Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Panda Web Security Tools

PYPI · PANDA-WEB-SECURITY-TOOLS

Site/email/agent safety and monitors: SPF/DKIM, SEO, change + RSS monitors, hidden-AI, WHOIS (7).

+3 this week 68 Trust /100

Last scanned (9 hours ago)

Scores higher than 61% of PyPI servers

Category Security

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to pandadad0214/panda-web-security-tools). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 10 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability58
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 6232 tokens (~890/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 18 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 17 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 11 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/panda-web-security-tools@0.2.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo pandadad0214/panda-web-security-tools
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/pandadad0214/panda-web-security-tools/.github/workflows/release.yml@refs/tags/v0.2.0
Rekor log index 3789100286
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:a3166b1a7557cfd4a7843a80a0a3545dd7b3c6d0aefe08c3bd9b01b4540ba543

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 31 packages
Packages resolved 31
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~5,990 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ai_search_seo_audit ~801

Audit web pages for classic SEO and for AI-search readiness (ChatGPT, Perplexity, Claude, Google AI Overviews): titles, meta, schema/FAQ markup, author/date signals, blocked AI crawlers, llms.txt and ranked fixes, with an SEO score and an AI-readiness score per page. Unlike website_change_monitor (diffs pages over time) and hidden_ai_instructions_scanner (finds concealed prompt-injection text), this grades how discoverable and citable a page is. Use when you need an on-page SEO/GEO audit or an llms.txt draft. Do not use for change tracking (use website_change_monitor) or security scanning (use hidden_ai_instructions_scanner or email_domain_security_checker). Parameters: crawlInternalLinks multiplies pages: each URL can add up to that many same-site pages, and every page is billed, so maxPages/run_max_items is the real cost cap. generateLlmsTxt drafts one llms.txt per site lacking it at no extra charge. Pages that block our crawler are returned unbilled. Returns per item: agentSummary, url, seoScore, aiReadinessScore, title, metaDescription, h1, wordCount, schemaTypes, faqSchema, aiSearchBotsBlocked, aiTrainingBotsBlocked, llmsTxt, sitemapFound, canonical, noindex, crawlerBlocked, fixes. Behavior: read-only; runs the Apify Actor pandadad0214/ai-search-seo-audit (https://apify.com/pandadad0214/ai-search-seo-audit) on your own Apify account. Price: $0.004 per page audited. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxPages when you leave it unset, so it also limits what is billed; setting maxPages higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

NameTypeReqDescription
crawlInternalLinksinteger–Also audit internal pages (per URL). 0 = audit only the URLs above. 1 to 100 = also audit up to this many same-site pages linked from each URL (good for a quick whole-site check from the homepage).
generateLlmsTxtboolean–Draft an llms.txt for sites without one. On by default: for each site with no /llms.txt, writes a ready-to-edit draft (from the audited pages and homepage links) into the LLMS_TXT_DRAFTS record and t…
maxPagesinteger–Maximum pages. You pay per audited page, so this also caps the cost. Whole number, 1 to 2,000; default 50.
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
urlsarray–Page URLs. Pages to audit, one per line. https:// is added if missing (example.com/pricing works). Leave empty for a 2-page demo.

No output schema declared.

No examples provided.

broken_link_checker ~787

Crawl one or more start pages and check every unique http(s) link for HTTP status, final URL after redirects, a broken flag (status 400+) and a redirected flag, with external links checked by default. Unlike ai_search_seo_audit (page SEO/GEO scoring) and website_change_monitor (content diffs over time), this finds dead and redirecting links. Use when SEO, content or agency teams need a 404 report for a site or page. Do not use to search the web, to crawl a whole large site in one call or to check private or internal addresses (blocked and never billed). Parameters: startUrls (required in practice) are the pages crawled; maxPages is pages followed per host (1 = only the start pages); maxLinks caps checked links and therefore billing; checkExternal=false stays on-site; timeoutSecs is the per-request timeout (default 15). Billed per link that returns an HTTP status; timeouts, DNS failures and robots-skipped targets are free. Returns per item: agentSummary, originalUrl, finalUrl, statusCode, broken, redirected, external, contentType, sourcePage, error; plus LINKS_XLSX (all links plus a Broken sheet)/CSV. Behavior: read-only; runs the Apify Actor pandadad0214/broken-link-checker (https://apify.com/pandadad0214/broken-link-checker) on your own Apify account. Price: $0.001 per link checked. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxLinks when you leave it unset, so it also limits what is billed; setting maxLinks higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

