MCP server
Remote Model Context Protocol server for Peak Answer. OAuth 2.0, one active brand at a time,49 tools.
The MCP server is included on every plan. Start 7 day trial. See what the MCP and API include. The REST API has its own reference.
Endpoint
https://peakanswer.com/api/mcpStreamable HTTP. There is nothing to install and no local process: the server runs on our infrastructure and a client connects to it over the URL.
Connecting
Claude Code
claude mcp add --transport http peak-answer https://peakanswer.com/api/mcpCursor, VS Code and other clients that read mcp.json
{
"mcpServers": {
"peak-answer": {
"url": "https://peakanswer.com/api/mcp"
}
}
}Claude.ai and ChatGPT: add the URL under Settings, Connectors. A step-by-step walkthrough with screenshots is at the setup section.
Authentication
OAuth 2.0 with dynamic client registration, discovered automatically. An unauthenticated request returns 401 carrying the discovery header:
WWW-Authenticate: Bearer resource_metadata="https://peakanswer.com/.well-known/oauth-protected-resource/api/mcp", scope="mcp"The client follows it, the user approves access in Peak Answer, and the client holds the token. Both discovery documents are public: /.well-known/oauth-protected-resource/api/mcp and /.well-known/oauth-authorization-server.
A client that would rather hold a static credential can send an API key from Peak Answer Settings as a bearer token instead. Keys are revocable from the same screen, and revoking one ends every session using it.
Scope of access
A connection starts on one brand, the website you approved it for. It cannot read another customer’s data. If your account has more than one brand, call list_brands to see them and switch_brand to move the connection to another for the rest of the session. It returns to the approved brand on its own after a few hours. To act on another brand for one call only, pass its id or domain as brand on that call. A brand your account cannot use is refused with an error, never answered with someone else’s data, and every answer names the brand it came from. Call my_brand to find out which domain is active rather than assuming. A connection made with an API key belongs to its one brand and cannot switch.
Tools
49 tools: 36 that read and 13 that change something. Every tool carries MCP behaviour annotations, so a client knows without being told which calls need the user’s permission first.
Reading
Annotated readOnlyHint: true. None of these writes to the account, publishes anything, or changes a setting.
| Tool | What it does | What it reads |
|---|---|---|
audit_site | Answer readiness, AI crawler access, robots.txt, sitemap, structured data, headings, meta description, readability and entities for one URL, in one call | The public URL you pass it |
generate | Produces an llms.txt, FAQPage JSON-LD, a content brief, a prompt set or semantic keywords | The public URL or topic you pass it |
geo_audit | Asks a model ten real buying questions about a category and reports who is named. Starts a background run and returns immediately; call again with the same domain to collect it | The public domain you pass it |
my_brand | Which brand is active for this connection | The connected account |
list_brands | Every brand the account can use, with plan and questions tracked, and which one is active | The connected account |
switch_brand | Makes another of your brands the active one for the rest of the session. Takes a brand id or domain | The connected account |
my_competitors | The competitors tracked for the active brand, with domains and notes | The connected account |
my_visibility | Measured visibility history for that brand, rather than a one-off check | The connected account |
my_questions | Tracked questions, with only_losing for the ones where a competitor is named and the brand is not | The connected account |
my_suggested_questions | Suggested questions with search demand labels. Use Track to add one | The connected account, same as the question list |
my_question_google_results | One question on Google: the first 10 sites, your position, Google AI answer, competitors on page one, and check date | The connected account, same as the question detail page |
my_question_google_page | The page on your website that shows up on Google for a tracked question, its position and check date | The connected account, same as the question detail page |
my_question_history | One tracked question over time | The connected account |
my_actions | The ranked backlog of recommended work for that brand | The connected account |
my_search_console | Search Console queries sitting near the top of page two | The connected account, and only if Search Console was connected by the customer |
gsc_query | Search Console performance data as Google returns it: clicks, impressions, ctr and position by date, query, page, country, device or search appearance, with filters and any search type | The connected account, read live from Google |
gsc_properties | The Search Console properties on the connected Google account | The connected account, read live from Google |
gsc_sitemaps | The submitted sitemaps with Google’s warnings, errors and indexed counts | The connected account, read live from Google |
gsc_inspect_url | Google’s index status for one URL | The connected account, read live from Google |
ga4_report | Google Analytics reports as Google returns them: any metrics by any dimensions for any dates, with filters, sorting, totals and period comparisons. Sessions, users, channels, sources, pages, countries, devices, events, key events, revenue, campaigns and custom dimensions | The connected account, read live from Google |
ga4_realtime | Who is on the site right now, by country, device, page, event or source | The connected account, read live from Google |
ga4_metadata | Every dimension and metric the property supports, including its custom ones | The connected account, read live from Google |
ga4_properties | The Google Analytics properties on the connected Google account | The connected account, read live from Google |
ga4_pivot_report | Cross-tab reports, such as channel by device | The connected account, read live from Google |
ga4_funnel_report | How many people get through each step you define, and where they drop | The connected account, read live from Google |
