Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Certificate changed, valid to 2027-01-04
Changed the definition of "claim_mcp_server", "deep_scan_app" and "my_server_report"
⟨117 unchanged words⟩ is in place, call again to confirm. The first verification returns an owner secret, shown once: keep it, because later changes to an already verified server (note, alerts) need it as owner_secret. If it is lost, call with recover true, put the one-time code on the host, then call with recover_check. Verifying does not change how the server is ⟨5 unchanged words⟩
⟨94 unchanged words⟩ "maxLength":280,"type":"string"},"owner_secret":{"description":"The owner secret returned once at the first verification. Needed to change an already verified server.","maxLength":80,"type":"string"},"recover":{"description":"Lost the owner secret: true returns a one-time code to put on the host, and a check value","type":"boolean"},"recover_check":{"description":"The check value from the recover step, once its code is on the host","maxLength":700,"type":"string"},"server":{"description":"The MCP server address ⟨17 unchanged words⟩
⟨148 unchanged words⟩ value. Because it probes an app directly,iteach scan runs only after ownership is proven now: call it once to receiveanainertone-timeverificationcodetokenand a check id, addthatthetokencode to the app (a meta tag on the home page, or a/7it-verify.txtlinefilein /7it-verify.txt), then call again with the check id and the scan runs.
⟨26 unchanged words⟩ key returned to the verified owner by claim_mcp_server (the newest one; each verification issues a new key)","maxLength":64,"type":"string"} ⟨28 unchanged words⟩
Changed the definition of "find_tool"
⟨102 unchanged words⟩ change","any"],"type":"string"},"payment":{"description":"Payment terms: any (default); free_only = only servers that declare no payment; paid_ok = servers that charge are fine, servers whose payment terms are unknown are left out. Paid servers show their declared price per call.","enum":["any","free_only","paid_ok"],"type":"string"}},"required":["job"],"type":"object"}
Changed the definition of "deep_scan_app"
⟨14 unchanged words⟩ an app they control for exposed files andopenleakeddatabasessecret keys before launch. A deeper security scan than check_app_security, ⟨34 unchanged words⟩ , or a published source map. It alsofindsreads theSupabaseapp'sorownFirebasepublicbackendcode (theapp
Changed the definition of "my_7maps_usage"
⟨36 unchanged words⟩ an estimate of the tokens saved compared withconnecting tofindingserverstheandsameloadingthingtheirouttoolwithoutlists7Maps, failures avoided (servers not answering that were ⟨56 unchanged words⟩
Added "find_tool", "my_7maps_usage" and "my_server_report"; changed the definition of "claim_mcp_server", "report_road" and "submit_mcp_server" (18 tools before, 21 now)
⟨7 unchanged words⟩ : where to send down and up alerts.AAn ntfy topic for phone push without email (https://ntfy.sh/<hard-to-guess topic, at least 10 characters>, a self-hosted https://ntfy.<domain>/<topic>, or ntfy:https://<host>/<topic>), a Slack incoming webhook (https://hooks.slack.com/services/...), a ⟨77 unchanged words⟩
⟨43 unchanged words⟩ not ask for. Fixed fields only, nofreeopen text. Reports from many agents become the server's rating and
Changed the definition of "claim_mcp_server" and "deep_scan_app"
⟨45 unchanged words⟩ get a live status badge for their README. Verified owners' servers are checked every 5 minutes (uptime on the page and badge), and with alert_url the owner gets a message when the server stops answering and when it is back. First call returnsa linetheofprooftextoptionsto(aputline in /.well-known/7maps-verify.txt on the server'shost;host,afterathe
Added "claim_mcp_server", "report_road" and "submit_mcp_server" (15 tools before, 18 now)
Verify ownership of an MCP server on 7Maps — Use this when the person you work for owns or runs an MCP server that is on the 7Maps map and wants its page to show it is owner verified, add a short note for agents (rate limits, sign-up, what the tools are for), or get a live status badge for their README. First call returns a line of text to put in /.well-known/7maps-verify.txt on the server's host; after the file is there, call again to confirm. Verifying does not change how the server is measured or ranked. No charge.
Report how a call to an MCP server went (7Maps) — Use this after calling a tool on an MCP server (especially one 7Maps pointed you to) to report how it went: whether it worked, why not, how long it took, whether the result matched the description, and anything it did that you did not ask for. Fixed fields only, no free text. Reports from many agents become the server's rating and live incident alerts that every agent sees, like traffic reports on a map. You can also pass the same fields as last_trip on any paid 7Maps call. No charge.