NameTypeReqDescription
checkExternalboolean–Check outbound (external) links. When on, links to other hosts are checked too. Turn off to check only same-host links.
maxLinksinteger–Maximum links to check. Maximum unique http(s) URLs to check. This is what you are charged for. Hard max 2,000. (maxResults is accepted as an alias.)
maxPagesinteger–Pages to crawl per host. How many HTML pages on the same host as each start URL to fetch for extracting more links. 1 = only the start URL(s). Further same-host pages are queued only when this is gre…
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
startUrlsarray–Start URLs. Pages to start from. The Actor fetches each page, extracts http(s) links, and checks them. Leave empty for a short demo on example.com. One URL per line.
timeoutSecsinteger–Per-request timeout (seconds). How long to wait for each request. Timed-out URLs are recorded but not charged.

No output schema declared.

No examples provided.

bulk_domain_whois_expiry ~878

Check many domains at once with official RDAP (WHOIS fallback): registered or available, registrar, created/updated/expiry dates, days to expiry, transfer lock and pending-delete status, nameservers, DNS host and DNSSEC. Unlike email_domain_security_checker (SPF/DKIM/DMARC mail security) and company_website_enricher (site content and contacts), this is registration and expiry data for a domain portfolio. Use when you audit a domain portfolio for renewals, check which names are available, or verify registrar and DNS host for vendors or phishing look-alikes. Do not use for website content, uptime or email-auth checks (use email_domain_security_checker). Parameters: domains accepts URLs (scheme, www and paths stripped; duplicates dropped; up to 10,000); rootDomainOnly (default true) reduces subdomains to the registrable domain; expiringWithinDays sets the expiringSoon flag and only=expiringSoon|available|registered returns (and bills) just that subset; sortBy=expiry puts the soonest renewals first; followRegistrar adds registrant org/country when published but is slower; maxResults caps billed domains. Failed lookups are free. Returns per item: agentSummary, domain, registered, available, registrar, registrarIanaId, createdDate, updatedDate, expiresDate, daysToExpiry, ageYears, expiringSoon, statuses, transferLocked, pendingDelete, nameservers, dnsHost, dnssec, registrantOrg, registrantCountry, abuseEmail, source; plus DOMAINS_XLSX/CSV. Behavior: read-only; runs the Apify Actor pandadad0214/bulk-domain-whois-expiry (https://apify.com/pandadad0214/bulk-domain-whois-expiry) on your own Apify account. Price: $0.001 per domain checked. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for…

NameTypeReqDescription
domainsarray–Domains. Up to 10,000 domains or URLs (https://, www. and paths are removed; duplicates dropped).
expiringWithinDaysinteger–Expiring soon = within N days. Flags domains whose expiry is this close. Default 60.
followRegistrarboolean–Ask the registrar's RDAP too. Adds registrant org/country when the registrar publishes them (slower).
maxResultsinteger–Maximum results. You pay per domain returned, so this also caps the cost. Default 1000.
onlystring–Only return. Filter the results (you pay only for returned domains). Choices: all = All domains; expiringSoon = Expiring soon only; available = Not registered (likely available) only; registered = Re…
rootDomainOnlyboolean–Look up the root domain. blog.example.co.uk -> example.co.uk. Off = look up exactly what you typed.
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
sortBystring–Sort by. Order of results. Choices: input = Input order; expiry = Soonest expiry first.

No output schema declared.

