AGENTKIT/WORKS

Ref — AI search visibility

Paid MCP server that gives AI coding agents fast, token-efficient access to up-to-date documentation for APIs and libraries, so agents stop hallucinating against stale training data · ref.tools

Cited in 0 of 10 buyer queries (0%)

Rank 53 of 111 on the index · checked 2026-09-06 · every row below is a measured result, not an estimate

THE QUERIES, AND WHO GETS NAMED INSTEAD

Buyer queryRefNamed instead
best MCP server for documentationNot cited—
how do I stop my AI coding agent from hallucinating API docsNot cited—
Context7 alternativesNot cited—
how to give Claude Code up to date library documentationNot cited—
best paid MCP serverNot cited—
how to reduce token usage when my coding agent searches documentationNot cited—
MCP server that searches library docs for coding agentsNot cited—
context7 vs deepwikiNot cited—
best way to give Cursor access to the latest API documentationNot cited—
how do I keep my AI agent from writing code against outdated library versionsNot cited—

Method: each query, phrased the way a buyer would ask, was run once on the date shown by a Claude (Anthropic) research agent using its web-search tool (English, no location targeting), recording which products the results would lead an assistant to name. “Cited” meansRef was named or its site was used as a source; audits from late October 2026 on record named, recommended and linked separately. One engine and one run per query is a sample: a zero means not observed in this sample, not invisible everywhere.

Why Ref doesn't appear — and how to fix it

The full audit names the exact pages answer engines read in this category, the three cheapest gaps to close, and the pages to publish first. It exists already — it is how this score was measured.

Something wrong or already fixed? Re-audits are free and this page updates either way.

NEARBY ON THE INDEX