Agents Index

squirrelscan

Online

Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.

Visit publisherConnectJSON

What it can do: 38 tools

  • run_auditRun a cloud audit of a website (crawl + 350+ rule analysis + report). Only for sites the user owns or is authorized to test. Credits are spent as the audit runs (pay-as-you-go). The dry run is optional: pass confirm: tru
  • get_audit_status read-onlyPoll a running audit by run_id (from run_audit or list_audits). Status queued/pending/running means keep polling (every 15-30 seconds): the response includes a progress field (phase, message, current, total, failed, pend
  • list_audits read-onlyList the organization's audit runs: currently active (queued/pending/running; queued means waiting for a free cloud slot, and it starts by itself) plus recent runs of any status. Pass website_id (from list_websites) to g
  • list_websites read-onlyList the websites registered with the organization, with their name (`name`: the display name, else the title the site gives itself, else the domain), latest run status, health score, and owned/prospect kind. Each row ca
  • add_websiteRegister a website with the organization without running an audit (run_audit registers automatically, so this is only needed to set a site up ahead of time). Returns the website_id. Calling it again for the same domain r
  • delete_websiteDelete a website from the organization (soft delete: past audits, reports, and issues are preserved, and published report links keep working). Frees a slot under the plan's website limit. Re-adding the same domain later
  • delete_websitesDelete up to 50 websites in one call, for cleaning up a dashboard that has filled with one-off or prospect audits. Same soft delete as delete_website (past audits, reports, and issues are preserved, published report link
  • get_website_settings read-onlyRead one website's stored audit settings: its audit level (quick, surface, full or custom) with the page cap, crawl strategy, rendering and external link checks it sets, the crawl depth, crawl scope, include/exclude patt
  • update_website_settingsChange one website's stored audit settings: level, max_pages, render, external_links, max_depth, scope, include_patterns, exclude_patterns and internal_links, broken_link_alerts (Pro and Team; switching it off is allowed
  • list_folders read-onlyList the organization's website folders (the groups the dashboard files sites into), each with its folder_id, name and how many websites it holds. Use a folder_id or name with move_websites_to_folder, or a folder_id with
  • create_folderCreate a website folder with a name of 1 to 60 characters. Names are unique per organization, ignoring case: a name that already exists is refused with the existing folder_id in the error. Creating a folder costs nothing
  • move_websites_to_folderMove up to 200 websites into a folder, or out of any folder. Name the folder with folder_id or folder (its name, ignoring case; both from list_folders). A folder that does not exist is an error, unless create_if_missing
  • get_report read-onlyFetch the finished report for an audit run (use the run_id from run_audit once get_audit_status shows completed). Formats: "summary" (default) is structured JSON with health score, category scores, and the top failing is
  • compare_audits read-onlyCompare two completed audits of one website and get what changed. Defaults to the website's latest completed audit against the one before it; pass base/head run ids to compare any two. The DEFAULT answer is a short summa
  • list_issues read-onlyList a website's issues (cloud only). An ISSUE is an action plan, like a bug tracker ticket numbered per website: a title, a Markdown plan, a priority, a type and the FINDINGS it covers. A FINDING is what an audit proves
  • get_issue read-onlyFetch one issue (an action plan; cloud only) by website_id + issue number: its Markdown plan `body_md`, priority, type, effort, labels, state and state reason, the FINDINGS it covers (`covered_findings`, up to 100 with t
  • comment_on_issuePost a comment on a website issue (a triaged action plan or an older one-rule issue alike) to record analysis, a proposed fix, or what you changed, so the team sees it in the dashboard issue thread. Comments stay on the
  • update_issueChange one website issue (an action plan; cloud only) the way a person does in the dashboard: its status (open, in_progress, resolved, dismissed for a close as not planned that stays closed, wontfix), its assignee (the u
  • list_path_ignores read-onlyList the path-scoped rule ignores stored for one website: each is a rule id plus a path glob, and findings of that rule on matching page paths are left out of later audit reports, their score and the issue tracker while
  • add_path_ignoreIgnore one rule on the pages of a website whose path matches a glob, for example rule core/meta-title with /blog/archive/**. Later audits leave those findings out of the report and its score, and open tracker issues ever
  • remove_path_ignoreRemove one path ignore from a website. Tracker issues it alone was holding go back from ignored to open; the findings appear again in the next audit's report and score. Needs the audits:write scope and an owner or admin
