":{"default":10,"description":"Max results.","maximum":50,"minimum":1,"type":"integer"},"q":{"description":"Keywords
Submit an app built with AI to the Vibe Shipped review queue. UseNeedswhen: the user explicitly asks to list their app on Vibe Shipped and can give a public sourcelink(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"}
{"additionalProperties":false,"properties":{"builder_name":{"description":"Maker's name or handle.","type":"string"},"one_liner":{"description":"One-sentence description.","type":"string"},"source_url":{"description":"Public post proving it was built withAIAI.
⟨22 unchanged words⟩ Brief on AI coding tools and harnesses).OnlyUsecallwhen:thisonly when the user explicitly asks to subscribe and gives their own email address.ReturnsNever subscribe an address the user did not provide. Behavior: Write: stores the subscription and returns a receipt that can be used tounsubscribe.unsubscribe (DELETE /api/subscribe). Idempotent for the same email and list. Example: {"email":"me@example.com","list":"agent-brief"}
{"additionalProperties":false,"properties":{"email":{"description":"The user's own emailaddressaddress.","format":"email","type":"string"},"list":{"default":"daily","description":"Which newsletter.
Rank AI build tools bynumberaofsinglelistedmetric 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 monthlyrevenue (revenueUSD), median (median stated monthlyrevenue (medianUSD),or trending (new listings in the last 30 days(trending). Revenue is as stated by makers, not audited. Example: {"by":"revenue","limit":5}
Keep current on AI coding tools:List dated additions and updates to the Vibe Shipped directory (apps built with AI, AI build tools(Cursor,Claude Code, Lovable...),Agent Toolbox entriesand, 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.Usesince(YYYY-MM-DD)filters toget onlychanges on or after adate.date; type filters by entry type; limit caps results (default 50). Example: {"since":"2026-10-15","type":"harness,agent-tool","limit":20}
Added "get_tool" and "recommend_stack"; changed the definition of "compare_tools" (14 tools before, 16 now)
Compare AI build tools and harnessesSide-by-sidecomparisonfactsoffor2-62-4 slugs, mixing AI build toolsusing(cursor,sourcedlovable, bolt...), agent harnesses (claude-code, openai-codex-cli, cline...) and Agent Toolbox entries: official pricing with checked date and source, free tier, lowest stated $/mo,
Added "get_sponsorship_info" and "subscribe_newsletter" (12 tools before, 14 now)
Sponsorship offers and prices — Vibe Shipped sponsorship offers (featured listing, week sponsor, Weekly Top 10 presenting sponsor, month takeover) with prices, what each includes, Stripe payment links where available, and the contact email. Sponsored placements are always labeled; rankings are not for sale.
Subscribe to a Vibe Shipped newsletter — 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). Only call this when the user explicitly asks to subscribe and gives their own email address. Returns a receipt that can be used to unsubscribe.
Added "get_harness", "list_harnesses" and "whats_new" (9 tools before, 12 now)
Get one agent harness — Full sourced details for one agent harness by slug (e.g. claude-code, openai-codex-cli, grok-build, hermes-agent, muse-code, langgraph), with source URLs and links to related Vibe Shipped tool and Agent Toolbox pages.
List agent harnesses — Agent harnesses: coding agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, goose, Cline, Grok Build, Hermes Agent, Muse Code and more) and agent frameworks (Claude Agent SDK, OpenAI Agents SDK, smolagents, Mastra, LangGraph). Each has 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.
What's new on Vibe Shipped — Keep current on AI coding tools: dated additions and updates to apps built with AI, AI build tools (Cursor, Claude Code, Lovable...), Agent Toolbox entries and agent harnesses, newest first. Each item has type, slug, name, change (added/updated), date, url to cite, source and date_basis. Use since (YYYY-MM-DD) to get only changes on or after a date.
Certificate recorded, valid to 2027-01-14
Authorization not required
Unknown → Live
First tool surface recorded: 9 tools (server version 1.1.0)
https://vibeshipped.io/api/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 9 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Get app"}
{"additionalProperties":false,"properties":{"slug":{"description":"Harness slug, e.g. claude-code, openai-codex-cli, aider, langgraph.","minLength":1,"type":"string"}},"required":[" ⟨3 unchanged words⟩
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Get harness"}
{"additionalProperties":false,"properties":{},"type":"object"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Sponsorship info"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Get tool"}
{"additionalProperties":false,"properties":{"include_unranked":{"default":false,"description":"Also return the unranked/notable list.","type":"boolean"},"limit":{"default":50,"description":"Number of ranked apps.","maximum":50,"minimum":1,"type":"integer"},"tool":{"description":"FilterOnlybyapps built with this tool id, e.g.cursorcursor.","type":"string"}},"type":"object"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Vibe Shipped 50"}
{"additionalProperties":false,"properties":{"category":{"description":"Agent category.","enum":["CLI agent","IDE agent", ⟨8 unchanged words⟩ :"string"},"open_source":{"description":"Onlytrue = only open-sourcetoolstools.","type":"boolean"}},"type":"object"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"List agent tools"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"List harnesses"}
{"additionalProperties":false,"properties":{},"type":"object"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"List tools"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Recommend stack"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Search apps"}
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":false,"title":"Submit app"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":true,"readOnlyHint":false,"title":"Subscribe"}
{"additionalProperties":false,"properties":{"by":{"default":"count","description":"Ranking metric.","enum":["count","revenue","median","trending"],"type":"string"},"limit":{"default":10,"description":"Number of tools.","maximum":20,"minimum":1,"type" ⟨3 unchanged words⟩
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"Top tools"}
{"additionalProperties":false,"properties":{"limit":{"default":50,"description":"Max items to return.","maximum":500,"minimum":1,"type":"integer"},"since":{"description":"YYYY-MM-DD; onlyOnly changes on or after this date, format YYYY-MM-DD.","pattern":"^\\d{4}-\\d{2}-\\d ⟨3 unchanged words⟩ :"string"},"type":{"description":"Filter by entryEntry type filter: app, tool, agent-tool or harness. Comma-separate several, e.g. \"harness,agent-tool\".","type":"string"}},"type":"object"}
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true,"title":"What's new"}
{"properties":{"tools":{"description":"Tool idsSlugs, e.g. [\"cursor\",\"claude-code\",\"lovable\"]","items":{"type":"string"},"maxItems":64,"minItems":2,"type":"array"}} ⟨4 unchanged words⟩
Get one AI build tool or agent tool — Full sourced facts for one slug: an AI build tool (cursor, lovable, bolt, replit, v0...), an agent harness or an Agent Toolbox entry, with official pricing and checked date, app stats and Vibe Shipped links.
Recommend an AI build stack — Rank AI build tools and coding-agent harnesses for an app idea, with deterministic, documented scoring (no LLM): number of shipped apps on Vibe Shipped per tool, apps matching the idea, platform (web/mobile), coding experience, budget vs stated official pricing (with checked dates and source links), and a preferred harness. Each result has a score breakdown, pricing, and example apps with Vibe Shipped links.