# OnPage.dev (remote · onpage.dev)

Free SEO MCP that closes the loop: find, fix, ship as a PR or to a CMS, prove. 37 tools, no key.

- Trust score: 73/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `onpage.dev`: 73/100 (this document), [markdown](https://verifymcp.io/servers/dev-onpage-onpage/onpage.md), [page](https://verifymcp.io/servers/dev-onpage-onpage/onpage)

## Channel facts

- Endpoint: `https://onpage.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.14.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 9349 tokens (~233/item across 40 items; 37 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 11 days we've observed: 18 tool removals, 0 breaking changes, 0 auth/transport breaks, 35 additions.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 39 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the OnPage.dev MCP server?

OnPage.dev is a hosted endpoint at https://onpage.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-onpage-onpage 'https://onpage.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-onpage-onpage": {
      "url": "https://onpage.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-onpage-onpage": {
      "type": "http",
      "url": "https://onpage.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-onpage-onpage]
url = "https://onpage.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-onpage-onpage": {
      "type": "remote",
      "url": "https://onpage.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-onpage-onpage --url 'https://onpage.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-onpage-onpage:
    url: "https://onpage.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-onpage-onpage": {
      "Transport": "http",
      "Url": "https://onpage.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-onpage-onpage -t streamable-http -u 'https://onpage.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-onpage-onpage": {
      "type": "http",
      "url": "https://onpage.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-15 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “content” rewrote its description, which is the text the model reads
- [security] Tool “get_fix_pack” rewrote its description, which is the text the model reads
- [functional] New prompt “content_autopilot”
- [cosmetic] “content” added an optional parameter “html”
- [cosmetic] “content” added an optional parameter “ideas”
- [cosmetic] “content” added an optional parameter “per_week”
- [cosmetic] “content” added an optional parameter “start”
- [cosmetic] “content” added an optional parameter “urls”
- [cosmetic] “content” added an optional parameter “webhook_url”
- [cosmetic] “content” added an optional parameter “weeks”