No examples provided.

email_domain_security_checker ~749

Audit email authentication for a list of domains: SPF, DKIM (about 40 common selectors), DMARC, MX provider, MTA-STS, TLS-RPT and BIMI, graded A-F with spoofing risk and plain-English fixes. Unlike company_website_enricher (firmographics, tech stack, contacts), this only grades mail security posture from public DNS. Use when you need deliverability or spoofing checks, a security prospect list, or a vendor review. Do not use for website SEO or AI-readiness (use ai_search_seo_audit) or for page-level prompt injection (use hidden_ai_instructions_scanner). Parameters: domains accept bare domains, emails or URLs and are normalized and de-duplicated. DKIM is only confirmed when a selector matches; add dkimSelectors you know are in use, otherwise a missing DKIM may be a false negative. Nonexistent or unresolvable domains are returned with a status and not charged. Returns per item: agentSummary, domain, grade, score (0-100), spoofable, mailProvider, spfRecord, spfAll, spfLookups, dmarcRecord, dmarcPolicy, dmarcReporting, dkimSelectorsFound, mtaSts, tlsRpt, bimi, mxHosts, fixes (prioritized), status. Behavior: read-only; runs the Apify Actor pandadad0214/email-domain-security-checker (https://apify.com/pandadad0214/email-domain-security-checker) on your own Apify account. Price: $0.002 per domain checked. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxDomains when you leave it unset, so it also limits what is billed; setting maxDomains higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

NameTypeReqDescription
dkimSelectorsarray–Extra DKIM selectors. Optional. About 40 common selectors (google, selector1, selector2, k1, s1, s2, default…) are always tried. Add your own if you sign with a custom one, e.g. 20230601 or mailo.
domainsarray–Domains, emails or URLs. One per line: example.com, name@example.com or https://www.example.com/page all work (the domain is extracted, www. removed, duplicates dropped). Leave empty for a 3-domain d…
maxDomainsinteger–Maximum domains. You pay per checked domain, so this also caps the cost. Whole number, 1 to 10,000; default 1,000.
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).

No output schema declared.

No examples provided.

hidden_ai_instructions_scanner ~906

Scan web pages for text hidden from people but read by AI agents (display:none, off-screen, tiny or same-color text, HTML comments, alt/meta/data attributes, zero-width and Unicode tag characters) and classify it as policy notice, manipulation or harmful prompt injection, with location and excerpt. Unlike ai_search_seo_audit (visible SEO and AI-readiness) and website_change_monitor (diffs over time), this is a security check on content an agent is about to read. Use when an agent or workflow will ingest a page and you need to know whether it carries hidden instructions, or when auditing your own site. Do not use for SEO grading (use ai_search_seo_audit) or for email security (use email_domain_security_checker). Parameters: renderJs=true runs a real browser to catch script-injected text (much slower, plus settleSecs per page); off is a fast HTTP read. agentUaDiff adds three fetches per page (GPTBot, ClaudeBot, ChatGPT-User) to detect cloaking. crawlDepth follows same-site links but maxPages always caps the run. Findings are leads for review, not proof of intent. Returns per item: page summaries (type page-summary, url, verdict, findings, categories, topSeverity, techniques, agentSummary) and findings (technique, location, excerpt, category, severity). Behavior: read-only; runs the Apify Actor pandadad0214/hidden-ai-instructions-scanner (https://apify.com/pandadad0214/hidden-ai-instructions-scanner) on your own Apify account. Price: free (no per-result charge). Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxPages when you leave it unset, so it also limits what is billed; setting maxPages higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long te…

