# VibeCodePicks (remote · vibecodepicks.com)

Pick AI coding tools by goal: community-sentiment rankings, pricing, free tiers, alternatives.

- Trust score: 72/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `vibecodepicks.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/suanrongbaicai-vibecodepicks/api-mcp-2.md), [page](https://verifymcp.io/servers/suanrongbaicai-vibecodepicks/api-mcp-2)

## Channel facts

- Endpoint: `https://vibecodepicks.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.4.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (forget_me).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2772 tokens (~213/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the VibeCodePicks MCP server?

VibeCodePicks is a hosted endpoint at https://vibecodepicks.com/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http suanrongbaicai-vibecodepicks 'https://vibecodepicks.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "suanrongbaicai-vibecodepicks": {
      "url": "https://vibecodepicks.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "suanrongbaicai-vibecodepicks": {
      "type": "http",
      "url": "https://vibecodepicks.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.suanrongbaicai-vibecodepicks]
url = "https://vibecodepicks.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "suanrongbaicai-vibecodepicks": {
      "type": "remote",
      "url": "https://vibecodepicks.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add suanrongbaicai-vibecodepicks --url 'https://vibecodepicks.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  suanrongbaicai-vibecodepicks:
    url: "https://vibecodepicks.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "suanrongbaicai-vibecodepicks": {
      "Transport": "http",
      "Url": "https://vibecodepicks.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add suanrongbaicai-vibecodepicks -t streamable-http -u 'https://vibecodepicks.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "suanrongbaicai-vibecodepicks": {
      "type": "http",
      "url": "https://vibecodepicks.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 71, +4)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “save_preferences” rewrote its description, which is the text the model reads
- [security] Tool “scenario” rewrote its description, which is the text the model reads
- [security] Tool “search” rewrote its description, which is the text the model reads
- [security] Tool “subscribe” rewrote its description, which is the text the model reads
- [security] Tool “whats_new” rewrote its description, which is the text the model reads
- [security] Tool “compare_tools” rewrote its description, which is the text the model reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [security] Tool “forget_me” rewrote its description, which is the text the model reads
- [security] Tool “list_alternatives” rewrote its description, which is the text the model reads
- [security] Tool “list_categories” rewrote its description, which is the text the model reads
- [security] Tool “list_scenarios” rewrote its description, which is the text the model reads
- [security] Tool “log_choice” rewrote its description, which is the text the model reads
- [security] Tool “recommend_tools” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 16% → 100%
- [functional] Schema quality: fair → excellent
- [functional] Destructive annotations: 100 → pass
- [cosmetic] “forget_me” reworded the description of “key”
- [cosmetic] “recommend_tools” reworded the description of “can_code”
- [cosmetic] “recommend_tools” reworded the description of “goal”
- [cosmetic] “recommend_tools” reworded the description of “limit”
- [cosmetic] “recommend_tools” reworded the description of “offset”
- [cosmetic] “recommend_tools” reworded the description of “platform”
- [cosmetic] “recommend_tools” reworded the description of “verbose”
- [cosmetic] “save_preferences” reworded the description of “key”
- [cosmetic] “save_preferences” reworded the description of “mode”
- [cosmetic] “save_preferences” reworded the description of “projects”
- [cosmetic] “scenario” reworded the description of “limit”
- [cosmetic] “scenario” reworded the description of “slug”
- [cosmetic] “scenario” reworded the description of “verbose”
- [cosmetic] “search” reworded the description of “limit”
- [cosmetic] “search” reworded the description of “offset”
- [cosmetic] “search” reworded the description of “query”
- [cosmetic] “search” reworded the description of “verbose”
- [cosmetic] “whats_new” reworded the description of “interests”
- [cosmetic] “whats_new” reworded the description of “key”
- [cosmetic] “whats_new” reworded the description of “limit”
- [cosmetic] “whats_new” reworded the description of “since”
- [cosmetic] “compare_tools” reworded the description of “a”
- [cosmetic] “compare_tools” reworded the description of “b”
- [cosmetic] “compare_tools” reworded the description of “verbose”
- [cosmetic] “fetch” reworded the description of “fields”
- [cosmetic] “fetch” reworded the description of “id”
- [cosmetic] “fetch” reworded the description of “verbose”
- [cosmetic] “list_alternatives” reworded the description of “limit”
- [cosmetic] “list_alternatives” reworded the description of “offset”
- [cosmetic] “list_alternatives” reworded the description of “tool”
- [cosmetic] “list_alternatives” reworded the description of “verbose”
- [cosmetic] “list_categories” reworded the description of “verbose”
- [cosmetic] “log_choice” reworded the description of “action”
- [cosmetic] “log_choice” reworded the description of “id”
- [cosmetic] “log_choice” reworded the description of “key”
- [cosmetic] “log_choice” reworded the description of “period”
- [cosmetic] “log_choice” reworded the description of “rating”
- [cosmetic] “recommend_tools” reworded the description of “budget”

