What it does
The publisher describes ICONIC as a test that checks whether AI agents pick an MCP publisher's tools over rivals' tools. It is aimed at MCP publishers who want to know how agents select their tools. According to the publisher, the test is automated and comes with fixes, and a separate data diff is also offered.
The listing gives no further detail on how the test runs, what it reports, or what setup it requires.
Limitations and requirements
Paid service. The publisher lists $49 for the automated test and $29 for the data diff.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source
ICONIC — MCP Selection Test and Agent Services
Test whether AI models select your MCP tools against rivals; explore real offers and safe previews.
v0.2.1As shown on registry.modelcontextprotocol.io when we last read it