NameTypeReqDescription
agentUaDiffboolean–Check AI-agent cloaking. Also fetch each page as GPTBot, ClaudeBot and ChatGPT-User and flag AI-addressed text served to those agents but not to a normal browser.
crawlDepthinteger–Crawl depth. 0 = only the URLs you give. 1+ = also follow same-site links that many clicks deep (signed-out pages only). Max pages still caps the run.
maxPagesinteger–Max pages. Hard cap on pages scanned in one run.
minSeveritystring–Minimum severity. Drop findings below this severity. Choices: low = Low (include policy notices); medium = Medium; high = High only.
renderJsboolean–Render JavaScript (browser). Off: fast HTTP fetch, reads inline styles, rules, comments, meta, data-* and other attributes, JSON-LD/script data blocks, iframe srcdoc and Unicode tricks. On: loads eac…
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
settleSecsinteger–Wait after load (render mode). Extra wait after network idle so text injected on a timer is caught.
timeoutSecsinteger–Page timeout. Per-page load timeout.
urlsarrayyesPage URLs. Pages to scan, one per line. Each URL is scanned once; links are not followed.

No output schema declared.

No examples provided.

rss_feed_monitor ~895

Watch many RSS 2.0, Atom or JSON Feed URLs, or plain website and blog URLs (the feed is found automatically), and return one row per item with title, link, published date, age, author, plain-text summary, categories, enclosure and matched keywords. With onlyNew (default true) the Actor remembers returned items per stateKey in a named key-value store in your account, so scheduled runs return and bill only items that are new since the last run. Unlike website_change_monitor (diffs a whole page) and federal_register_monitor (US rulemaking only), this follows any site's feed. Use when you need a daily digest of competitor blogs, news, regulator or vendor feeds, filtered by keywords. Do not use for pages without a feed (use website_change_monitor), for full article text or for private or internal addresses (blocked and never billed). Parameters: feeds (up to 500); keywords and excludeKeywords match title, summary and categories; maxAgeHours skips old items; onlyNew and stateKey control the memory (use a different stateKey per watch list); maxItemsPerFeed (default 50); summaryChars (default 500); maxResults caps billed items. Items already seen, failed feeds and empty runs are free; per-feed health is in FEED_STATUS. Returns per item: agentSummary, feedTitle, feedUrl, siteUrl, title, link, published, ageHours, author, summary, categories, enclosureUrl, matchedKeywords, itemKey; plus RSS_XLSX/CSV. Behavior: read-only; runs the Apify Actor pandadad0214/rss-feed-monitor (https://apify.com/pandadad0214/rss-feed-monitor) on your own Apify account. Price: $0.0005 per feed item returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes,…

NameTypeReqDescription
excludeKeywordsarray–Exclude keywords. Drop items containing any of these words.
feedsarray–Feeds or websites. RSS, Atom or JSON Feed URLs, or plain website/blog URLs (the feed is found automatically). Up to 500 per run.
keywordsarray–Keywords (any). Keep items whose title, summary or categories contain any of these words (case-insensitive). Empty = keep all.
maxAgeHoursinteger–Maximum age (hours). Skip items older than this. 0 or empty = any age. Undated items are kept.
maxItemsPerFeedinteger–Max items per feed. Newest N items considered per feed. Default 50.
maxResultsinteger–Maximum results. You pay per item returned, so this also caps the cost. Default 500.
onlyNewboolean–Only new items since last run. Default on. Remembers returned items (per state key) in a named key-value store, so scheduled runs return and charge only new items.
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
stateKeystring–State key. Separate memory for different watch lists, e.g. competitors or regulators. Default: default.
summaryCharsinteger–Summary length (characters). Plain-text summary length per item. Default 500.

No output schema declared.

No examples provided.

