VibeCodePicks
Server Details
The best vibe coding tools, ranked by what you want to build
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 16 tools
Three near-duplicate pairs make selection risky: set_preferences vs save_preferences (both store tags, differing only in feed-key/feed-mode detail), check_updates vs whats_new (both are 'max 3' new-item feeds honoring saved interests), and list_scenarios vs scenario (both surface scenarios ranked by community sentiment). feedback vs log_choice also overlap as user-signal recorders. Descriptions contain hints, but an agent must read carefully to avoid the wrong twin.
A verb_noun pattern dominates (check_updates, compare_tools, list_alternatives, list_categories, recommend_tools, save_preferences, set_preferences, log_choice), but several tools break it with bare nouns or verbs: fetch, search, feedback, scenario, subscribe, forget_me. The singular 'scenario' next to 'list_scenarios' is especially inconsistent.
16 tools sits at the top of a reasonable catalog surface and the redundancy (duplicate preference writers, duplicate feeds, duplicate scenario readers) means roughly 3-4 tools could be merged away. Each remaining tool does earn a place, so it is heavy rather than bloated.
The catalog lifecycle is well covered: discovery (search, list_categories, list_scenarios, scenario), inspection (fetch, compare_tools, list_alternatives), ranking (recommend_tools), personalization (set/save_preferences, subscribe, check_updates, whats_new), feedback (feedback, log_choice), and privacy (forget_me). Minor gaps exist — no tool to read back the stored profile/tags for verification, and no key rotation/revocation beyond forget_me.
Available Tools
16 toolscheck_updatesCheck matching updatesBInspect
Tools added or updated since this user's last check that match their saved tags. Optional since (YYYY-MM-DD or catalog v). When nothing matches, returns {new:0} — a minimal response when nothing new matches. Tracks last_checked. Max 3 items. Does not change recommend_tools. Optional key: same feed key passed to set_preferences, to read that project's profile.
Inputs: key, since.
compare_toolsCompare two toolsCRead-onlyIdempotentInspect
Side-by-side of two tools + comparison page url.
Inputs: a (required), b (required), verbose.
feedbackRecord feedbackAInspect
Adjust this user's check_updates ranking for a listed tool. action is one of used, not_useful, not_relevant. Stores only the tool id and that enum. Does not change recommend_tools. Optional key: same feed key passed to set_preferences, to adjust that project's ranking.
Inputs: action (required), tool_id (required), key.
fetchGet tool detailsBRead-onlyIdempotentInspect
Tool profile by id. Default: summary, best_for, price, free, 2 strengths, 2 weaknesses, url. fields: summary description best_for not_for skill coding pricing platforms strengths weaknesses alternatives video compare official all.
Inputs: id (required), fields, verbose.
forget_meForget meADestructiveIdempotentInspect
Delete this client's anonymous id, tag profile and last_checked. Feedback is first folded into anonymous aggregate counters (tool_id × used/not_useful/not_relevant, no uid). Those aggregate counts are kept. If you pass a feed key, that keyed feed record is deleted too.
Inputs: key.
list_alternativesFind alternativesCRead-onlyIdempotentInspect
Alternatives to a tool. Rows: id|name|$from/mo|free.
Inputs: tool (required), limit, offset, verbose.
list_categoriesList categoriesCRead-onlyIdempotentInspect
Category and use-case keys with tool ids.
Inputs: verbose.
list_scenariosList scenariosBRead-onlyIdempotentInspect
Use-case scenarios (e.g. ai-game-development, code-review) with top tools by community sentiment.
Inputs: no named parameters.
log_choiceLog a choice or purchaseAInspect
Record a tool the user explicitly picked/rejected/tried/starred, or PURCHASED. Call it with action 'purchased' right after the user tells you they bought a paid plan of a listed tool (ask first; never log silently), and again later with action 'feedback' once they have used it for a while (e.g. weekly), passing rating and what worked / fell short. Optional fields apply to purchased/feedback only. Stored anonymously under the key; forget_me deletes it. picked/rejected also shape whats_new.
