Landfall MCP server
io.github.landfall-audit/landfalllandfall-auditstreamable-httpv1.4.0Scanned
Local business leads and website intelligence for AI agents: lead lists, contacts, tracking, SEO and
9 tools: 5 change things and 4 only read.
- Reads private data · 1
- Reads text others write · 8
- Can send data out · 7
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
5 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Landfall MCP server can do
The Landfall MCP server is published by the GitHub account landfall-audit. It has 9 tools. It can create or change data (5 tools: audit_landing_page, check_tracking, check_structured_data, check_crawlability and 1 more), but cannot delete data. 4 tools only read.
1 tool reads private data (get_business_details); 8 tools bring in text other people can write (audit_landing_page, get_business_details, check_tracking and 5 more); 7 tools can send data out of your system (audit_landing_page, get_business_details, check_tracking and 4 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 4, 2026, version 1.4.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
9 tools
Changes things 5Claude Code: ask
audit_landing_pageAudit a landing page before sending paid ad traffic.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Audit a landing page before sending paid ad traffic. Returns a 0-100 readiness score, a ready / fix_first / not_ready verdict, Meta, Google and TikTok tags with IDs, conversion paths (forms, click-to-call, WhatsApp, booking), trust and speed facts, and the top 5 fixes in priority order. Costs 0.05 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
check_crawlabilityCheck whether search engines and AI crawlers may read a page and how the site is mapped: robots.txt evaluated with Google's matching rules for Googlebot, Bingbot, GPTBot, OAI-Searc…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Check whether search engines and AI crawlers may read a page and how the site is mapped: robots.txt evaluated with Google's matching rules for Googlebot, Bingbot, GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Applebot-Extended and others (with the rule that decided each), meta robots and X-Robots-Tag, canonical link, declared sitemaps with entry counts and freshness, and llms.txt, with a list of fixes. Costs 0.01 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
check_structured_dataCheck a page's structured data: finds every schema.org item (JSON-LD, microdata, RDFa), reports JSON-LD that does not parse, checks each item against the required and recommended p…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Check a page's structured data: finds every schema.org item (JSON-LD, microdata, RDFa), reports JSON-LD that does not parse, checks each item against the required and recommended properties for common types (LocalBusiness, Organization, Product, Offer, Article, FAQPage, BreadcrumbList, Event, Review, JobPosting and more), flags bad dates, ratings and URLs, and reports Open Graph, Twitter card and canonical tags, with a list of fixes. Costs 0.01 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
check_trackingCheck which ad pixels and analytics a website runs: Meta Pixel, Google Ads and TikTok tags with their IDs, Google Analytics 4, tag managers (Google, Tealium, Adobe and others), con…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Check which ad pixels and analytics a website runs: Meta Pixel, Google Ads and TikTok tags with their IDs, Google Analytics 4, tag managers (Google, Tealium, Adobe and others), conversion events, cookie consent tools and Google Consent Mode, the site platform (WordPress, Wix, Shopify, Squarespace...) and booking/chat tools. Costs 0.01 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
full_site_reportEvery Landfall check in one call, for less than the tools cost separately: the landing page audit, business contact details, tracking and pixel check, structured data check and cra…Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Every Landfall check in one call, for less than the tools cost separately: the landing page audit, business contact details, tracking and pixel check, structured data check and crawlability check, from a single read of the page. Ideal for agency audits, lead qualification and prospect research. Costs 0.08 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
Only reads 4Show 4 read-only tools
find_leadsFind sales leads: independent local businesses of one type in one place (for example plumbers in Leeds, dentists in Austin, cafes in Lisbon).Reads text others writeNo findings
Why it is in this group
- The name "find_leads" says "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Find sales leads: independent local businesses of one type in one place (for example plumbers in Leeds, dentists in Austin, cafes in Lisbon). For each business: name, address, phone numbers, emails, WhatsApp, social profiles and website, plus what its website is missing (no website at all, social page only, site down, not HTTPS, not mobile-friendly, no ad tracking, no analytics, no way to enquire, phone not tappable, no reviews, slow server). Leads with the most problems come first. Use page to get the next batch. Ideal for agencies, web designers and outreach agents. Costs 0.5 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
get_business_detailsExtract contact and business details from a company website: name, phone numbers (normalised), emails, WhatsApp, postal address, opening hours, social profiles, review platforms, b…Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "get_business_details" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "contact": it reads contacts.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Extract contact and business details from a company website: name, phone numbers (normalised), emails, WhatsApp, postal address, opening hours, social profiles, review platforms, booking and chat tools, UK company and VAT numbers, and page headings. Reads the homepage plus its contact page when the homepage lacks a phone or email. Every value comes from the site itself. Costs 0.02 USDC per completed call, paid automatically via x402 if your client supports it. Never charged if the call fails.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
preview_landing_pageFree quick check of a landing page: ready / fix_first / not_ready verdict, 0-100 score, issue counts and the most important blocker.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "preview_landing_page" says "preview": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Free quick check of a landing page: ready / fix_first / not_ready verdict, 0-100 score, issue counts and the most important blocker. Limited per hour. Use audit_landing_page for the evidence and fixes.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
- idempotentHint: true
sample_auditReturns a complete example audit report for a fictional page, showing every field the paid audit returns.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns a complete example audit report for a fictional page, showing every field the paid audit returns.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
- idempotentHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
56 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write8
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out7
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__landfall__get_business_details"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:07 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 404.
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 5 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-06-18 to none
Tools1 added.+1 addedView diff
- Added:find_leadsOnly reads
Install
Pinned to version 1.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http landfall https://landfall-production-74ad.up.railway.app/v1/mcpclaude mcp add --transport http landfall https://landfall-production-74ad.up.railway.app/v1/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__landfall__find_leads",
"mcp__landfall__sample_audit"
],
"ask": [
"mcp__landfall__audit_landing_page",
"mcp__landfall__get_business_details",
"mcp__landfall__check_tracking",
"mcp__landfall__check_structured_data",
"mcp__landfall__check_crawlability",
"mcp__landfall__full_site_report",
"mcp__landfall__preview_landing_page"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as landfall. Review it before you use it.
Capability tags behind 8 rules
- mcp__landfall__audit_landing_page untrusted-input, outbound
- mcp__landfall__get_business_details private-data, untrusted-input, outbound
- mcp__landfall__check_tracking untrusted-input, outbound
- mcp__landfall__check_structured_data untrusted-input, outbound
- mcp__landfall__check_crawlability untrusted-input, outbound
- mcp__landfall__full_site_report untrusted-input, outbound
- mcp__landfall__find_leads untrusted-input
- mcp__landfall__preview_landing_page untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.landfall-audit/landfall/verify?hash=c9544400a07d9e421c04babd92236f33879397f0d9ebed58050e939a1a2a2752" | jq -e '.changed == false'Pinned hash c9544400a07d, from Nov 4, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.landfall-audit/landfall/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.landfall-audit/landfall)Source: MCP Registry. Synced Nov 4, 2026, 14:17 UTC.
Landfall MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Landfall MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Landfall MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Landfall MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Landfall MCP server have?
- 9 tools: 5 write, 4 read. audit_landing_page, check_tracking, check_structured_data, check_crawlability, full_site_report, get_business_details, find_leads, preview_landing_page and 1 more.
Does the Landfall MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Landfall MCP server send data to outside services?
- 7 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): audit_landing_page, get_business_details, check_tracking, check_structured_data, check_crawlability, full_site_report and 1 more.
Has the Landfall MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 4, 2026. Every change is on this page and in its Atom feed.