
nice to have MCP server
Which servers in the official MCP registry are nice to have's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry nameapp.nicetohave/kitsverified in the MCP registry
The registry name sits under nicetohave.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools5
- Server calls itselfnice-to-have
- Server version1.1.0
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 113 ms.
- Its tools do none of the product's use cases we checked: produce short videos with subtitles for YouTube; generate sprite sheets and images with Gemini.
- Checked on 3 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 3 of 5 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer190 ms
- Space in an agent's context≈ 756 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 90 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 3 of 5
What an agent can do with it
- not sure · make LINE sticker sets from generated characters
- cannot · produce short videos with subtitles for YouTube
- cannot · generate sprite sheets and images with Gemini
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_kitsSearch nice to have, a shelf of ready-made build kits for Claude Code and Codex (step-by-step recipes with fixes for pitfalls found in real work). Use this whenever the user wants to make or build something — slides/decks, LINE stickers…
get_kitGet the details of one nice to have kit by id: what it does, the first three decisions, what you need, and the fixes it contains. Use after search_kits to explain a kit to the user.
open_kitUse when the user pasted a nice to have line such as "…https://nicetohave.app/g/XXXXXXXX-YYYYYYYYYY のとおりに取り込んで" and you cannot download from nicetohave.app directly (for example, a cloud session with restricted network). Checks the…
get_kit_fileGet the content of one file listed by open_kit. Save it exactly as returned, at the same relative path inside the new kit folder. Long files come in parts: if the answer says part 1/3, call again with part 2 and 3 and append them in order…
list_kitsList every kit currently on the nice to have shelf (id, name, what it does, page URL).
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"kits": {
"type": "http",
"url": "https://nicetohave.app/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http nicetohave https://nicetohave.app/api/mcpclaude.ai, ChatGPT and other clients: add https://nicetohave.app/api/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.