ga4_check_compatibility | Whether a set of dimensions and metrics can be reported together | The connected account, read live from Google |
ga4_property_config | How the property is set up: data streams, key events, custom definitions, audiences, channel groups, retention and links to Google Ads, Firebase and BigQuery | The connected account, read live from Google |
my_answers | The recorded answers for a tracked question, with the sources each engine cited, consulted or linked | Your tracked data in Peak Answer |
export_answers | Every recorded answer as rows for a sheet, one row per source: date, question, engine, whether you were named, who else was, and each source’s URL, domain and type. Filter by question, engine and dates, with a link to download the full CSV | Your tracked data in Peak Answer |
my_cited_sources | Every domain the engines cite for your questions, how often, and whether your own pages are among them | Your tracked data in Peak Answer |
my_links | Ranked places worth being on, like sites engines already quote, directories and review sites, with how reachable each is and what it takes | Your tracked data in Peak Answer, same as the Links page |
my_landscape | Who wins your questions, how often, and where you sit against them | Your tracked data in Peak Answer, same as the Competitive Landscape page |
my_proof | Questions that started or stopped naming your brand, with the before and after | Your tracked data in Peak Answer, same as the Proof page |
my_weekly_report | The weekly report as you receive it: what moved, what was published, what to do next | Your tracked data in Peak Answer |
my_traffic | Clicks and impressions over time | Your Search Console data, same as the Traffic page |
my_ai_visits | Visits that came from AI assistants. Ask for Google Analytics (GA4) or PostHog by name, or leave it out for both | Your Google Analytics and PostHog data, same as the Traffic page |
audit_site, generate and geo_audit work on any public URL. The my_* tools read the customer’s own measured history and return nothing for an account with no tracking data yet.
Writing
Annotated readOnlyHint: false. These exist so the product can be run from the assistant the customer already has open, rather than read there and acted on somewhere else. Each is addressed by the words a person would use, not by an internal id, and an ambiguous reference is refused with the candidates listed rather than guessed at.
| Tool | What it changes | Annotations |
|---|---|---|
track_question | Starts tracking a buying question. Subject to the plan’s question limit | idempotent |
track_questions | Starts tracking a list of questions in one call, up to 50. Each is checked like a single one, and the reply says what happened to each | idempotent |
rename_question | Rewords a tracked question. It keeps its history and is measured with the new wording from the next sweep | idempotent |
move_question | Moves a tracked question up or down the priority list | none |
untrack_question | Stops tracking one. History is kept and it can be added back | destructive, idempotent |
mark_action_done | Marks a recommended action finished, which releases the next one | idempotent |
skip_action | Turns a recommended action down | destructive, idempotent |
add_competitor | Tracks a competitor, so answers are checked for whether it is named | idempotent |
remove_competitor | Stops tracking one, keeping the reason so discovery does not re-add it | destructive, idempotent |
set_competitor_note | Saves or clears a note on a tracked competitor | idempotent |
set_autopilot | Pauses or resumes autopilot for the active brand | idempotent |
save_context | Saves something about the business the crawl cannot see. The content engine reads it | not idempotent |
approve_article | Publishes a drafted article to the connected website. The only tool that changes anything outside Peak Answer | destructive, open world, not idempotent |
Plan limits are enforced on the write path exactly as they are on the screen: the same code runs for both, so an assistant cannot add a twenty-first question to a plan that allows twenty.
What the server cannot do
- It cannot change billing, plan, team membership, connected websites or credentials.
- It cannot delete anything. Removals deactivate and keep the history.
- It cannot read or change another brand’s data, or another customer’s.
- It cannot publish anywhere except a website the customer has already connected, and only through
approve_article, which is marked destructive so the client asks first. - It cannot reach a private URL. Every page it fetches, it fetches as a public visitor.
- It does not accept file uploads and returns no executable content.
Data handling
The API behind these tools is our own. A tool call reads the account’s existing data or fetches a public page; it does not send the conversation, the prompt, or anything else from the client to a third party beyond the providers already named in our privacy policy. Calls are logged with the account, the tool and the timestamp, for rate limiting and support, and no conversation content is stored.
Data returned to the client is the customer’s own measured data and the public pages they asked about. Nothing about other customers is ever returned, including in the cross-customer aggregates the product computes internally.
Limits
Calls count against the account’s plan in the same way work started in the app does. geo_audit is the expensive one: it asks a real model ten real questions, takes minutes, and is rate limited per brand. Call it once and collect the result later rather than polling. audit_site returns in seconds and is the right default.
Requirements
A Peak Answer account. MCP access is included on every plan, and the free tools at peakanswer.com/tools need no account at all. Sign up at peakanswer.com/signup.
Source and registry
The server.json this server is published with, and its connection instructions, are public at github.com/peakanswer/peak-answer-mcp. It is listed in the official MCP Registry as io.github.peakanswer/peak-answer.
Support
Email john@peakanswer.com. Security reports go to the same address, and security.txt carries the current contact.
Privacy policy · Terms