### 2026-10-13 (score 73, +1)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

- [security regression] Tool “find_duplicate_content” was removed
- [security regression] Tool “analyze_logs” was removed
- [security regression] Tool “check_hreflang” was removed
- [security regression] Tool “extract_from_pages” was removed
- [security regression] Tool “check_local_seo” was removed
- [security regression] Tool “check_product_page” was removed
- [security regression] Tool “check_url_parameters” was removed
- [security regression] Tool “create_content_brief” was removed
- [security regression] Tool “map_topics” was removed
- [security regression] Tool “match_intent” was removed
- [security regression] Tool “plan_redirects” was removed
- [security regression] Tool “plan_split_test” was removed
- [security regression] Tool “plan_sprint” was removed
- [security regression] Tool “render_page” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_opportunities” rewrote its description, which is the text the model reads
- [security] Tool “accessibility” rewrote its description, which is the text the model reads
- [security] Tool “ai_visibility” rewrote its description, which is the text the model reads
- [security] Tool “answer_readiness” rewrote its description, which is the text the model reads
- [security] Tool “backlinks” rewrote its description, which is the text the model reads
- [security] Tool “check_keyword” rewrote its description, which is the text the model reads
- [security] Tool “check_links” rewrote its description, which is the text the model reads
- [security] Tool “compare” rewrote its description, which is the text the model reads
- [security] Tool “dashboard” rewrote its description, which is the text the model reads
- [security] Tool “edge_worker” rewrote its description, which is the text the model reads
- [security] Tool “entity” rewrote its description, which is the text the model reads
- [security] Tool “explain_google” rewrote its description, which is the text the model reads
- [security] Tool “fix_log” rewrote its description, which is the text the model reads
- [security] Tool “get_fix_pack” rewrote its description, which is the text the model reads
- [security] Tool “internal_links” rewrote its description, which is the text the model reads
- [security] Tool “layout” rewrote its description, which is the text the model reads
- [security] Tool “llms_txt” rewrote its description, which is the text the model reads
- [security] Tool “measure” rewrote its description, which is the text the model reads
- [security] Tool “request_recrawl” rewrote its description, which is the text the model reads
- [security] Tool “robots_txt” rewrote its description, which is the text the model reads
- [security] Tool “scan_page” rewrote its description, which is the text the model reads
- [security] Tool “schema” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 156 → 227
- [functional regression] Schema quality: 156 → 231
- [functional improvement] MCP protocol: fail → pass
- [functional] New prompt “ai_search_review”
- [functional] New prompt “executive_summary”
- [functional] New prompt “investigate_drop”
- [functional] New prompt “client_report”
- [functional] New prompt “fix_and_prove”
- [functional] New prompt “migration”
- [functional] New prompt “pick_up”
- [functional] New prompt “weekly_routine”
- [functional] MCP protocol version: 2025-06-18 → 2026-07-28
- [functional] Server version: 2.8.0 → 2.11.0
- [functional] Server version: 1.4.0 → 2.8.0
- [cosmetic] “compare” added an optional parameter “bypass_token”
- [cosmetic] “compare” added an optional parameter “paths”
- [cosmetic] “compare” added an optional parameter “preview_url”
- [cosmetic] “compare” added an optional parameter “production_url”
- [cosmetic] “find_opportunities” added an optional parameter “drop_date”
- [cosmetic] “get_fix_pack” added an optional parameter “change_id”
- [cosmetic] “get_fix_pack” added an optional parameter “changes”
- [cosmetic] “get_fix_pack” added an optional parameter “note”
- [cosmetic] “get_fix_pack” added an optional parameter “site_key”
- [cosmetic] “measure” added an optional parameter “detail”
- [cosmetic] “sitemap” added an optional parameter “detail”
- [cosmetic] “accessibility” added an optional parameter “detail”
- [cosmetic] “accessibility” added an optional parameter “memory_key”
- [cosmetic] “ai_visibility” added an optional parameter “detail”
- [cosmetic] “ai_visibility” added an optional parameter “memory_key”
- [cosmetic] “answer_readiness” added an optional parameter “detail”
- [cosmetic] “answer_readiness” added an optional parameter “memory_key”
- [cosmetic] “backlinks” added an optional parameter “detail”
- [cosmetic] “backlinks” added an optional parameter “memory_key”
- [cosmetic] “check_keyword” added an optional parameter “detail”
- [cosmetic] “check_keyword” added an optional parameter “memory_key”
- [cosmetic] “check_links” added an optional parameter “detail”
- [cosmetic] “check_links” added an optional parameter “memory_key”
- [cosmetic] “compare” added an optional parameter “detail”
- [cosmetic] “compare” added an optional parameter “memory_key”
- [cosmetic] “dashboard” added an optional parameter “detail”
- [cosmetic] “dashboard” added an optional parameter “memory_key”
- [cosmetic] “edge_worker” added an optional parameter “detail”
- [cosmetic] “edge_worker” added an optional parameter “memory_key”
- [cosmetic] “entity” added an optional parameter “detail”
- [cosmetic] “entity” added an optional parameter “memory_key”
- [cosmetic] “explain_google” added an optional parameter “bing_queries”
- [cosmetic] “explain_google” added an optional parameter “detail”
- [cosmetic] “explain_google” added an optional parameter “google_queries”
- [cosmetic] “explain_google” added an optional parameter “issues”
- [cosmetic] “explain_google” added an optional parameter “memory_key”
- [cosmetic] “find_opportunities” added an optional parameter “ads”
- [cosmetic] “find_opportunities” added an optional parameter “brand_terms”
- [cosmetic] “find_opportunities” added an optional parameter “detail”
- [cosmetic] “find_opportunities” added an optional parameter “gsc”
- [cosmetic] “find_opportunities” added an optional parameter “memory_key”
- [cosmetic] “fix_log” added an optional parameter “detail”
- [cosmetic] “fix_log” added an optional parameter “memory_key”
- [cosmetic] “get_fix_pack” added an optional parameter “detail”
- [cosmetic] “get_fix_pack” added an optional parameter “memory_key”
- [cosmetic] “internal_links” added an optional parameter “detail”
- [cosmetic] “internal_links” added an optional parameter “memory_key”
- [cosmetic] “layout” added an optional parameter “detail”
- [cosmetic] “layout” added an optional parameter “memory_key”
- [cosmetic] “llms_txt” added an optional parameter “detail”
- [cosmetic] “llms_txt” added an optional parameter “memory_key”
- [cosmetic] “measure” added an optional parameter “memory_key”
- [cosmetic] “prioritize_fixes” added an optional parameter “detail”
- [cosmetic] “prioritize_fixes” added an optional parameter “memory_key”
- [cosmetic] “request_recrawl” added an optional parameter “detail”
- [cosmetic] “request_recrawl” added an optional parameter “memory_key”
- [cosmetic] “robots_txt” added an optional parameter “detail”
- [cosmetic] “robots_txt” added an optional parameter “memory_key”
- [cosmetic] “scan_page” added an optional parameter “detail”
- [cosmetic] “scan_page” added an optional parameter “memory_key”
- [cosmetic] “schema” added an optional parameter “detail”
- [cosmetic] “accessibility” reworded the description of “detail”
- [cosmetic] “accessibility” reworded the description of “memory_key”
- [cosmetic] “ai_visibility” reworded the description of “detail”
- [cosmetic] “ai_visibility” reworded the description of “memory_key”
- [cosmetic] “answer_readiness” reworded the description of “detail”
- [cosmetic] “answer_readiness” reworded the description of “memory_key”
- [cosmetic] “backlinks” reworded the description of “detail”
- [cosmetic] “backlinks” reworded the description of “memory_key”
- [cosmetic] “check_keyword” reworded the description of “detail”
- [cosmetic] “check_keyword” reworded the description of “memory_key”
- [cosmetic] “check_links” reworded the description of “detail”
- [cosmetic] “check_links” reworded the description of “memory_key”
- [cosmetic] “compare” reworded the description of “detail”
- [cosmetic] “compare” reworded the description of “memory_key”
- [cosmetic] “content” reworded the description of “detail”
- [cosmetic] “content” reworded the description of “memory_key”
- [cosmetic] “dashboard” reworded the description of “detail”
- [cosmetic] “dashboard” reworded the description of “memory_key”
- [cosmetic] “edge_worker” reworded the description of “detail”
- [cosmetic] “edge_worker” reworded the description of “memory_key”
- [cosmetic] “entity” reworded the description of “detail”
- [cosmetic] “entity” reworded the description of “memory_key”
- [cosmetic] “explain_google” reworded the description of “detail”
- [cosmetic] “explain_google” reworded the description of “memory_key”
- [cosmetic] “find_opportunities” reworded the description of “detail”
- [cosmetic] “find_opportunities” reworded the description of “memory_key”
- [cosmetic] “fix_log” reworded the description of “detail”
- [cosmetic] “fix_log” reworded the description of “memory_key”
- [cosmetic] “get_fix_pack” reworded the description of “detail”
- [cosmetic] “get_fix_pack” reworded the description of “memory_key”
- [cosmetic] “internal_links” reworded the description of “detail”
- [cosmetic] “internal_links” reworded the description of “memory_key”
- [cosmetic] “layout” reworded the description of “detail”
- [cosmetic] “layout” reworded the description of “memory_key”
- [cosmetic] “llms_txt” reworded the description of “detail”
- [cosmetic] “llms_txt” reworded the description of “memory_key”
- [cosmetic] “local” reworded the description of “detail”
- [cosmetic] “local” reworded the description of “memory_key”
- [cosmetic] “measure” reworded the description of “detail”
- [cosmetic] “measure” reworded the description of “memory_key”
- [cosmetic] “plan” reworded the description of “detail”
- [cosmetic] “plan” reworded the description of “memory_key”
- [cosmetic] “prioritize_fixes” reworded the description of “detail”
- [cosmetic] “prioritize_fixes” reworded the description of “memory_key”
- [cosmetic] “request_recrawl” reworded the description of “detail”
- [cosmetic] “request_recrawl” reworded the description of “memory_key”
- [cosmetic] “robots_txt” reworded the description of “detail”
- [cosmetic] “robots_txt” reworded the description of “memory_key”
- [cosmetic] “scan_page” reworded the description of “detail”
- [cosmetic] “scan_page” reworded the description of “memory_key”
- [cosmetic] “schema” reworded the description of “detail”
- [cosmetic] “schema” reworded the description of “memory_key”
- [cosmetic] “share” reworded the description of “detail”
- [cosmetic] “share” reworded the description of “memory_key”
- [cosmetic] “site_audit” reworded the description of “detail”
- [cosmetic] “site_audit” reworded the description of “memory_key”
- [cosmetic] “site_memory” reworded the description of “detail”
- [cosmetic] “sitemap” reworded the description of “detail”
- [cosmetic] “sitemap” reworded the description of “memory_key”
- [cosmetic] “snippet” reworded the description of “detail”
- [cosmetic] “snippet” reworded the description of “memory_key”
- [cosmetic] “technical” reworded the description of “detail”
- [cosmetic] “technical” reworded the description of “memory_key”
- [cosmetic] “text_quality” reworded the description of “detail”
- [cosmetic] “text_quality” reworded the description of “memory_key”
- [cosmetic] “track_rankings” reworded the description of “detail”
- [cosmetic] “track_rankings” reworded the description of “memory_key”
- [cosmetic] “tracking” reworded the description of “detail”
- [cosmetic] “tracking” reworded the description of “memory_key”
- [cosmetic] “watch” reworded the description of “detail”
- [cosmetic] “watch” reworded the description of “memory_key”
- [cosmetic] “web_vitals” reworded the description of “detail”
- [cosmetic] “web_vitals” reworded the description of “memory_key”
- [cosmetic] “layout” reworded the description of “mode”
- [cosmetic] Tool “explain_google” changed its title: Explain Google → Explain Google and Bing
- [cosmetic] Tool “layout” changed its title: Layout → Layout and first screen

