
emendrix MCP server
Which MCP servers are emendrix'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 nameeu.emendrix/emendrixverified in the MCP registry
The registry name sits under emendrix.eu. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools8
- Server calls itselfemendrix
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 555 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 5 of the 7 days it takes to judge reliability.
Once connected
- For "look up chemical entries by CAS or EC number", the likely first call is find_substance.
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
- Answeredmeasuring5 of the 7 daily checks it takes to print a share
- Median first answer542 ms
- Space in an agent's context≈ 3,218 tokensthe definitions of all its tools (8), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · track provision-level changes across 86 watched EU acts
- can do · look up chemical entries by CAS or EC number
- not sure · watch regulation provisions from CI and open issues on change
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 →
list_actsList the acts the record holds, with each act's label, aliases and sector from the site catalogue, its newest version, `updated_on` and the counts its index carries. `query` matches names case-insensitively; `domain` matches the…
find_provisionsFind touched provisions of one act whose canonical location string or stored heading contains `query`, each with its newest row. It never reads law text; an empty list means no touched provision of the act has that name in the window…
changes_sinceList recorded changes whose `basis` date is on or after `since`, newest first, with each row's event and provision pages: `updated_on` (the event or its latest repair), `detected_on` (when the run saw the event) or `in_force` (the…
provision_historyEvery recorded change to one top-level provision, newest first, with the window the record covers for the act. An empty list means no recorded change to that provision in the window, and the result says so in words. Every list is complete…
get_changeOne change in full: the verbatim text before and after, each side cut at `max_chars` (1 to 50000) with a marker '[… N characters omitted, continue with offset=M]' and paged by `offset`; the cited sentences with their URLs…
get_eventOne event of one act: its counts, repairs and stored corroboration (each signal's units, the pairwise agreements and disagreements), the units only the metadata or only the instruction parse names, and every row of the event. Every list…
list_disputedDisputed rows grouped by their stored `dispute_reason`, each group with the sentence the site prints for that code. `omitted` counts rows past `limit`. An empty list means no recorded change in the window is disputed for that filter…
find_substanceFind the entries that print a CAS or EC number, given with or without hyphens, in the newest version of each act the record holds, and every recorded change to them, each with its date, the amending act the change names and the file it…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"emendrix": {
"type": "http",
"url": "https://emendrix.eu/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http emendrix https://emendrix.eu/mcpclaude.ai, ChatGPT and other clients: add https://emendrix.eu/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.
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.