Peak Answer

io.github.peakanswerPublished by GitHub account peakanswerv1.0.0Updated Nov 10, 2026

Whether AI search recommends your brand, which questions rivals win, and why engines skip your site.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Remote MCP server for Peak Answer that lets an assistant check whether AI search engines recommend a brand, which buying questions rivals win, and why engines…

What you can do
  • Audit a public URL for AI answer readiness: crawler access, robots.txt, sitemap, structured data, headings, meta description, readability and entities
  • Generate llms.txt, FAQ schema, content briefs, prompt sets and semantic keywords
  • Run a GEO audit that asks a real model ten buying questions, as a background run collected later
  • Read the connected brand's measured visibility history, tracked questions, per-question history and ranked action backlog
  • List Search Console queries sitting near the top of page two
  • Identify which domain the connection is scoped to
When to use it
Useful for SEO, content and marketing teams that want to know how a brand shows up in AI-generated answers, which competitor wins specific buying questions, and what technical or content gaps block quoting. Also handy for auditing any public site before publishing content aimed at AI search.
Requirements
A remote endpoint only, with nothing to install locally. Requires a Peak Answer account and OAuth 2.0 authorization, which clients discover automatically; an API key from Peak Answer settings can be used as a bearer token instead. The connection is scoped to a single brand.
Before you install
Access is tied to a Peak Answer account and a single brand scope, so the assistant can read that account's measured data, tracked questions and Search Console queries. The geo_audit tool starts a background run that must be polled again with the same domain. Tools are described as read-only, but generated artifacts and audits are produced from public URLs you supply.

Installation

In SourceWeft

  1. Open Peak Answer in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. 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.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.peakanswer%2Fpeak-answer/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "peak-answer": {
      "type": "http",
      "url": "https://peakanswer.com/api/mcp"
    }
  }
}

README

Peak Answer MCP

[M8ven verified]

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.

https://peakanswer.com/api/mcp

Connect

Claude Code

bash
claude mcp add --transport http peak-answer https://peakanswer.com/api/mcp

mcp.json (Cursor, VS Code and other clients that read this format)

json
{  "mcpServers": {    "peak-answer": {      "url": "https://peakanswer.com/api/mcp"    }  }}

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

WWW-Authenticate: Bearer resource_metadata="https://peakanswer.com/.well-known/oauth-protected-resource/api/mcp", scope="mcp"

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

ToolWhat it does
audit_siteAnswer readiness, AI crawler access, robots.txt, sitemap, structured data, headings, meta description, readability and entities for one URL, in one call. Seconds
generateProduces llms_txt, faq_schema, content_brief, prompt_set or semantic_keywords
geo_auditAsks a real model ten real buying questions. Starts a background run and returns immediately; call again with the same domain to collect it
my_brandWhich domain this connection is scoped to
my_visibilityMeasured visibility history for that brand, rather than a one-off check
my_questionsTracked questions, with only_losing for the ones a competitor wins
my_question_historyOne question over time
my_actionsThe ranked backlog for that brand
my_search_consoleSearch Console queries near the top of page two

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 758c74f

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 29, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.