### 2026-10-12 (score 72, +5)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

### 2026-10-10 (score 67)

First indexed and scored.

## MCP tools (37)

### `site_memory` (~220 tokens)

Site memory

A memory per site that every OnPage.dev tool writes to, across chats and clients. Open it first when working on a site over time. Pick with mode: open = Open or create the memory, bind it to this chat, get the brief and next steps (default). Needs url. next = The best next steps from everything recorded. timeline = What happened, newest first. note = Record a decision or context. Needs note. forget = Delete the memory (ask the user first). Needs memory_key.

Input parameters:

- `detail` (string): brief = short summary.
- `kind` (string)
- `limit` (number)
- `memory_key` (string): The memory_key you got when the memory was created.
- `mode` (string): Default open.
- `note` (string)
- `share_learning` (boolean): Opt in (true) or out (false) of sharing anonymous results: only the fix type and the rounded lift, never the site, URLs or numbers.
- `url` (string): The site's home page.

### `scan_page` (~189 tokens)

SEO and AI scan

Scan a page for Google and AI search: 0-100 score, issues to fix first with why and how, AI readiness and key facts. Pick with mode: page = A live page by url (default). Needs url. html = Unpublished HTML before deploy, to gate a release. Needs html. deep = Everything measured on one page, by section. Needs url. rescan = Scan again after fixes and compare with the last scan. Needs url.

Input parameters:

- `detail` (string): brief = short summary.
- `html` (string): The complete HTML document, up to 900 KB.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default page.
- `sections` (array): Sections to include. Default: all.
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `site_audit` (~384 tokens)

Whole-site audit

Audit a whole site, step by step, and work with the result. Pick with mode: start = Start an audit of up to 25 pages; returns audit_id. Needs url. continue = Scan the next pages; call until complete. Issues by code, sections, average score. Needs audit_id. import = Turn a crawl from Screaming Frog, Ahrefs or Semrush (up to 500 pages) into an audit_id. Needs pages[{url, status, redirect_to, title, meta_description, h1}]. compare = What changed since the last audit, or against a competitor audit. Needs audit_id. report = A client-ready report page with a link. Needs audit_id.

Input parameters:

- `audit_id` (string): The id returned by start_site_audit.
- `brand` (string): Optional agency or team name to show instead of OnPage.dev.
- `competitor_audit_id` (string): Optional: a finished audit of a competitor's site, to compare the two sites side by side instead of over time.
- `detail` (string): brief = short summary.
- `links` (array): Optional internal links, for link equity, orphans and internal link suggestions.
- `max_pages` (integer): How many pages to audit, default 10, at most 25.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default start.
- `note` (string): Optional short note for the reader, shown at the top.
- `pages` (array): One row per crawled page.
- `previous_audit_id` (string): Optional: the audit to compare with.
- `source` (string): Where the rows come from, for example Screaming Frog or Ahrefs Site Audit.
- `url` (string): Full address, for example https://example.com.

### `watch` (~376 tokens)

Keep watching

Monitoring that runs on its own and posts changes to a webhook. Each kind takes action create (default), status or stop where it applies. Pick with mode: page = Watch one page (or a competitor page with competitor_of) for SEO changes. Needs url. page_status = Latest result of a page watch. Needs watch_id. page_stop = Stop a page watch. Needs watch_id. site_audit = Audit the whole site every 1, 7 or 30 days and alert on regressions. guard = Every 6 hours: robots.txt, sitemap, https, noindex and canonical on key pages, for deploy accidents. competitors = Weekly new, updated and removed pages from competitors' sitemaps, flagged by your topics.