Put a new MCP server on the 7Maps map — Use this when someone has built or runs an MCP server that is not in the official MCP registry (for example a small business's own server) and wants AI agents to be able to find it, or asks how to get their server listed. Give the server address, or just the business's domain and the usual endpoint paths are tried. The server is observed every 6 hours for 7 days; if it answers at least 90% of the time, keeps its tools stable and describes every tool, it joins the 7Maps map that agents use to choose servers. Placement cannot be bought. Returns the status page and an optional owner-verification…
Certificate recorded, valid to 2026-11-02
Authorization not required
Added "check_accessibility", "check_ai_shopper_readiness", "check_email_authentication" and 1 more (11 tools before, 15 now)
Check a website’s accessibility — Use this when someone asks whether a website or online store is accessible, meets WCAG, or could face an ADA accessibility complaint. Runs Google Lighthouse's automated accessibility checks (axe-core rules) on the page as a phone sees it, and returns the score, each failing rule in plain English with its WCAG criterion and how many elements fail, and how the site compares with 7IT's study of US online stores. Automated checks cover only part of WCAG; this is a starting point, not a legal opinion. Takes 20 to 60 seconds.
Check if a store is ready for AI shopping agents — Use this when someone asks whether ChatGPT, Claude, Perplexity or other AI shopping agents can find, read and recommend their online store's products. Checks what robots.txt tells AI search crawlers versus training-only crawlers, llms.txt, agents.md, the UCP commerce discovery file, and one product page's structured data (price, currency, stock, brand, GTIN or SKU, reviews, shipping and returns). Returns the gaps with fixes, compared with 7IT's study of US online stores. Uses an identified crawler that respects robots.txt.
Check email authentication (SPF, DKIM, DMARC) — Use this when someone asks why their emails land in spam, whether their domain is protected from spoofing or phishing in their name, or whether they meet the Gmail, Yahoo and Outlook rules for bulk senders. Reads the domain's public DNS records (SPF, DKIM under the common email services' selectors, the DMARC policy, BIMI, MX) and returns what is missing with the exact fix, compared with 7IT's study of US online stores. Sends no email and needs no access.
Added "check_app_security", "deep_scan_app" and "report_problem"; changed the definition of "ask_7it", "describe_studio", "estimate_automation_roi" and 5 more (8 tools before, 11 now)
Use this when the user has a specific question for 7IT that describe_studio does not answer. Ask 7IT Solutions, a solo senior software studio ⟨48 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"answer":{"description":"Answer from the published profile, or null when it was forwarded without one","type":["string","null"]},"contact":{"type":"string"},"forwarded_to_founder":{"type":"boolean"}},"required":["answer","forwarded_to_founder","contact"],"type":"object"}Unknown → Live
First tool surface recorded: 8 tools (server version 1.1.0)
https://7it.co.il/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 15 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"check":{"description":"The check id the first call returned, after the one-time code is on the app","maxLength":500,"type":"string"},"url":{"description":"The app’s public web ⟨7 unchanged words⟩ You must be able to add a verificationtokencode to this app.","maxLength":300,"minLength ⟨7 unchanged words⟩
⟨27 unchanged words⟩ properties":{},"type":"object"},"check":{"description":"The check id to pass on the next call, once the code is on the app","type":"string"},"clean":{"description":"True when no exposed file was found","type":"boolean"},"code":{"description":"One-time verification code to place on the app (30 minutes)","type":"string"},"findings":{"description":"Exposed paths, plus ⟨67 unchanged words⟩ when ownership is not proven yet; add thetokencode and call again with the check id","type":"boolean"},"report_url":{"type":"string"},"token":{"description":"InertTheverificationsite's ownership tokento(forplacetheon7ITtheGuardappwatch; it no longer unlocks a scan by itself)","type":"string"},"verified":{ ⟨4 unchanged words⟩
⟨5 unchanged words⟩ backend":{"additionalProperties":{},"description":"What wasThefoundSupabasebehindproject theapp:publicsupabase/firebasecodepresencenames, and how manytablessecretankeysanonymousitvisitorcarriescould(thereaddatabase is never contacted)","properties":{},"type":"object" ⟨11 unchanged words⟩ findings":{"description":"Exposed paths, plusopensecretbackendkeystables/bucketsinwiththeapublicrowcodecount;by kind; file contents and key values are neverread orreturned","items":{"additionalProperties":{}, ⟨83 unchanged words⟩
⟨65 unchanged words⟩ 6 hours for 7 days; if it answersat least 90% of the timereliably, keeps its tools stable and describes every ⟨27 unchanged words⟩
Find an MCP tool for a job (7Maps) — Use this when you need a tool for a job and do not know which MCP server has one: searches every tool of every public MCP server on the 7Maps map (over 200,000 tools, probed daily) and returns the best matches with an automated estimate of what each tool can do (read-only, changes data, high risk), whether its server is answering now, its handshake time, the tokens its tool list costs to load, and a page to check it. Filter to read-only tools, servers answering now, a latency or token ceiling. Copies of the same tool on several servers are collapsed. No charge. To have 7Maps pick one server a…
