mcp server

squirrelscan

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

Description as published by the maintainer. Source

• version 1.0.2
• active
• security

active — Most recent push to the repository was 2026-08-05. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

18 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

add_website(url, kind)

Register 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; idempotent per domain, so calling it again returns the existing website. Pass kind to classify it as owned or prospect up front. Required: url.

comment_on_issue(body, website_id, issue_number)

Post a comment on a website issue — use it to record analysis, a proposed fix, or what you changed, so the team sees it in the dashboard issue thread. Markdown is supported. Required: website_id, issue_number, body.

create_api_key(name, scopes, expires_in_days)

Mint a new squirrelscan API key for this organization (requires credentials carrying the keys:write scope, which OAuth sign-in grants). The key is returned EXACTLY ONCE: show it to the user immediately and suggest saving it as the SQUIRRELSCAN_API_KEY environment variable for the CLI, CI, and MCP. Minted keys cannot themselves mint keys. Required: name.

delete_website(confirm, website_id)

Delete 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 registers a fresh website with a new website_id. Call once without confirm to see what will happen; call again with confirm: true to delete. To remove many sites at once, use delete_websites. Required: website_id.

delete_websites(confirm, website_ids)

Delete 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 links keep working, slots are freed) and the same two-step confirm: call once without confirm to see the domain behind every id, then again with confirm: true. EVERY result echoes the domain, so read them back to the user before and after: an id is not a name, and this is the tool most likely to be pointed at the wrong list. The preview also shows each site's kind and an owned_count: unclassified sites read as owned, so an 'owned' entry in a list you built from prospects is the clearest sign the wrong ids were assembled. Ids that do not resolve are reported per-id, never as a whole-call failure. To pick the ids, list_websites with kind: "prospect" returns only sites explicitly marked disposable. Required: website_ids.

get_audit_status(run_id)

Poll a running audit by run_id (from run_audit or list_audits). Status pending/running means keep polling (every 15-30 seconds) — the response includes a progress field (phase, message, page/link counts) when available. Status completed means the report is ready: call get_report with the same run_id. Status failed/cancelled includes the error and completion reason. Required: run_id.

get_credit_balance

Get 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 before starting. Top up at https://app.squirrelscan.com/billing.

get_issue(website_id, issue_number, occurrence_limit)

Fetch one issue by website_id + issue number, including its full description, recommendation, affected pages, occurrence detail from the latest report (which page/image/URL, snippets), and comment thread. Use comment_on_issue to add analysis or a fix note to the thread. Required: website_id, issue_number.

get_report(format, run_id, top_issue_limit)

Fetch 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 issues (topIssues reference a rule_id; look up its name/description/solution once in the sibling `rules` dict rather than per occurrence). Each topIssues row carries `provenance`: "carried" means the finding is re-injected from a page not re-crawled this run (not a fresh result) — check `lastSeenAt` for when it was last actually observed. `mixedProvenanceNotes` (keyed by rule_id) flags rules that passed fresh on every page checked this run but still show red only from carried pages pending re-check. Also includes a `history` array of prior audits of this website with score/issue deltas when available; each entry carries its own `runId`/`reportId`, so you can walk backwards through a website's audits by calling get_report again with an earlier `runId` (use list_audits with website_id to page past what history returns); "llm" is a compact text rendering optimized for LLM context (carried findings marked inline); "markdown" is a full human-readable report. Start with summary, then pull llm or markdown when you need every issue and page detail. Required: run_id.

get_rule(rule_id)

Fetch one audit rule by id (e.g. "meta/title-length"), 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. Rule ids appear in report topIssues and issue rule_id fields. Required: rule_id.

list_audits(limit, offset, website_id)

List the organization's audit runs: currently active (pending/running) plus recent runs of any status. Pass website_id (from list_websites) to get one website's full audit history, oldest runs included, and page through it with limit/offset using the returned total/has_more. This is the way to reach the preserved reports of a soft-deleted website: its runs still list under its old website_id. total/has_more describe the `recent` array only, and `recent` already includes any pending/running run, so `active` is a live view of those same runs and not extra items to add to the count. Use the run ids with get_audit_status or get_report, and website ids with list_issues.

list_credit_transactions(limit, cursor)

Audit the organization's credit accounting log: grants (signup/monthly/pack/promo), debits (audit_base 50cr + render 2cr/page + folded 0-cost services), refunds, and adjustments — newest first, paginated. Each debit/refund carries `run_id` so you can group a single audit's spend. Use this to explain why an audit cost what it cost or to reconcile a balance. For one audit's per-feature breakdown, use get_report (its `cost` field). Read-only.