Input parameters:

- `action` (string): create (default), status or stop.
- `competitor_of` (string): Optional: your own page.
- `competitors` (array): Competitor home pages.
- `detail` (string): brief = short summary.
- `every_days` (number): How often, default 7.
- `guard_id` (string): For status and stop.
- `max_pages` (number): Pages per audit, default 25.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default page.
- `pages` (array): Key pages to guard besides the home page (money pages first).
- `schedule_id` (string): For status and stop.
- `topics` (array): Your topics or keywords, to flag overlapping pages.
- `url` (string): Full address, for example https://example.com/pricing.
- `watch_id` (string): For status and stop.
- `webhook_url` (string): Optional https URL that receives a JSON POST when something changes, for example a Slack or Discord incoming webhook.

### `dashboard` (~302 tokens)

SEO dashboard

A daily SEO data feed for key pages and a live dashboard in the chat. Pick with mode: feed = Start a daily feed of key pages; returns feed_id. Needs url. data = The feed as clean tables over time. Needs feed_id, dataset. build = Blueprint for a live SEO command center with realtime GA4 visitors. Needs feed_id.

Input parameters:

- `bigquery` (object): Optional, for ready SQL.
- `dataset` (string)
- `detail` (string): brief = short summary.
- `feed_id` (string): Feed from create_dashboard_feed.
- `fix_log_id` (string): Optional fix log from log_fix, to include shipped fixes.
- `format` (string): blueprint (default) for Claude Dashboards, or html for a complete, designed dashboard page filled with the feed's data, ready to show as an artifact.
- `from` (string): Start date, YYYY-MM-DD.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default feed.
- `name` (string): Optional name, for example the client's name.
- `pages` (array): Optional key pages to track, up to 10.
- `replace` (boolean): Replace this connection's existing feed.
- `sources` (array): What the user has connected in Claude.
- `to` (string): End date, YYYY-MM-DD.
- `url` (string): Home page of the site.

### `measure` (~419 tokens)

Measure results

Prove and measure with numbers from the user's Search Console, GA4, Ahrefs or Semrush, including numbers the user pastes. Use it instead of calculating by hand: it handles spelling variants, control groups and trends. Pick with mode: impact = Before and after fixes, against pages you did not touch. Needs pages[{url, before, after, changed, fix}]. ai_citations = AI citations before and after, per engine. Needs pages[{url, before, after, changed}]. ai_referrals = Visits from ChatGPT, Perplexity, Gemini and other assistants, from GA4. Needs rows[{source, sessions, landing_page, period, conversions, revenue}]. brand_split = Brand versus non-brand clicks and how each moved. Needs brand_terms, rows[{query, keyword, clicks, traffic, impressions, position}]. share_of_voice = Share of the clicks against competitors from rank rows. Needs your_domain, rows[{keyword, position, volume, domain, url, group}].

Input parameters:

- `brand_terms` (array): Brand and product names, and misspellings.
- `days` (integer): Length of each period in days.
- `detail` (string): brief = short summary.
- `fix_date` (string): Date the fixes went live, YYYY-MM-DD.
- `fix_log_id` (string): Optional fix log from log_fix: takes the fix date from it and saves the result per fix, with a rollback plan for fixes that did worse.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default impact.
- `pages` (array)
- `rows` (array)
- `rows_before` (array): Optional same rows from an earlier period.
- `source` (string): Where the counts come from, for example Ahrefs Brand Radar.
- `watch_ids` (array): Optional watch ids, to list what changed on each page and when.
- `your_domain` (string): Your domain, e.g. example.com.

### `find_opportunities` (~504 tokens)

Find search opportunities

Turn Search Console, GA4 or Ahrefs rows (also rows the user pastes) into the fastest wins, instead of judging them by hand; content_decay and traffic_drop take search_type for Discover, News, Image or Video rows. Pick with mode: ctr_gaps = Page 1 results with a click-through rate far below normal. Needs rows[{position, page, query, clicks, impressions, ctr}]. striking_distance = Queries at positions 8 to 20 worth a push. Needs rows[{position, page, query, clicks, impressions, ctr}]. content_decay = Pages slowly losing clicks over months: a refresh queue. Needs rows[{url, month, clicks}]. traffic_drop = Explain a drop page by page, by device and country. Needs rows[{url, before, after, query, device, country}]. prune = Keep, refresh, merge (301), noindex or remove (410) per page. Needs rows[{url, clicks, impressions, conversions, referring_domains, inlinks}]. discover = Readiness for Google Discover and News, with Discover or News rows. paid_organic = Google Ads terms against Search Console: ad spend you can test cutting, content to write. Needs ads[{term, cost, clicks, conversions}], gsc[{query, position, clicks, page}]. anomalies = Spike and drop days in daily rows, with Google updates near them. Needs rows[{date, clicks, impressions, page}]. ai_queries = Question and prompt-style queries per page, for AI answers. Needs rows[{query, page, clicks, impressions, position}].

Input parameters:

- `ads` (array): Google Ads search terms.
- `brand_terms` (array): Optional brand names, handled apart.
- `detail` (string): brief = short summary.
- `drop_date` (string): Optional first day of the drop, YYYY-MM-DD, to check Google updates around it.
- `fix_log_id` (string): Optional fix log from log_fix, to spot undone fixes on losing pages.
- `gsc` (array): Search Console queries.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default ctr_gaps.
- `rows` (array): Search Console rows for one period (28 days works well).
- `search_type` (string): Search Console search type of the rows, default web.
- `urls` (array): Article pages to check.

### `backlinks` (~390 tokens)

Backlinks

Turn backlink data from Ahrefs, Semrush or similar into links won back, won or cleaned up. Pick with mode: broken = Broken and lost backlinks and 404 visits into 301s and outreach. Needs rows[{target_url, source_url, anchor, domain_rating, dofollow, http_code}]. opportunities = Sites linking to competitors, and unlinked brand mentions. Needs site. outreach = One outreach email per site, as drafts for the user's mail after approval. Needs your_site, prospects[{page, type, your_url, dead_url, anchor, contact}]. disavow = A conservative disavow.txt, only after a manual action or clear negative SEO. Needs rows[{url_from, domain, is_spam, domain_rating, anchor, traffic}], reason.

