
Jan Zimprich MCP server
Which MCP servers are Jan Zimprich'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 2026-10-30
- Registry namedev.dryl/componentsverified in the MCP registry
The registry name sits under dryl.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-30
- Tools4
- Server calls itselfdryl-components
- Server version3.12.1
- Protocol version2025-06-18
On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 751 ms.
- Its tools do none of the product's use cases we checked: stream AI agent output into interactive Blazor interfaces; add human approval steps to Blazor agent workflows.
- Checked on 5 of the 7 days it takes to judge reliability.
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: 5 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring5 of the 7 daily checks it takes to print a share
- Median first answer799 ms
- Space in an agent's context≈ 601 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · build Blazor interfaces from prebuilt animated UI components
- cannot · stream AI agent output into interactive Blazor interfaces
- cannot · add human approval steps to Blazor agent workflows
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 →
search_componentsFind DRYL Blazor components (DRYL.Components and DRYL.Components.Agents) by name, title, category or purpose. Use this first when you need a component for a job; then call get_component for its exact API.
get_componentThe exact public API of one DRYL component: every parameter with type, default and description, the members of every enum it uses, its public methods and a canonical Razor example. DRYL variants are enums, never strings: write an enum…
get_tokensThe CSS custom properties DRYL styles itself with, grouped (colors, glass, accent, spacing, radius, motion, …), with the dark value and — where light mode differs — the light value. Reference these with var(--name) in your CSS instead of…
validate_markupCheck a Razor snippet's <Dryl…> tags against DRYL's real API before you finish: unknown components, unknown parameters, and enum parameters given a string or a member that does not exist — each with a suggested fix. Call it on every DRYL…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"components": {
"type": "http",
"url": "https://components.dryl.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http dryl https://components.dryl.dev/mcpclaude.ai, ChatGPT and other clients: add https://components.dryl.dev/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.
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.