
WerkCV MCP server
Which MCP servers are WerkCV'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 2026-10-21
- Registry namenl.werkcv/cv-checkverified in the MCP registry
The registry name sits under werkcv.nl. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools3
- Server calls itselfwerkcv-cv-check
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 187 ms.
- Whether its tools do the product's job has not been judged yet.
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 score87 of 100answers 100 · definitions 100 · context 100 · use 0 · connects 100
- Answered100% of days15 of 15 daily checks
- Median first answer561 ms
- Space in an agent's context≈ 729 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · build a CV from a template or uploaded file
- not sure · check CV content in a live preview while typing
- not sure · download a finished CV as a PDF
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 →
check_cvGrade a CV (cv, curriculum vitae, résumé) for the Dutch job market: 0-100 score plus a 1-10 grade, the three fixes to make first with the exact lines they refer to, and ATS readability. Use when the user asks 'is my CV good', 'check my…
match_vacancyCompare a CV with one vacancy (vacature, job ad), requirement by requirement, with exact quotes from both, missing ATS keywords and the fixes to make first. Use when the user asks 'do I fit this job', 'past mijn cv bij deze vacature' or…
open_in_editorOpen the CV, and optionally the vacancy, in the WerkCV editor to edit it and download a PDF. No account needed. Returns a single-use link that expires after 60 minutes; the text is deleted when the link is opened. Call when the user wants…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"cv-check": {
"type": "http",
"url": "https://werkcv.nl/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http werkcv https://werkcv.nl/api/mcpclaude.ai, ChatGPT and other clients: add https://werkcv.nl/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.
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.