Input parameters:

- `audit_id` (string): Optional: a finished site audit, to match on page titles too.
- `brand` (string): Brand name to look for in mention pages.
- `competitors` (array): Each competitor with its referring domains.
- `detail` (string): brief = short summary.
- `format` (string): Rule format, default redirects (Cloudflare Pages and Netlify _redirects).
- `live_urls` (array): Optional: your live pages, instead of reading the sitemap.
- `memory_key` (string): site_memory key, records this call.
- `mentions` (array): Pages that mention the brand.
- `mode` (string): Default broken.
- `prospects` (array)
- `reason` (string): Why a disavow is considered.
- `rows` (array): Broken backlink rows, one per linking page.
- `sender_name` (string): Name to sign with.
- `site` (string): Optional: your site's address.
- `your_site` (string): Your site or brand name, e.g.
- `yours` (array): Your own referring domains.

### `ai_visibility` (~282 tokens)

AI visibility

Whether AI assistants can read, quote and recommend a site. Pick with mode: check = AI crawler access, llms.txt, 15 citability checks and the page as a model reads it. Needs url. bots = Fetch the page as Googlebot, GPTBot, ClaudeBot, PerplexityBot and more against a browser: firewall blocks, challenges, cloaking. Needs url. gaps = Where AI answers name competitors, not you, from Brand Radar or similar. Needs site, brand, responses[{question, response, links, search_queries, engine, volume}]. citations = What pages cited by AI do differently, from citation counts. Needs pages[{url, chatgpt, perplexity, gemini, google_ai_overviews, google_ai_mode}].

Input parameters:

- `brand` (string): Your brand name as people write it.
- `competitors` (array)
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default check.
- `pages` (array)
- `responses` (array)
- `site` (string): Your site, for example example.com.
- `source` (string): Where the citation counts come from.
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `answer_readiness` (~210 tokens)

Answers for AI search

Whether a page answers the questions people ask AI and Google. Pick with mode: questions = Sub-questions AI Mode fans out to, and which the page answers. Needs url, topic, questions. passages = The passages that answer given questions, or the gaps. Needs url, question. format = Answer format against the pages that rank. Needs url, question, competitors.

Input parameters:

- `competitors` (array): Optional: up to 2 pages that rank for the topic.
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default questions.
- `question` (string): The question people ask, for example 'how long does shipping take to Germany'.
- `questions` (array): The sub-questions an AI search engine would ask for the topic.
- `topic` (string): The topic or main query, for example 'passport renewal'.
- `url` (string): Full address of the page.

### `get_fix_pack` (~363 tokens)

Fixes as code

Fixes ready to ship: as code, for a CMS through its MCP, as a pull request or at the edge. Pick with mode: fixes = Title, description, canonical, social tags, JSON-LD; platform html, wordpress, shopify, webflow, wix, storyblok, sanity, contentful, strapi, ghost, magento, git or cloudflare. Needs url. alt_texts = Write and ship missing alt texts. Needs url. web_vitals = Speed fixes as tags, WordPress steps or a Worker. Needs url. wordpress = Send fixes, new drafts and post updates to the OnPage.dev WordPress plugin for one-click approval and undo. Needs site_key.

Input parameters:

- `alts` (array): Step 2: the alt text per image src.
- `change_id` (string): Status of an earlier send.
- `changes` (array): Optional field and new value pairs.
- `detail` (string): brief = short summary.
- `failing` (array): Metrics that fail for real users, if known.
- `framework` (string): With platform git: the site's framework.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default fixes.
- `note` (string): Optional reason shown to the site owner.
- `platform` (string): html (default) for code to paste; wordpress, webflow, wix, shopify, storyblok, sanity, contentful, strapi, ghost or magento for a plan with the exact fields and
- `site_key` (string): The site key from the plugin, wpk_...
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `edge_worker` (~167 tokens)

Cloudflare Workers

Fixes applied at the edge on the user's own Cloudflare, on any CMS. Pick with mode: rules = One Worker that fixes a whole section by rules. Needs audit_id. prerender = Serve rendered HTML to AI crawlers for JavaScript apps. Needs url.

Input parameters:

- `audit_id` (string): Id of a completed site audit (start_site_audit, then get_site_audit until complete).
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default rules.
- `site_name` (string): Brand name for title endings, for example 'Acme Shoes'.
- `url` (string): A page of the app, for example https://app.example.com/pricing.

### `fix_log` (~263 tokens)

Fix log

Record shipped fixes, keep them live and report on them. Pick with mode: log = Record a shipped fix; checked every 6 hours, restore code on regression. Needs fixes[{url, field, new, old, via, ref}]. report = Every fix with status and results: a monthly client report. Needs fix_log_id.

Input parameters:

- `brand` (string): For the report: your agency name for the header.
- `detail` (string): brief = short summary.
- `fix_log_id` (string): Add to an existing log.
- `fixes` (array)
- `format` (string): status (default), a client report, or GA4 annotations (one per ship date) for the Admin API.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default log.
- `month` (string): For the report: YYYY-MM.
- `shipped_at` (string): Date the fixes went live, YYYY-MM-DD.
- `verify` (boolean): Check the live pages now (4 pages per call).
- `webhook` (string): Optional https URL (Slack, Discord, Zapier, n8n, a GitHub Action) that gets the restore code when a fix is undone.

### `request_recrawl` (~157 tokens)

Recrawl

Get changed pages recrawled. Pick with mode: recrawl = Check pages are indexable, sitemap lastmod entries, IndexNow and Search Console steps (default). Needs urls. indexnow = Submit URLs to IndexNow, or set up the key. Needs urls.

Input parameters:

- `detail` (string): brief = short summary.
- `indexnow_key` (string): Optional IndexNow key that is live at /<key>.txt.
- `key` (string): The site's IndexNow key (8 to 128 letters, digits or dashes).
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default recrawl.
- `urls` (array): Changed pages on one site.