  • dismiss_issueClose one website issue as not planned (status dismissed): it stays closed when a later audit runs. The same write as update_issue with status dismissed. Closing a real problem as not planned hides it from the tracker, s
  • list_findings read-onlyList the raw FINDINGS of one audit of a website (cloud audits). A FINDING is what an audit proved: one rule's failing or warning check, exactly as the audit reported it (no model-written text, no rewriting), so it is the
  • list_entities read-onlyList the entities a site declares in its JSON-LD, collapsed across every crawled page into one graph, so an Organization declared identically on 60 pages is one row rather than 60. Declarations collapse by resolved @id,
  • get_entity read-onlyGet one entity as the map recorded it: the properties the map keeps (name, url, logo, image, sameAs, telephone, email, address, description), the pages that declare it, the properties whose values disagree between those
  • get_entity_graph read-onlyGet the whole entity graph, or a filtered part of it, in a chosen format: json for the canonical document, jsonld for a validator, mermaid or markdown to read in a conversation, dot or graphml for a graph tool. Defaults
  • compare_entities read-onlyCompare two audits of a site and get the change set: entities added and removed, entities that gained or lost an @id, occurrence changes, new and resolved conflicts and dangling references, summary deltas, and the pages
  • get_entity_findings read-onlyGet the schema/entity-* rule verdicts for an audit: what is wrong with the site's entity graph, which entity keys and pages each finding affects, and the fix text for each. Use this instead of re-deriving the problems fr
  • list_pages read-onlyOne row per page a stored audit crawled, failed pages included: url, final url, status, canonical, noindex, title and length, description and length, h1, heading count, word count, JSON-LD types and @ids, internal links
  • list_rules read-onlyBrowse the catalog of 350+ audit rules that run during an audit, grouped into categories (crawlability, meta tags, performance, security, accessibility, content, and more). Filter by category code or search by keyword to
  • get_rule read-onlyFetch one audit rule by id (e.g. "core/meta-title"), including what it checks, how to fix it (recommendation), its severity and score weight, a docs link, and whether it is a cloud (credit-billed) rule (`requires_cloud`)
  • whoami read-onlyIdentify the current credentials: how you are authenticated, which organization you act for, the plan, and the current credit balance. Useful at the start of a session, to see which organization the other tools act for.
  • get_credit_balance read-onlyGet the organization's credit balance: monthly credits (reset each billing period) and pack credits (purchased, never expire). Audits spend credits pay-as-you-go while they run; run_audit shows an upper-bound estimate be
  • list_credit_transactions read-onlyAudit the organization's credit accounting log: grants (signup/monthly/pack/promo), debits (audit_base 50cr + audit_page 2cr per audited page + external_link 1cr per checked link + folded 0-cost services; older audits ca
  • create_api_keyMint a new squirrelscan API key for this organization and return it. The result contains a secret, a live credential for the organization, returned exactly once and never retrievable again; it is meant to be saved as the
  • send_feedbackSend feedback to the squirrelscan team: a bug, a missing feature, what worked, what was confusing, missing report data, or tool ergonomics. Use it when the user wants to report something or share their experience. Works
  • verify_urlCheck whether one URL is really live. Returns state live (answered 2xx), redirected (with finalUrl), dead (confirmed 4xx/5xx or a domain that does not exist), blocked (alive but bot protection refused every tier) or unve
  • list_notifications read-onlyRead the organization's notification feed, newest first: what finished, what broke, and what changed since you last looked. Categories include audit_complete, issues_detected, audit_failed, broken_links, link_monitoring,

Connect it

Claude Code
claude mcp add --transport http squirrelscan https://mcp.squirrelscan.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.squirrelscan.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "squirrelscan": {
      "url": "https://mcp.squirrelscan.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "squirrelscan": {
      "type": "http",
      "url": "https://mcp.squirrelscan.com/mcp"
    }
  }
}

Questions

What does squirrelscan do?

Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP. It exposes 38 tools to AI assistants.

What tools does squirrelscan provide?

38 tools, including run_audit, get_audit_status, list_audits, list_websites, add_website, delete_website, delete_websites, get_website_settings, update_website_settings, list_folders, create_folder, move_websites_to_folder….

How do I connect squirrelscan to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.squirrelscan.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does squirrelscan require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is squirrelscan online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes squirrelscan?

squirrelscan.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Web Search & Scraping