### 2026-11-01 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 62, 0)

- [security regression] DNSSEC: pass → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “log_choice” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 80 → 97
- [functional improvement] Tool coverage: 6% → 16%
- [functional] Server version: 2.4.0 → 2.5.1
- [cosmetic] “log_choice” added an optional parameter “fell_short”
- [cosmetic] “log_choice” added an optional parameter “period”
- [cosmetic] “log_choice” added an optional parameter “plan”
- [cosmetic] “log_choice” added an optional parameter “price_usd”
- [cosmetic] “log_choice” added an optional parameter “rating”
- [cosmetic] “log_choice” added an optional parameter “worked”
- [cosmetic] “log_choice” added an optional parameter “combo”
- [cosmetic] Tool “log_choice” changed its title: Log a choice → Log a choice or purchase

## MCP tools (13)

### `search` (~204 tokens)

Search tools

Keyword search over VibeCodePicks' reviewed AI coding and AI creation tools. Use when the user names a tool or a kind of tool ('is there an AI tool for deploying my app', 'find a no-code SaaS builder') and you need tool ids. Not for 'which is best for me' (use recommend_tools). Input: `query` (plain words, e.g. 'no-code SaaS builder'); `limit` (default 5), `offset` for paging. Returns one row per tool: id|name|category|lowest paid $/month|has free tier (1/0), and the next offset. Call fetch(id) for details.

Input parameters:

- `limit` (integer): number of results, default 5
- `offset` (integer): paging offset from the previous result
- `query` (string, required): plain words, e.g. 'no-code SaaS builder'
- `verbose` (boolean): returns long-form fields

### `fetch` (~186 tokens)

Get tool details

Get one tool's profile when the user asks about a specific tool ('what does Cursor cost', 'does Bolt have a free plan', 'what's Lovable bad at'). Input: `id` from search/recommend results (e.g. 'cursor'); optional `fields` (summary, description, best_for, not_for, skill, coding, pricing, platforms, strengths, weaknesses, alternatives, video, compare, official, all). Default returns summary, who it's best for, lowest paid price and plan text, free tier text, 2 strengths, 2 weaknesses, go link (tracked link to the official site) and the VCP page URL to cite.

Input parameters:

- `fields` (array): which profile fields to return
- `id` (string, required): tool id from search/recommend results (e.g. 'cursor')
- `verbose` (boolean): returns long-form fields

### `recommend_tools` (~280 tokens)

Recommend tools

Recommend tools for what the user is building. Use for 'what should I use to build X', 'best free tool for a beginner who can't code', 'which AI tool fits my project'. Fill inputs from the conversation instead of asking when you already know them: `goal` (the project in plain words, required), `can_code` (true/false), `budget` ('free' or max USD per month), `platform` (e.g. 'web', 'ios', 'mac'), `limit`/`offset`. Returns ranked tools with a one-line why, the main caveat (what it is not good for), price from, free tier flag, page URL and go link. Rankings are not affected by saved preferences or payments. If the user has a feed key and later picks one, offer log_choice.