### `explain_google` (~208 tokens)

Explain Google and Bing

Explain what Google Search Console and Bing Webmaster Tools report, and what to do. Pick with mode: index_status = Index coverage and rich result statuses, with the fix. Needs rows[{url, coverageState, verdict, indexingState, robotsTxtState, pageFetchState}]. manual_action = A manual action, with the cleanup plan and reconsideration draft. Needs action. bing = Bing Webmaster crawl issues, and Bing against Google per query.

Input parameters:

- `action` (string): The manual action as Search Console shows it.
- `bing_queries` (array)
- `detail` (string): brief = short summary.
- `google_queries` (array)
- `issues` (array): Bing crawl or index issues.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default index_status.
- `rows` (array)
- `sample_urls` (array): Example URLs Google listed.
- `site` (string): The site or Search Console property.

### `check_keyword` (~197 tokens)

Keyword targeting

How pages target a keyword. Pick with mode: focus = One page against one keyword: 8 checks. Needs url, keyword. cannibalization = Your pages competing for one keyword, side by side on every signal, with the plan. Needs keyword, target_url.

Input parameters:

- `competing_urls` (array): Other pages of the same site that compete for the keyword.
- `detail` (string): brief = short summary.
- `keyword` (string): The search term the page should rank for, for example 'running shoes'.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default focus.
- `rows` (array): Optional Search Console rows for the keyword, to find the competing pages and their positions.
- `target_url` (string): The page that should rank for it.
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `accessibility` (~140 tokens)

Accessibility

Accessibility for people and the European Accessibility Act. Pick with mode: wcag = WCAG 2.1 AA checks. Needs url. screen_reader = The page as a screen reader reads it. Needs url.

Input parameters:

- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default wcag.
- `tree` (object): Optional: an accessibility snapshot from your own browser (role, name, level, children), for example Puppeteer page.accessibility.snapshot().
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `local` (~279 tokens)

Local SEO

Local search: the site, the Business Profile and the map. Pick with mode: check = LocalBusiness markup, NAP, locations and the Business Profile (default). Needs url. reviews = Reply drafts for Google reviews, unhappy ones first, for the user's GBP connector after approval. Needs reviews[{rating, author, text, date, replied, review_id}]. demand = Business Profile search terms and geo-grid ranks into new service and location pages.

Input parameters:

- `business` (string): Business name to sign with.
- `city` (string): Main city, left out when matching terms to pages.
- `contact` (string): Where unhappy customers can reach you, e.g.
- `detail` (string): brief = short summary.
- `gbp_profile` (object): Optional: the Google Business Profile of this location, from the user's GBP connector or typed by the user, to compare with the site.
- `grid` (array): Optional geo-grid rankings.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default check.
- `pages` (array): The site's page URLs, e.g.
- `reviews` (array)
- `terms` (array): Search terms from the Business Profile performance report.
- `url` (string): The home page, a location page or the locations overview page.

### `tracking` (~178 tokens)

Tracking and consent

Whether analytics and consent are set up right, and whether the numbers add up. Pick with mode: ga4 = GA4 tags, events and duplicates. Needs url. consent = Cookie banner and Consent Mode v2. Needs url. gsc_vs_ga4 = Search Console clicks against GA4 sessions per page: broken or filtered tracking. Needs gsc[{page, clicks}], ga4[{landing_page, sessions}].

Input parameters:

- `detail` (string): brief = short summary.
- `ga4` (array): GA4 sessions per landing page, organic Google only.
- `gsc` (array): Search Console clicks per page.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default ga4.
- `url` (string): Full address of the page, for example https://example.com/.

### `check_links` (~130 tokens)

Check links

Status of URLs and links. Pick with mode: urls = Status, redirect chain and canonical of a list of URLs. Needs urls. outbound = Dead or moved links from a page to other sites, with archived copies. Needs url.

Input parameters:

- `detail` (string): brief = short summary.
- `expected` (array): Optional expected final address for each URL, in the same order.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default urls.
- `url` (string): The page to check.
- `urls` (array): Addresses to check.

### `web_vitals` (~127 tokens)

Core Web Vitals

Core Web Vitals from real Chrome users. Pick with mode: now = The latest field data for a page or site. Needs url. trend = Weekly history, before and after a change date. Needs url.

Input parameters:

- `change_date` (string): Optional date a speed fix went live, YYYY-MM-DD.
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default now.
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `share` (~148 tokens)

Share and export

Send results where the team works. Pick with mode: link = A link to the visual report. Needs url. export = A Google Sheet, CSV, Slack message or one task per issue.

Input parameters:

- `audit_id` (string): A finished site audit from start_site_audit, to export the whole site.
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default link.
- `slack_webhook_url` (string): Optional https incoming webhook (Slack, Discord, Teams) to post the summary to.
- `url` (string): Full address, for example https://example.com/pricing.

### `plan` (~301 tokens)

Plan the work

Plans for migrations, experiments and the team. Pick with mode: redirects = Redirect map for a migration or URL change. split_test = SEO split test on a page template, with the Worker. Needs urls, field, pattern. sprint = Fixes into a week plan of tickets per role. Needs fixes[{title, url, detail, severity, impact, effort}].

Input parameters:

- `clicks` (array): Optional clicks per page for a balanced split.
- `detail` (string): brief = short summary.
- `field` (string): What to change.
- `fixes` (array)
- `format` (string): Output format, default redirects (Cloudflare Pages and Netlify).
- `hours` (object): Hours per week per role, default 8 each.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default redirects.
- `new_site` (string): New site address, to read its sitemap instead of new_urls.
- `new_urls` (array)
- `old_site` (string): Old site address, to read its sitemap instead of old_urls.
- `old_urls` (array)
- `pattern` (string): The new value with {title} or {description} as placeholders.
- `start_date` (string): Optional planned start, YYYY-MM-DD.
- `urls` (array): Pages of one template.
- `weeks` (number): Weeks to plan, default 4.

