KentekenKompas is answering right now. Last checked 8 min ago. It exposes 7 tools.
Read-only Dutch vehicle knowledge, comparisons, terminology and cited sources for AI clients.
Uptime history
67 days of history · worst day 93%
67 days agonow
100.0%
Uptime 24h
91 of 91 checks
7
Tools
read from the server
247 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 14
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 September 2026. No other catalogue keeps this.
24 Sep
a tool description was rewritten
compare_vehicle_models
21 Sep
7 tool descriptions were rewritten
compare_vehicle_models, explain_dutch_vehicle_term, get_answer_context and 4 more
21 Sep
6 tools changed the parameters they ask for
compare_vehicle_models, explain_dutch_vehicle_term, get_answer_context and 3 more
Nothing serious here today
Today is the operative word: we check KentekenKompas every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.
run in your terminal
claude mcp add vehicle-knowledge --transport http https://api.kentekenkompas.nl/mcpSettings → Connectors → Add custom connector, then paste this address
https://api.kentekenkompas.nl/mcp~/.codex/config.toml
[mcp_servers.vehicle-knowledge]
url = "https://api.kentekenkompas.nl/mcp".cursor/mcp.json
{
"mcpServers": {
"vehicle-knowledge": {
"url": "https://api.kentekenkompas.nl/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"vehicle-knowledge": {
"type": "http",
"url": "https://api.kentekenkompas.nl/mcp"
}
}
}Available tools 7
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
answer
get_answer_context
Read one existing Direct Answer by exact answerId; no text generation. Use search_vehicle_knowledge when the ID is unknown, get_model_context with includeAnswers=true for a model's answers, or explain_dutch_vehicle_term for a term key. Do not pass a free-text question as an ID. Unknown ID returns ANSWER_NOT_FOUND; preserve the returned evidence and limitations. Public read-only access; no knowledge writes. Calls consume rate limits.
compare
compare_vehicle_models
Read one stored sourceModelKey-to-targetModelKey relation, not a generated comparison. Returns model keys, relationType/meaning and rationale, with evidence, sources and citations. Preserve classification and limitations; do not strengthen the stored claims. Only DIRECT_ALTERNATIVE denotes a direct alternative. Existing models need not have a relation; the reverse direction is a separate lookup. Use get_model_context for one model and its peers, or search_vehicle_knowledge to discover keys. Unknown model returns MODEL_NOT_FOUND; self/missing relation returns COMPARISON_NOT_AVAILABLE. Public read-only access; no knowledge writes. Calls consume rate limits.
explain
explain_dutch_vehicle_term
Read one existing Dutch vehicle definition by lowercase term slug or term.<slug>. Use search_vehicle_knowledge for free text or an unknown key, get_answer_context for a known answerId, or get_model_context for model-specific context. No fuzzy definition generation. Unknown valid key returns TERM_NOT_FOUND; uppercase/spaced inputs fail validation before normalization. Public read-only access; no knowledge writes. Calls consume rate limits.
fuel
get_fuel_price_context
Read the existing fuel-price provenance/status, not current pump prices or a vehicle's consumption. No arguments. Currently succeeds with SOURCE_REQUIRED_AT_RUNTIME and prices=[] because no validated current-price adapter is configured. Use get_source_context for an exact source ID or search_vehicle_knowledge for broader fuel knowledge. Never treat empty prices as zero or invent a current price. Public read-only access; no knowledge writes. Calls consume rate limits.
model
get_model_context
Read model-level knowledge for an exact modelKey; optionally include its existing Direct Answers. Use search_vehicle_knowledge to discover a key, get_answer_context for a known answerId, or compare_vehicle_models for a known pair. Not a license-plate lookup or individual-car assessment. Unknown key returns MODEL_NOT_FOUND; incomplete coverage remains a successful result with coverage and limitations. Public read-only access; no knowledge writes. Calls consume rate limits.
source
get_source_context
Read one public SOURCE or SOURCE_GROUP by exact opaque sourceId to inspect provenance, freshness and limitations. Use search_vehicle_knowledge to discover sources; get_model_context or get_answer_context retrieves the knowledge a source supports. Not a search by URL or source label. Never split composite-looking IDs. Unknown ID returns SOURCE_NOT_FOUND. Public read-only access; no knowledge writes. Calls consume rate limits.
vehicle
search_vehicle_knowledge
Discover public models, existing answers, terms and provenance from free text when no canonical key is known. Use get_model_context, get_answer_context, explain_dutch_vehicle_term or get_source_context for known IDs; compare_vehicle_models for a known model pair; get_fuel_price_context for fuel-source status. Results use deterministic lexical/intent relevance, never AI confidence; no supported match returns data=[] with limitations. Public read-only access; no knowledge writes. Calls consume rate limits.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.kentekenkompas.nl/mcp | streamable-http | answering | 272 ms | 8 min ago |
Alternatives to KentekenKompas
same job, measured the same way
A
Addness
by addnesstech
Company brain for teams and AI: read and write goals, to-dos, comments, and knowledge.
S
SanctionScreen
by sanctionsscreen
Screen counterparties and enrich companies for AI agents — sanctions checks, cited sources.
AICostBudget AI API Pricing
by aicostbudget
Read-only source-linked AI API prices, comparisons, cost estimates, and price changes.
VerifiedPricing
by pucilpet
Source-linked SaaS pricing records and scenario comparisons for AI agents.
AI TPM Knowledge
by aitpm
Read-only, source-linked AI, architecture, governance and technical product articles from AI TPM.
OpenDont
by opendont
Sourced public knowledge for AI agents: search and read records with evidence; moderated writes.
KG-SSOT
by marciocar
Company-brain knowledge graphs: confirmed claims cite sources, and decisions get revisited
Zekra
by fadymondy
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
KentekenKompas — questions
Answers built from our own checks of this server.
What can KentekenKompas do?
It exposes 7 tools, read directly from the server on our last check. Among them: compare_vehicle_models, explain_dutch_vehicle_term, get_answer_context, get_fuel_price_context, get_model_context, get_source_context and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is KentekenKompas working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 247 ms. The bar chart above shows every period we have measured.
How do I connect KentekenKompas?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does KentekenKompas need an API key?
No. KentekenKompas completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is KentekenKompas?
It answers our handshake in 247 ms on average, which is faster than 56% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.