website_change_monitor ~974

Check a watch list of web pages against snapshots saved by your previous run and report added and removed text, change percent, price changes and keyword appear/disappear alerts, with an optional webhook when something changes. Unlike ai_search_seo_audit (one-time quality audit) and hidden_ai_instructions_scanner (concealed AI-directed text), this is stateful diffing over time. Use when you need to track competitor pricing, terms, product or careers pages on a schedule. Do not use for a one-off page read or audit (use ai_search_seo_audit), or for pages behind a login. Parameters: the first run per monitorName only saves baselines (status 'baseline saved'); reuse the same monitorName for every later run, and use a new name for a separate watch list. cssSelector, ignorePatterns and ignoreNumbersAndDates cut false alarms from banners, counters and timestamps. Below minChangePercent the old snapshot is kept, so small edits accumulate. onlyReportChanges shrinks output but every page checked is still billed; unreachable pages are free. webhookUrl posts outside the Apify run; only set it if you control that endpoint. Returns per item: agentSummary, url, label, status, changed, changePercent, addedCount, removedCount, addedLines, removedLines, prices, priceChanges, keywordsPresent, keywordsAppeared, keywordsDisappeared, titleBefore, titleAfter, previousCheckAt. Behavior: read-only; runs the Apify Actor pandadad0214/website-change-monitor (https://apify.com/pandadad0214/website-change-monitor) on your own Apify account. Price: $0.0015 per page checked. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxPages when you leave it unset, so it also limits what is billed; setting maxPages higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300)…

NameTypeReqDescription
cssSelectorstring–Only watch this part (CSS selector). Optional. Compare only the matching elements, e.g. main or #pricing. Ignores headers, footers and banners.
ignoreNumbersAndDatesboolean–Ignore dates and times. Strip dates and clock times before comparing, to avoid noise from 'updated today' widgets.
ignorePatternsarray–Ignore text matching (regex). Optional regular expressions removed before comparing (counters, timestamps, rotating promos).
maxPagesinteger–Maximum pages. You pay per page checked, so this also caps the cost.
minChangePercentnumber–Minimum change to report (%). Changes smaller than this are reported as 'unchanged (below threshold)' and the old snapshot is kept, so small edits add up.
monitorNamestring–Monitor name. Snapshots are saved in your account under this name (key-value store panda-change-monitor-). Use different names for separate watch lists; each run compares with the last run of the sam…
onlyReportChangesboolean–Dataset: changed pages only. Skip unchanged pages in the dataset (handy for alerts and integrations). Every page checked is still billed; failed pages never are.
run_max_charge_usdnumber–Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
run_max_itemsinteger–Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
run_timeout_secsinteger–Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
urlsarray–Pages to watch. One URL per line. Optional label after ' | ' (e.g. https://acme.com/pricing | Acme pricing). Leave empty for a 2-page demo.
watchKeywordsarray–Alert keywords. Optional. Reports when any of these words appear on or disappear from a page.
webhookUrlstring–Webhook URL for changes (optional). Optional https URL (Slack/Zapier/Make/n8n webhook). Gets a JSON POST listing changed pages, only when something changed.

No output schema declared.

No examples provided.

Install

How do I install the Panda Web Security Tools MCP server?

Panda Web Security Tools runs locally as a PyPI package, launched with uvx panda-web-security-tools. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · panda-web-security-tools

# add to Claude Code
claude mcp add pandadad0214-panda-web-security-tools -- uvx panda-web-security-tools
Common questions

What is the Panda Web Security Tools MCP server?

Panda Web Security Tools is an MCP server listed in the public MCP registry as io.github.pandadad0214/panda-web-security-tools. Site/email/agent safety and monitors: SPF/DKIM, SEO, change + RSS monitors, hidden-AI, WHOIS (7). This page covers its PyPI package (panda-web-security-tools).

Is the Panda Web Security Tools MCP server safe to use?

Panda Web Security Tools scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 Panda Web Security Tools MCP server expose?

Panda Web Security Tools exposes 7 tools: email_domain_security_checker, ai_search_seo_audit, website_change_monitor, hidden_ai_instructions_scanner, bulk_domain_whois_expiry, and 2 more. Their descriptions and schemas cost roughly 5,990 tokens of context every time the server is loaded.

Is the Panda Web Security Tools MCP server still maintained?

Panda Web Security Tools is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Panda Web Security Tools MCP server under?

Panda Web Security Tools declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Panda Web Security Tools MCP server?

VerifyMCP ran 15 checks on Panda Web Security Tools, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Panda Web Security Tools: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.