### `content` (~442 tokens)

Content strategy

What to write and how, in the site's own voice, from the pages that rank and the user's search data. Pick with mode: brief = A content brief from the pages that rank. Needs keyword, competitors. topics = Search Console queries into topics, with the page that owns each, and keyword gaps. Needs rows[{query, page, clicks, impressions, position, url}]. intent = Your page against the search intent of the pages that rank. voice = Learn how the site writes from its best articles. Needs urls. calendar = A dated calendar of refreshes and new pages, steered by what worked here. draft = A draft against the site's voice, sources and SEO, before approval. Needs html.

Input parameters:

- `audit_id` (string): Optional: a finished site audit, for internal link suggestions.
- `competitor_rows` (array): Optional keyword gap: competitors' organic keywords (Ahrefs organic-keywords or Semrush domain_organic for each competitor, or Semrush keyword gap rows).
- `competitors` (array): Pages that rank for the term.
- `detail` (string): brief = short summary.
- `html` (string): The draft as HTML, title in <title> or <h1>.
- `ideas` (array): Topics without a page yet.
- `keyword` (string): The search term the page should rank for.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default brief.
- `per_week` (number): Items per week, default 2.
- `queries` (array): Search Console rows by query and page, for the site-wide check.
- `rows` (array): Search Console rows by query and page.
- `start` (string): First day, YYYY-MM-DD, default today.
- `url` (string): Optional: your existing page for this term.
- `urls` (array): The site's own best articles, ones that rank and that the owner likes.
- `webhook_url` (string): Optional https Slack or Discord webhook for a Monday reminder; off stops it.
- `weeks` (number): Weeks to plan, default 8.

### `technical` (~325 tokens)

Technical SEO

Technical checks across pages and logs. Pick with mode: hreflang = Hreflang across language versions, with the corrected tag set. Needs url. parameters = URL parameters and filters that waste crawl budget. duplicates = Duplicate and near-duplicate pages. Needs audit_id. extract = One value pulled from many pages. Needs urls. logs = Access logs: what Googlebot and AI crawlers really crawl, with IP verification. Needs log.

Input parameters:

- `attribute` (string): With selector: read this attribute instead of the text, for example href or content.
- `audit_id` (string): Id of a completed site audit.
- `detail` (string): brief = short summary.
- `jsonld` (string): A JSON-LD path: the @type, then the properties, for example Product.offers.price or Article.author.name.
- `log` (string): Raw access log lines, one request per line.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default hreflang.
- `regex` (string): A regular expression; the first group is returned if there is one, otherwise the whole match.
- `selector` (string): CSS selector, for example .price, h1 or link[rel=canonical].
- `sitemap_urls` (array): Optional: the URLs from the site's sitemap, to find pages bots never crawl.
- `url` (string): Full address of one language version of the page.
- `urls` (array): Optional extra URLs, for example from server logs or Search Console.

### `llms_txt` (~122 tokens)

llms.txt

The llms.txt file for AI assistants. Pick with mode: generate = Write one from the sitemap and home page. Needs url. validate = Check an existing one and its links. Needs url.

Input parameters:

- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default generate.
- `text` (string): Optional llms.txt content to validate instead of the live file.
- `url` (string): Home page of the site, for example https://example.com.

### `schema` (~202 tokens)

Structured data

JSON-LD structured data for rich results. Pick with mode: generate = Write JSON-LD for a page: type Article, Product, FAQPage, Organization, BreadcrumbList, VideoObject, Event, Recipe, JobPosting, SoftwareApplication, ProfilePage or Course. Needs url. validate = Validate JSON-LD for rich results. Needs jsonld. product_page = Check an existing ecommerce product page (price, stock, merchant listing fields). To write Product JSON-LD use generate with type Product. Needs url.

Input parameters:

- `detail` (string): brief = short summary.
- `jsonld` (string): The JSON-LD as text, with or without the <script> tag.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default generate.
- `type` (string): Schema type, default auto.
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `robots_txt` (~175 tokens)

robots.txt

robots.txt for search and AI crawlers. Pick with mode: test = Which crawlers may fetch a URL, and the rule that decides. Needs url. ai_policy = Rules per AI crawler: allow AI search, block training. Needs url, policy.

Input parameters:

- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default test.
- `policy` (string): Which AI crawlers to allow.
- `robots_txt` (string): Optional robots.txt content to test instead of the live file.
- `url` (string): Full address of the page, for example https://example.com/pricing.
- `user_agents` (array): Crawler names, for example Googlebot, GPTBot, ClaudeBot, PerplexityBot.

### `sitemap` (~110 tokens)

XML sitemap

The XML sitemap. Pick with mode: check = Check the sitemap and a sample of its URLs. Needs url. generate = Write a sitemap from a page list or audit. Needs audit_id.

Input parameters:

- `audit_id` (string): A finished site audit.
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default check.
- `url` (string): The site's home page, or the sitemap URL itself.

### `layout` (~181 tokens)

Layout and first screen

What visitors and crawlers see on every screen size. Pick with mode: render = First screen on phone, tablet and desktop in a real browser, and what crawlers without JavaScript get (default). Needs url. probe = A measurement script to run in the user's own browser tool. analyze = Analyse the results of that script. Needs url, results.

Input parameters:

- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default render.
- `no_js` (object): Optional: the probe result with JavaScript turned off, for an exact comparison.
- `results` (array): One probe result per viewport, each with device set to phone, tablet or desktop.
- `url` (string): Full address of the page, for example https://example.com/pricing.

### `internal_links` (~221 tokens)

Internal links

Internal links and link equity. Pick with mode: suggest = Links to add, with anchors, applied by Worker or CMS. Needs audit_id. equity = Internal PageRank and click depth from a site audit. Needs audit_id.