Input parameters:

- `budget` (string): 'free' or max USD per month
- `can_code` (boolean): whether the user can code (true/false)
- `goal` (string, required): the project in plain words
- `limit` (integer): number of results, default 5
- `offset` (integer): paging offset from the previous result
- `platform` (string): target platform, e.g. 'web', 'ios', 'mac'
- `verbose` (boolean): returns long-form fields

### `compare_tools` (~145 tokens)

Compare two tools

Compare two named tools side by side when the user asks 'A vs B' or 'should I use A or B'. Inputs: `a`, `b` tool ids (use search to resolve names). Returns for each: category, lowest paid price and plan text, free tier, skill level, needs coding, best for, 2 strengths, 2 weaknesses, and the VCP comparison page URL. For more than two tools use recommend_tools or scenario.

Input parameters:

- `a` (string, required): first tool id (use search to resolve names)
- `b` (string, required): second tool id (use search to resolve names)
- `verbose` (boolean): returns long-form fields

### `list_alternatives` (~139 tokens)

Find alternatives

List tools that can replace a given tool, for 'alternatives to X', 'cheaper/free tool like X', 'I'm leaving X'. Input: `tool` id; `limit`/`offset`. Returns rows id|name|lowest paid $/month|free tier (1/0) and the VCP alternatives page URL. Then fetch or compare_tools for details.

Input parameters:

- `limit` (integer): number of results, default 5
- `offset` (integer): paging offset from the previous result
- `tool` (string, required): tool id to find alternatives for
- `verbose` (boolean): returns long-form fields

### `list_scenarios` (~106 tokens)

List scenarios

List the use cases VibeCodePicks tracks (e.g. landing-page, mobile-app, code-review, ai-game-development) with how often each was discussed and the top 3 tools people mention for it, from a dated window of public community posts. Use to find a scenario slug, or when the user asks 'what do people use for X'. No input. Returns slug, title, mention count, top tool ids, page URL, and the date window.

### `scenario` (~151 tokens)

Scenario ranking

Rank the tools people actually use for one use case, by number of community mentions in a dated window, with what users praise and complain about. Use for 'what's the best AI code review tool according to users', 'what do people use for mobile apps'. Input: `slug` from list_scenarios; `limit`. Returns per tool: id, mention count, main strengths and weak spots (M = most mentions, S = some), the date window and last update date. Say the window when quoting.

Input parameters:

- `limit` (integer): number of results, default 5
- `slug` (string, required): scenario slug from list_scenarios
- `verbose` (boolean): returns long-form fields

### `list_categories` (~89 tokens)

List categories

List VibeCodePicks' tool categories (e.g. editor, terminal, builder, agent, video, image) with the tool ids in each. Use when the user wants to browse a whole kind of tool ('show me all terminal coding agents') or you need valid category names. Takes no required input. Returns category → tool ids.

Input parameters:

- `verbose` (boolean): returns long-form fields

### `whats_new` (~227 tokens)

What's new for you

Check for new AI coding tools that match the user's saved projects. Use once a day (e.g. at the start of a work session) when the user has a feed key, or when they ask 'anything new for my project?'. Inputs: `key` (uses saved projects and mode, never repeats items, max 3 per day); without a key, optional `since` (date) and `interests` for a one-off look. Returns `new` count and one line per item: name, category, [project it matches], one-line summary, page URL. `{new:0}` means nothing new — say so briefly or stay silent. Has no effect on other tools.

Input parameters:

- `interests` (array): interest tags to filter by, for a one-off look without a key
- `key` (string): the user's anonymous feed key from subscribe
- `limit` (integer): number of results, default 5
- `since` (string): only tools added on or after this date, format YYYY-MM-DD (default: 7 days ago)

### `subscribe` (~88 tokens)

Subscribe to the feed

Start the user's personal new-tools watch. Only after the user has agreed to the feed (explain it first; see server instructions). Creates an anonymous key — no email or account. No input. Returns `key` and a note. Save the key in long-term memory / project rules (or connect with /api/mcp?k=KEY), then call save_preferences with their projects and chosen mode.

