
Kwixa MCP server
Which MCP servers are Kwixa's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-28
- Registry nameuk.co.kwixa/hotshot-gearverified in the MCP registry
The registry name sits under kwixa.co.uk. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools3
- Server calls itselfhotshot-gear
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 598 ms.
- Its tools do none of the product's use cases we checked: score darts games on a 301, 501 or 701 board; work back from a serving time to a Christmas dinner timeline.
Once connected
- Parameters are untyped or undescribed in 3 of 3 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 score68 of 100answers 100 · does the job 0 · definitions 83 · context 100 · connects 100
- What an agent can do with it0 of 2 use cases
- Answered100% of days8 of 8 daily checks
- Median first answer415 ms
- Space in an agent's context≈ 594 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 3 of 3
What an agent can do with it
- cannot · score darts games on a 301, 501 or 701 board
- not sure · convert oven temperatures and times to air fryer settings
- cannot · work back from a serving time to a Christmas dinner timeline
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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 →
find_gearRecommends up to three darts-equipment items (steel-tip and soft-tip darts, bristle and electronic dartboards, flights, shafts, cases, oche mats, lighting, surrounds) from a curated UK catalogue, ranked by fit, not by payment. Each result…
get_itemReturns the full record for one item by id (ids come from find_gear): specs, fit fields, why and why not, evidence links, retailers that stock it (names only, no links), provenance and when it was last checked.
compareSide-by-side specs and fit notes for two or three catalogue items by id.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"hotshot-gear": {
"type": "http",
"url": "https://mcp.kwixa.co.uk/"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http kwixa https://mcp.kwixa.co.uk/claude.ai, ChatGPT and other clients: add https://mcp.kwixa.co.uk/ 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.
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.