Bridges the active *.darwinium.com tab to a local MCP server for external LLM clients (Claude Desktop, Claude Code).
Users
21
+15 in 30 days
Rating
0.0 / 5
unchanged in 30 days
Ratings
0
0 in 30 days
Store rank
#149K
#124K among extensions
Version
0.0.2
updated 3 Sep 2026
Users
monthly, 1 months
Latest, 16 Oct 2026:21 usersMove the mouse over the chart for any month
Ratings count
monthly, 1 months
Latest, 16 Oct 2026:0 ratingsMove the mouse over the chart for any month
The Chrome Web Store rounds user counts down to the leading digit, so the user line moves in steps. The ratings count is exact and is the better signal of real adoption.
About Darwinium Portal MCP
Darwinium Portal MCP connects an AI assistant to the Darwinium portal you already
have open in your browser, so you can investigate traffic and author rules by
asking for what you want in plain language.
ABOUT DARWINIUM
Darwinium is a digital security and fraud prevention platform. It instruments a
customer journey — registration, login, checkout, payment, account change — at the
perimeter, profiling each step for device, network, behavioural and identity
signals. Those signals feed the features, models and rules that decide, event by
event, whether to accept, challenge or reject. Fraud teams use the Darwinium portal
to investigate what actually happened on live traffic, and to write the rules that
decide what happens next.
WHAT THIS EXTENSION DOES
The extension is half of a two-part bridge. It reads the commands the portal page
publishes and relays them to a local MCP (Model Context Protocol) server that your
assistant runs on the same machine. The assistant can then see the page you are
looking at and operate it on your behalf.
FOR FRAUD ANALYSTS
- Query live event data in Investigations using Darwinium query syntax, and get
counts, aggregates, top-N breakdowns and quantile distributions back in the
conversation.
- Find the right attribute without memorising the schema. Search the attribute
index in plain terms — "device identifier", "email", "geolocation" — and get the
correct syntax, data type and example values.
- Pull journey metadata and step names, browse and search the label catalogue, and
apply labels to events.
- Read dashboards and graphs, including screenshots, and have them interpreted
against the underlying data rather than guessed at from a picture.
FOR RULE AND SIGNAL AUTHORS
- Draft signal conditions grounded in your workspace's real feature and signal
names, which the assistant reads from the page instead of inventing.
- Validate a proposed condition and count how many events it would actually match,
before you commit to it.
- Check workspace diagnostics after an edit, so a change is confirmed clean rather
than assumed clean.
- Move between Investigations, Workflows, Labels and Dashboards without losing the
thread of the conversation.