list_issues(limit, offset, status, category, severity, website_id)

List a website's open audit issues (like a bug tracker: each issue is one failing rule with occurrences across pages, numbered per website). Returns issues sorted by severity, plus severity and status summaries. Use the issue number with get_issue for full detail and comments. Filter by status/severity/category to narrow down. Required: website_id.

list_rules(search, category)

Browse the catalog of 260+ 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 find what a specific rule checks. Use get_rule for one rule's full detail.

list_websites(kind, limit, offset)

List websites the organization has audited, with their latest run status, health score, and owned/prospect kind. Each row carries last_run_id (the latest run, any status) and last_report_run_id / last_report_id (the latest completed run whose report has not been deleted) — pass last_report_run_id to get_report to read a website's newest report without knowing a run id in advance, or list_audits with website_id for its full history. Use the website_id with list_issues/get_issue. Websites registered but never audited do not appear; run_audit or add_website registers a new one. Ephemeral one-shot audits never appear. Returns total/has_more for pagination. Filter by kind to separate sites the user runs from one-off prospect audits: kind: "prospect" returns ONLY sites explicitly marked as such, so it is the safe way to build a bulk-delete list.

run_audit(url, kind, render, confirm, coverage, ephemeral, max_pages, max_credits)

Run a cloud audit of a website (crawl + 260+ rule analysis + report). Credits are spent as the audit runs (pay-as-you-go). The dry run is optional: pass confirm: true on the first call to start straight away. Without confirm, an audit whose estimate is over the org's auto-run threshold comes back as status "confirmation_required" with the estimate to show the user, and you call again with confirm: true; one at or under the threshold just starts. Use max_pages to size the crawl (max_pages: 1 audits just the entry URL, the cheapest run). Audits are asynchronous and take minutes: poll get_audit_status with the returned run_id, then fetch results with get_report. The website is registered automatically on first audit. Required: url.

send_feedback(run_id, message, category, website_id)

Report your experience using squirrelscan mid-session: a bug, a missing feature, what worked, what confused you, missing report data, or tool ergonomics. Reviewed by the team to improve the product — use it any time something surprises you, not just at the end of a session. Works with any authenticated credentials, including read-only API keys. Required: category, message.

whoami

Identify the current credentials: how you are authenticated, which organization you act for, the plan, and the current credit balance. Call this first in a session to orient yourself before running audits.

Last successful function declaration observed on 2026-08-13. Source: https://mcp.squirrelscan.com/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://mcp.squirrelscan.com/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/squirrelscan/squirrelscan
• Website — https://squirrelscan.com
• Remote endpoint (streamable-http) — https://mcp.squirrelscan.com/mcp

Related, by what their authors tagged them

• WebAnatomy — last commit 2026-07-02, shares website
  Help your AI improve landing pages, grounded in 3,500+ scored sections and 500 real pages.
• Crosby, TX Weather — last commit 2026-08-05, shares website
  Crosby, TX weather, air quality, tropics, floods, fishing, pollen, roads, radar, news & schools.
• ShipStatic — last commit 2026-08-06, shares website
  Deploy websites from AI agents. Free at mcp.shipstatic.com. Install for the full toolset.
• io.github.eugenregehr/geo-seo-analyzer-octoboost — last commit 2026-03-24, shares performance, seo
  Analyze multiple URLs with categorized SEO / GEO checks and scored results.
• io.github.eugenregehr/octoboost — last commit 2026-03-24, shares performance, seo
  Analyze multiple URLs with categorized SEO / GEO checks and scored results.
• io.github.carloshpdoc/memorydetective — last commit 2026-05-25, shares performance
  iOS leak/perf debugging via MCP: memgraph cycles, .trace analysis, SourceKit-LSP bridging.
• io.github.dragnoir/shopify-theme-inspector — last commit 2026-08-05, shares performance
  Profile Shopify Liquid performance, find slow theme code, and explain fixes in plain language.
• io.github.ganapativs/microcharts — last commit 2026-08-07, shares performance
  Find, wire, and render microcharts — word-sized React charts with generated alt text.
• io.github.commitshow/audit — last commit 2026-07-24, shares audit, cli
  Score any public GitHub repo 0-100 against the commit.show audit rubric.
• io.github.commitshow/legitshow-search — last commit 2026-07-24, shares audit, cli
  Search launched software (SaaS, AI tools, MCP servers) by measured production-readiness.

These share tags the maintainers applied themselves, such as website, performance, seo, audit. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agent, audit, cli, llm, performance, seo, website.