Input parameters:

- `audit_id` (string): Id of a completed site audit.
- `detail` (string): brief = short summary.
- `important_urls` (array): Optional. Pages that matter most, for example top pages by clicks or revenue.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default suggest.
- `phrases` (array): Optional: phrases to turn into the link, besides the anchor text, for example natural variants.
- `platform` (string): Optional: also return the links ready to apply: a Cloudflare Worker that links the first mention on each page, a WordPress edit plan, or the edits for the code.
- `target_url` (string): Page that should receive links.
- `topic` (string): Topic or main keyword of the target page.

### `compare` (~213 tokens)

Compare

Compare pages side by side. Pick with mode: pages = Your page against up to 3 competitors. Needs url, competitors. html = Two versions of HTML before and after. Needs before, after. preview = Deploy preview against production before merging. Needs preview_url, production_url.

Input parameters:

- `after` (string): HTML after the change.
- `before` (string): HTML before the change.
- `bypass_token` (string): Vercel protection bypass secret.
- `competitors` (array): Competitor page addresses.
- `detail` (string): brief = short summary.
- `keyword` (string): Optional search term to compare keyword use.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default pages.
- `paths` (array): Paths like /pricing, default /.
- `preview_url` (string): The deploy preview URL.
- `production_url` (string): The live site.
- `url` (string): Full address, for example https://example.com.

### `snippet` (~157 tokens)

Snippets and share cards

How a page looks in Google and when shared, measured in pixels the way Google truncates. Use it instead of estimating title or description length. Pick with mode: search = Title and description as Google shows them; give title (and description) or a url to read them. social = Open Graph and X cards, and the share image. Needs url.

Input parameters:

- `description` (string): Proposed meta description.
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default search.
- `title` (string): Proposed title tag text.
- `url` (string): Page to read the current title and description from, when no title is given.

### `entity` (~104 tokens)

Entity and trust

How Google understands who is behind a site. Pick with mode: graph = Organization, sameAs, logo and founder in structured data. Needs url. trust = Author, about, contact and policy signals. Needs url.

Input parameters:

- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default graph.
- `url` (string): Full address, for example https://example.com/blog/post.

### `text_quality` (~125 tokens)

Text quality

Readability and correct language. Pick with mode: readability = Readability that fits the page and the pages that rank. Needs url. spelling = Spelling and grammar errors in about 30 languages. Needs url.

Input parameters:

- `competitors` (array): Optional: top organic results for the keyword.
- `detail` (string): brief = short summary.
- `keyword` (string): Optional: the search term, for context.
- `memory_key` (string): site_memory key, records this call.
- `mode` (string): Default readability.
- `url` (string): Your page.

### `track_rankings` (~280 tokens)

Smart rank tracker that knows what matters

Use for ongoing rank tracking without picking keywords by hand. Each run, fetch Search Console rows by query and page (last 7 or 28 days) and, if connected, the rows of Ahrefs Rank Tracker (rank-tracker-overview) or Semrush Position Tracking, plus GA4 conversions or revenue per landing page if available, and pass them with the tracker_id (leave it out on the first run to create a tracker).

Input parameters:

- `action` (string): run (default), status or stop.
- `conversions` (array): Optional GA4 key events or revenue per landing page.
- `detail` (string): brief = short summary.
- `fix_log_id` (string): Optional fix log (log_fix) whose pages count as work done.
- `gsc_rows` (array): Search Console rows by query and page for the period.
- `memory_key` (string): site_memory key, records this call.
- `money_keywords` (array): Optional keywords you always want followed.
- `site` (string): Your site. Needed on the first run.
- `tracker_id` (string): From the first run. Leave out to create a tracker.
- `tracker_rows` (array): Ahrefs Rank Tracker or Semrush Position Tracking rows.
- `webhook_url` (string): Optional https webhook for the changes (Slack and Discord work).

Output parameters:

- `events` (array)
- `groups` (object)
- `runs` (number)
- `trackerId` (string)

### `prioritize_fixes` (~184 tokens)

Rank fixes by traffic impact

Use when Search Console, GA4, Ahrefs or Semrush data is available, also to explain a traffic drop (pass clicks_previous): ranks the fixes by the traffic or revenue they can win. Rank SEO fixes by how much traffic they can win, using data from the user's other connected tools. With GA4, also pass each page's organic conversions (key events) or revenue, and fixes are ranked by the money they can bring instead of clicks.

Input parameters:

- `audit_id` (string): Optional id of a finished site audit, so pages are not scanned again.
- `currency` (string): Currency of revenue, for example EUR or USD.
- `detail` (string): brief = short summary.
- `memory_key` (string): site_memory key, records this call.
- `pages` (array, required)
- `source` (string): Where the numbers come from.

Output parameters:

- `actions` (array)
- `mode` (string)
- `status` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-onpage-onpage/onpage#diagnostics

## Score history

- 2026-10-17: 73
- 2026-10-16: 73
- 2026-10-15: 73
- 2026-10-14: 73
- 2026-10-13: 73
- 2026-10-12: 72
- 2026-10-10: 67

## Common questions

### What is the OnPage.dev MCP server?

OnPage.dev is an MCP server listed in the public MCP registry as dev.onpage/onpage. Free SEO MCP that closes the loop: find, fix, ship as a PR or to a CMS, prove. 37 tools, no key. This page covers its hosted endpoint (https://onpage.dev/mcp).

### Is the OnPage.dev MCP server safe to use?

OnPage.dev scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the OnPage.dev MCP server expose?

OnPage.dev exposes 37 tools: site_memory, scan_page, site_audit, watch, dashboard, and 32 more. Their descriptions and schemas cost roughly 8,775 tokens of context every time the server is loaded.

### Does the OnPage.dev MCP server require authentication?

No. We connected to OnPage.dev without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the OnPage.dev MCP server still maintained?

OnPage.dev is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://onpage.dev/mcp
- Repository: https://github.com/seoonpage/seo-mcp-server
- Website: https://onpage.dev/mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-onpage-onpage/onpage.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-onpage-onpage/onpage.json
- HTML version of this page: https://verifymcp.io/servers/dev-onpage-onpage/onpage