Skip to content

Context7 Platform -- Up-to-date docs for AI agents

CTX7-3147: Name the ask endpoint in the Docs7 docs (#3400)

Enes Gules3131245817e9
diff --git a/docs/docs7/agent-readiness.mdx b/docs/docs7/agent-readiness.mdx
index d4d25468..ae986587 100644
--- a/docs/docs7/agent-readiness.mdx
+++ b/docs/docs7/agent-readiness.mdx
@@ -16,8 +16,8 @@ The paths below are relative to the documentation root. For a site mounted at `e
| `/llms.txt` | Lists routable pages with their Markdown URL and description. Pages in navigation come first. |
| `/llms-full.txt` | Combines the complete Markdown content of the site into one file. |
| `/<page>.md` | Returns the Markdown representation of one page. |
-| `/search?q=<query>` | Searches the site and returns matching pages, headings, and snippets as JSON. |
-| `/.well-known/agent-skills/index.json` | Advertises a site-specific Agent Skill with links to the docs and search. |
+| `/ask?q=<keywords or question>` | Returns the matching pages, headings, and snippets as JSON. Short keywords rank best. |
+| `/.well-known/agent-skills/index.json` | Advertises a site-specific Agent Skill with links to the docs and the ask endpoint. |
An agent can also request a normal page URL with `Accept: text/markdown`. Docs7 returns Markdown when the client prefers it. HTML responses advertise the Markdown page, both `llms.txt` files, and the Agent Skills index through `Link` headers.
diff --git a/docs/docs7/ai-visibility.mdx b/docs/docs7/ai-visibility.mdx
index 0731fef3..1d99112f 100644
--- a/docs/docs7/ai-visibility.mdx
+++ b/docs/docs7/ai-visibility.mdx
@@ -36,9 +36,12 @@ Docs7 currently tracks:
AI Visibility shows which product made the request. It does not show the exact model version.
</Note>
-## WebMCP searches
+## Agent questions
-Docs7 exposes a read-only `search_docs` WebMCP tool in browsers that support WebMCP. The **WebMCP searches** table shows the most common queries sent through that tool.
+The **Agent questions** card shows the most common questions that AI agents send to your docs. It shows one source at a time:
+
+- **Ask endpoint**: a note on every page tells agents how to ask the docs with `/ask?q=<keywords or question>`.
+- **WebMCP**: Docs7 exposes a read-only `ask_docs` WebMCP tool in browsers that support WebMCP.
These are separate from searches typed by people in the website search box. Human search terms appear under [Analytics](/docs7/analytics#searches).