Categories › Software Development › Git hosting, PRs, issues & code review
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
Remote server: your requests and data go to mcp.squirrelscan.com. Claude Code: claude mcp add --transport http squirrelscan https://mcp.squirrelscan.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
run_audit — Run a cloud audit of a website (crawl + 300+ rule analysis + report). Only for sites the user owns or is authorized to test. Credits are speget_audit_status — Poll a running audit by run_id (from run_audit or list_audits). Status queued/pending/running means keep polling (every 15-30 seconds): the list_audits — List the organization's audit runs: currently active (queued/pending/running; queued means waiting for a free cloud slot, and it starts by ilist_websites — List websites the organization has audited, with their name (`name`: the display name, else the title the site gives itself, else the domainadd_website — Register a website with the organization without running an audit (run_audit registers automatically, so this is only needed to set a site udelete_website — Delete a website from the organization (soft delete: past audits, reports, and issues are preserved, and published report links keep workingdelete_websites — 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 deletget_website_settings — Read one website's stored audit settings: its audit level (quick, surface, full or custom) with the page cap, crawl strategy, rendering and update_website_settings — Change one website's stored audit settings: level, max_pages, render, external_links, max_depth, scope, include_patterns, exclude_patterns aget_report — Fetch the finished report for an audit run (use the run_id from run_audit once get_audit_status shows completed). Formats: "summary" (defaulcompare_audits — Compare two completed audits of one website and get what changed. Defaults to the website's latest completed audit against the one before itlist_issues — List 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, get_issue — Fetch one issue (an action plan; cloud only) by website_id + issue number: its Markdown plan `body_md`, priority, type, effort, labels, statcomment_on_issue — Post 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 cupdate_issue — Change one website issue (an action plan; cloud only) the way a person does in the dashboard: its status (open, in_progress, resolved, dismilist_findings — List 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, exaclist_entities — List the entities a site declares in its JSON-LD, collapsed across every crawled page into one graph, so an Organization declared identicallget_entity — Get one entity as the map recorded it: the properties the map keeps (name, url, logo, image, sameAs, telephone, email, address, description)get_entity_graph — Get the whole entity graph, or a filtered part of it, in a chosen format: json for the canonical document, jsonld for a validator, mermaid ocompare_entities — Compare two audits of a site and get the change set: entities added and removed, entities that gained or lost an @id, occurrence changes, neget_entity_findings — Get the schema/entity-* rule verdicts for an audit: what is wrong with the site's entity graph, which entity keys and pages each finding afflist_pages — One row per page a stored audit crawled, failed pages included: url, final url, status, canonical, noindex, title and length, description anlist_rules — Browse the catalog of 300+ audit rules that run during an audit, grouped into categories (crawlability, meta tags, performance, security, acget_rule — Fetch one audit rule by id (e.g. "core/meta-title"), including what it checks, how to fix it (recommendation), its severity and score weightwhoami — Identify the current credentials: how you are authenticated, which organization you act for, the plan, and the current credit balance. Usefuget_credit_balance — Get the organization's credit balance: monthly credits (reset each billing period) and pack credits (purchased, never expire). Audits spend list_credit_transactions — Audit the organization's credit accounting log: grants (signup/monthly/pack/promo), debits (audit_base 50cr + audit_page 2cr per audited pagcreate_api_key — Mint a new squirrelscan API key for this organization and return it. The result contains a secret, a live credential for the organization, rsend_feedback — Send feedback to the squirrelscan team: a bug, a missing feature, what worked, what was confusing, missing report data, or tool ergonomics. verify_url — Check whether one URL is really live. Returns state live (answered 2xx), redirected (with finalUrl), dead (confirmed 4xx/5xx or a domain thalist_notifications — Read the organization's notification feed, newest first: what finished, what broke, and what changed since you last looked. Categories incluNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.