
Peak Answer
io.github.peakanswerv1.0.0Updated Sep 29, 2026
Whether AI search recommends your brand, which questions rivals win, and why engines skip your site.
Overview
Checks whether AI search engines recommend a brand, audits site answer-readiness, and tracks visibility and competitor-won questions.
- What it does
- A remote MCP server for Peak Answer that audits a public URL for answer readiness, AI crawler access, robots.txt, sitemap, structured data, headings, meta description, readability and entities in one call. It can generate llms_txt, faq_schema, content_brief, prompt_set or semantic_keywords, and run a geo_audit that asks a real model ten buying questions as a background run. Brand-scoped tools report the connected domain, measured visibility history, tracked questions (including ones a competitor wins), question history over time, a ranked action backlog, and Search Console queries near the top of page two.
- When to use it
- Use it when you want an assistant to evaluate or improve how a brand shows up in AI search answers, or to pull measured visibility, tracked-question and Search Console data for one brand. It suits marketing, SEO and content teams working on generative engine optimization.
- Requirements
- A remote endpoint only; nothing is installed locally. Connect a client to the Peak Answer MCP URL. OAuth 2.0 is discovered automatically, or an API key from Peak Answer Settings can be used as a bearer token. A Peak Answer account is required for the brand-scoped tools; the connection is scoped to one brand.
Installation
In SourceWeft
- Open Peak Answer in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"peak-answer": {
"type": "http",
"url": "https://peakanswer.com/api/mcp"
}
}
}README
Peak Answer MCP
The remote MCP server for Peak Answer: whether AI search engines recommend a brand, which buying questions competitors win instead, and the technical and content reasons an engine cannot quote a site.
Remote only. There is nothing to install and no local process; you point a client at the URL.
Connect
Claude Code
mcp.json (Cursor, VS Code and other clients that read this format)
Claude.ai and ChatGPT — add the URL under Settings, Connectors.
Setup with screenshots: https://peakanswer.com/tools/claude-mcp
Authentication
OAuth 2.0, discovered automatically. An unauthenticated request returns 401 with
and the client takes it from there. Clients that would rather hold a token can use an API key from Peak Answer Settings as a bearer token instead.
The connection is scoped to one brand. Call my_brand to find out which domain that is rather than
asking the user or guessing.
Tools
Every tool is read-only and annotated as such, so a client does not have to ask before each call.
audit_site, generate and geo_audit work on any public URL. The my_* tools read the
customer's own measured data.
Who it is for
Anyone with a Peak Answer account; the MCP is included on every plan. The free tools at peakanswer.com/tools need no account at all.
Agent skills that use these tools, and work without them: peakanswer/peak-answer-skills.
Registry
server.json in this repo is the MCP Registry entry.
Source: README.md at commit f15824f
Tools
0Version history
1- v1.0.0LatestSep 29, 2026

