New or changed MCP server use
An MCP server is used for the first time, or its recorded connection changes.
Why it is risky
Section titled “Why it is risky”An unexpected server can introduce a new recipient for data and a new source of tool behavior. First use is useful context even when nothing malicious happens.
Example
Section titled “Example”A session begins using a server that the user did not add to the project or recognize from their setup.
This is a fictional example, not an event from a customer.
What Omnodex Detects
Section titled “What Omnodex Detects”With machine state available, the rule records first use on that machine and changes to known transport or host information. Without that state, it falls back to first use in the session. Built-in tools are excluded.
| Rule ID | Event category | Tier | Base severity |
|---|---|---|---|
RULE_SUPPLY_CHAIN_NEW_MCP_SERVER | supply_chain | Community | LOW |
Base severity is the rule default. A finding involving content saved for later execution may have a lower severity. Your loaded rule version and event details determine the finding you see.
What to check next
Section titled “What to check next”Check the server against your configured integrations and expected connection details. Treat the LOW base severity as a prompt to verify identity.
False positives
Section titled “False positives”A new authorized installation, an expected endpoint change, or rebuilt machine state can produce a normal first-use finding. Session-only evaluation may report a known server again.
False negatives
Section titled “False negatives”A malicious server already present in the recorded baseline, a server whose identity is unchanged, or installation without a captured invocation may not trigger it.
Technical details
Section titled “Technical details”The finding reflects observed use, not the moment a server was installed. Connection-change detection depends on transport metadata supplied during evaluation. Changes to a known server’s version, configuration or tools are covered by MCP server or tool changed.
A finding describes a pattern in captured activity. Review the original call, its result, and the task context before concluding that harm occurred. Absence of a finding does not establish that an operation is safe.