
TracePass MCP server
Which MCP servers are TracePass'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 2026-10-27
- Registry nameeu.tracepass/complianceverified in the MCP registry
The registry name sits under tracepass.eu. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools9
- Server calls itselftracepass-compliance
- Server version1.20.3
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 472 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- create_draft_passport, update_profile, delete_profile change data without a sign-in: anyone with the address can call them.
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: 2 so far
- Use217 npm downloads a week1 GitHub stars
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer497 ms
- Space in an agent's context≈ 3,480 tokensthe definitions of all its tools (9), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · generate hosted passport pages with GS1 digital link QR codes
- not sure · suggest product data values from existing datasheets for review
- not sure · track which passport fields remain open for suppliers
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
- Tools that change data, on a server that answers without a sign-in: create_draft_passport, update_profile, delete_profile
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 →
scope_checkChecks whether EU law requires a Digital Product Passport for a type of product, from when, and what the law requires of each role. Use it for "do I need a passport", "from when", "who is responsible", whether that responsibility can be…
required_fieldsLists the data a passport must contain for a product category, with the article requiring each field, who may see it, how often it changes, and whether it usually comes from the maker or a supplier. Call it without `group` for a summary…
what_changedReports changes in EU passport law and standards for the user's categories since a date (default: since they last asked). Use it for "what's new" or "has X been adopted". Items marked "Planned, not law yet" are upcoming obligations, not…
registry_guidanceExplains the EU DPP Registry and the technical side: registration in the registry, identifiers, QR and data carriers, data formats (JSON, HTML, data models) and standards, and where passport data is kept. Each point carries the date of…
create_draft_passportCreates a **draft** passport in the user's own TracePass account from facts they stated. Use it whenever the user asks to create a passport, including "create and publish": create the draft, then say that publishing is done by the user in…
report_answerUse it when the user says an answer was wrong or unclear. Pass their words and the `ruleIds` of the answer. The report goes to a review queue. Use only what this tool returns: add no facts, dates or articles of your own, not even today's…
get_profileShows the company facts the assistant has stored (categories, markets, role, own-brand flag, etc.) and when they were last updated. Use only what this tool returns: add no facts, dates or articles of your own, not even today's date. Keep…
update_profileSaves or corrects company facts. Use it when the user states a lasting fact about their company (role, categories, markets, own-brand), or to save a `learnable` fact from a result. The update merges the given facts into the existing…
delete_profileDeletes every stored company fact. Use it only when the user explicitly asks to delete their profile. This is a separate tool so the assistant asks for confirmation before running it. Use only what this tool returns: add no facts, dates…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"compliance": {
"type": "http",
"url": "https://ai.tracepass.eu/compliance/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http tracepass https://ai.tracepass.eu/compliance/mcpclaude.ai, ChatGPT and other clients: add https://ai.tracepass.eu/compliance/mcp as a custom connector in the settings.
- eu.tracepass/tracepassanswers, 7 toolsverified in the MCP registry
OpenAPI spec
52 paths, read 2026-10-27. Open the spec ↗
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.