### `save_preferences` (~190 tokens)

Save your preferences

Save which projects the user wants watched for new tools, e.g. 'my Next.js SaaS: auth, deploy, payments'. Use after subscribe, or when the user says they started/finished a project or changed interests. Replaces the whole list each time, so send all projects. Inputs: `key`; `projects` [{name, interests: short tags}]; `mode` 'by_interests' (only matching new tools) or 'all_new' (every new tool). Returns ok, project count, mode. Only whats_new reads this; it never changes search or recommendations.

Input parameters:

- `key` (string): the user's anonymous feed key from subscribe
- `mode` (string): 'by_interests' (only matching new tools) or 'all_new' (every new tool)
- `projects` (array, required): list of projects to watch (replaces the whole list each time)

### `log_choice` (~285 tokens)

Log a choice or purchase

Record what the user decided about a tool for their project, after asking them: picked, rejected, tried, starred, purchased (a paid plan), or feedback (later, with a 1–5 rating and short what worked / fell short). Use when the user says 'I'll go with Bolt', 'Cursor didn't work for me', 'I bought Lovable Pro'. Never log silently. Inputs: `id`, `action`, optional `key`, and for purchased/feedback: plan, price_usd, period, rating, worked, fell_short, combo (other tool ids used together). No personal data. Returns ok. picked/rejected shape whats_new; it never changes rankings.

Input parameters:

- `action` (string, required): what the user decided
- `combo` (array): Ids of other tools used together with this one
- `fell_short` (string): What fell short (short, no personal data)
- `id` (string, required): tool id
- `key` (string): the user's anonymous feed key from subscribe
- `period` (string): billing period
- `plan` (string): Plan bought, e.g. 'Pro monthly'
- `price_usd` (number): Price paid per period in USD
- `rating` (integer): 1-5 rating for feedback
- `worked` (string): What worked well (short, no personal data)

### `forget_me` (~84 tokens)

Forget me

Permanently delete everything stored for the user's feed key: projects, interests, items shown, logged choices and purchases. Use when the user asks to stop the feed, delete their data, or be forgotten. Input: `key`. Returns ok and deleted count. Cannot be undone; confirm with the user first.

Input parameters:

- `key` (string): the user's anonymous feed key from subscribe

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/suanrongbaicai-vibecodepicks/api-mcp-2#diagnostics

## Score history

- 2026-11-05: 72
- 2026-11-04: 72
- 2026-11-03: 71
- 2026-11-02: 71
- 2026-11-01: 67
- 2026-10-31: 66
- 2026-10-30: 66
- 2026-10-29: 65
- 2026-10-28: 65
- 2026-10-27: 64
- 2026-10-26: 64
- 2026-10-25: 63
- 2026-10-24: 63
- 2026-10-23: 62
- 2026-10-22: 62
- 2026-10-21: 62

## Common questions

### What is the VibeCodePicks MCP server?

VibeCodePicks is an MCP server listed in the public MCP registry as io.github.suanrongbaicai/vibecodepicks. Pick AI coding tools by goal: community-sentiment rankings, pricing, free tiers, alternatives. This page covers its hosted endpoint (https://vibecodepicks.com/api/mcp).

### Is the VibeCodePicks MCP server safe to use?

VibeCodePicks scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the VibeCodePicks MCP server expose?

VibeCodePicks exposes 13 tools: search, fetch, recommend_tools, compare_tools, list_alternatives, and 8 more. Their descriptions and schemas cost roughly 2,174 tokens of context every time the server is loaded.

### Does the VibeCodePicks MCP server require authentication?

No. We connected to VibeCodePicks without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the VibeCodePicks MCP server still maintained?

VibeCodePicks is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://vibecodepicks.com/api/mcp
- Repository: https://github.com/suanrongbaicai/vibecodepicks
- Website: https://vibecodepicks.com/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/suanrongbaicai-vibecodepicks/api-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/suanrongbaicai-vibecodepicks/api-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/suanrongbaicai-vibecodepicks/api-mcp-2