Inputs: id (required), action (required), key, plan, +6 more.
recommend_toolsRecommend toolsBRead-onlyIdempotentInspect
Ranked best-fit tools for a goal, with why + caveat. Follows this ask only — saved tags do not change the ranking. On a new user's first call, also returns short onboarding questions (project types, platforms, budget, preferences, tools in use) for you to ask, then call set_preferences with tags only.
Inputs: goal (required), limit, budget, offset, +3 more.
save_preferencesSave your preferencesBIdempotentInspect
Replace the keyed-feed interest tags. Send allowed tags only (project types, platforms, budget, preferences) — do not send project names or other free text (they are dropped and never stored). Plus the feed mode ('by_interests' = only matching tools; 'all_new' = every new tool). Only used by whats_new.
Inputs: key, mode, interests.
scenarioScenario rankingCRead-onlyIdempotentInspect
Tools competing in one scenario, ranked by community sentiment, with compact strengths/weak spots here.
Inputs: slug (required), limit, verbose.
searchSearch toolsBRead-onlyIdempotentInspect
Find vibe coding / AI tools. Rows: id|name|category|$from/mo|free(1/0). Use fetch(id) for details.
Inputs: query (required), limit, offset, verbose.
set_preferencesSave preference tagsAIdempotentInspect
Store the user's onboarding answers as non-sensitive tags only: project_types, platforms, budget (free|under_20|any), preferences (nocode|code|open-source|free-tier), and tools_in_use (catalog ids). Unknown values are dropped — never send names, emails, code, project names or free text. Used by check_updates, not by recommend_tools. Optional key: pass a feed key (from subscribe, or /api/mcp?k=KEY) to keep this profile separate per project; without it, the anonymous client identity is used.
Inputs: key, budget, platforms, preferences, +2 more.
subscribeSubscribe to the feedAInspect
Create an anonymous feed key (no email/account). Save it in long-term memory / project instructions / rules, or connect with /api/mcp?k=KEY.
Inputs: no named parameters.
whats_newWhat's new for youAInspect
Daily feed. With key: honors the saved feed mode — by_interests: new items relevant to ANY saved project; all_new: every new item (tagged with a project when one matches). Max 3/day, one line each, never repeats. {new:0} = nothing. Call at most daily. Without key: stateless by since/interests. Never affects other tools.
Inputs: key, limit, since, interests.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Pick AI coding tools by goal: community-sentiment rankings, pricing, free tiers, alternatives.
Ship, discover and review vibe-coded projects on Shipyard, the invite-only feed for AI-built apps.
Backend for vibe coders. Connect Butterbase to any MCP-compatible AI coding tool and provision a full backend automatically — database, authentication, file storage, edge functions, and real-time — from a natural language prompt. No SQL, no configuration, no backend knowledge required. Free to start at butterbase.ai.
Build native iPhone apps and web apps by chatting. Vibecode's agent writes, builds and tests them.
Related MCP Servers
- AlicenseDqualityDmaintenanceFix your vibe coding prompts before they reach the AI. Scores and rewrites across 4 dimensions — no API key, no server, just npx. Now with codebase-aware context injection for design, database, API, auth, testing, and state management.25 npmMIT
- AlicenseAqualityBmaintenanceSocial layer for AI coding — DMs, presence, discovery, and multiplayer games between developers. 68 tools including messaging, presence, memory, and 27 multiplayer games.9405 npmMIT
- AlicenseNot gradedqualityCmaintenanceMCP turns vibe coding into a game. Steam-style achievements for Claude Code, Hermes and more.8 npm4MIT
- AlicenseAqualityDmaintenanceAssigns personality types to functions, rates variable name energy, and suggests aesthetic alternatives for code, providing an unscientific yet entertaining vibe assessment.152 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.