My 7Maps usage (personal key) — Use this when the person you work for asks what 7Maps has done for them: calls made with their personal 7Maps key today, in the last 7 days and in the last 30 days, servers checked, an estimate of the tokens saved compared with connecting to servers and loading their tool lists, failures avoided (servers not answering that were skipped, risk changes caught by watch or verify_lock, calls that would have failed) and the average response time. It reads the optional personal key sent with this connection (the X-7Maps-Key header); without one it says so in one line, since every 7Maps answer alread…
What agents looked for around your MCP server (7Maps) — Use this when the person you work for owns an MCP server on the 7Maps map and wants to know how AI agents look for servers like it: how often agents asked 7Maps for servers in its category in the last 7 or 30 days, how often this server was shown and picked, and, for a verified owner with owner_key, the words agents used, the servers picked instead, failure reasons agents reported, uptime, tool changes, and its token cost and handshake time against similar servers. Counts only, no agent identities. Without owner_key it returns the public numbers and how to verify ownership with claim_mcp_serv…
{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"alert_url":{"description":"Optional: where to send down and up alerts. A Slack incoming webhook (https://hooks.slack.com/services/...), a Discord webhook (https://discord.com/api/webhooks/...), or any https webhook that receives JSON. Stored encrypted, saved only once ownership is proven; a test message is sent on save. An empty string turns alerts off.","maxLength":600,"type":"string"},"note":{"description":"Optional plain-text note from ⟨35 unchanged words⟩
⟨13 unchanged words⟩ check an app they control for exposed files and open databases before launch. A deeper security scan than check_app_security, ⟨33 unchanged words⟩ listing, or a published source map. It also finds the Supabase or Firebase backend the app uses and checks what an anonymous visitor can read: tables, files, and whether anyone can sign up. It reads only, never writes, and never stores, logs or returns any key; it reports the exposed PATH, table or bucket name and a row count so the owner can seeit;it, neverreads or returnsa file's contents oranya secret value. Because it probes an app directly ⟨33 unchanged words⟩ ), then call again and the scan runs.Reports paths only.
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"backend":{"additionalProperties":{},"description":"What was found behind the app: supabase/firebase presence and how many tables an anonymous visitor could read","properties":{},"type":"object"},"clean":{"description":"True when no exposed ⟨5 unchanged words⟩ "},"findings":{"description":"Exposed paths,only;plus open backend tables/buckets with a row count; file contents and key values are never read or returned","items":{"additionalProperties":{},"properties":{"detail":{"type":"string"},"fix":{"type":"string"},"id":{"type":"string"},"kind":{"type":"string"},"label":{"type":"string"},"path":{"type":"string"},"rows":{"type":"number"},"severity":{"enum":["critical" ⟨58 unchanged words⟩
Map what an AI agent may do on its own — Use this when someone asks which actions their AI agent or its connected tools may take on their own, which need a person's approval, and which a person must do; or how to set up human oversight, permissions or AI governance for an agent (for example under the EU AI Act). Give either the address of a public MCP server, or the list of tools the agent has (name, description and annotations). Sorts every tool into green (runs alone: reads and prepares), yellow (a person approves: sending, updating, scheduling) or red (a person does it: money, permissions, deletion, code execution, commitments), …
Use this when the user asks who 7IT Solutions is, what it builds, or whether it fits their project, or is looking for a developer to review or take over an app built with an AI tool. Returns a factual profile of 7IT Solutions, a ⟨92 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"contact":{"description":"Where to reach Lior","type":"string"},"model":{"description":"How engagements work","type":"string"},"name":{"type":"string"},"ownership":{"description":"What the client owns","type":"string"},"services":{"description":"Each service with when it fits and when it does not","items":{"additionalProperties":{},"properties":{"name":{"type":"string"},"url":{"type":"string"}},"required":["name","url"],"type":"object"},"type":"array"}},"required":["name","services","contact"],"type":"object"}Use this when someone wants to know what a repetitive task costs their team, or whether automating it is worth the money. Calculates how many hours a month a team ⟨66 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"automatable_hours_per_month":{"type":"number"},"automatable_yearly":{"description":"Yearly cost automation could take over, USD","type":"number"},"break_even_budget_12_months":{"type":"number"},"break_even_budget_6_months":{"type":"number"},"hourly_cost":{"description":"Hourly cost used, in USD","type":"number"},"hours_per_month":{"type":"number"},"report_url":{"type":"string"},"tasks":{"description":"Per-task hours and cost","items":{"additionalProperties":{},"properties":{"name":{"type":"string"}},"type":"object"},"type":"array"},"yearly_cost":{"description":"Yearly cost of the work done by hand, USD","type":"number"}},"required":["hourly_cost","hours_per_month","yearly_cost","automatable_hours_per_month","automatable_yearly","break_even_budget_12_months","break_even_budget_6_months","tasks","report_url"],"type":"object"}Use this after list_field_kits, to read one checklist in full. Returns one 7IT Field Kit in full: every ⟨30 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"slug":{"type":"string"},"title":{"type":"string"},"url":{"type":"string"}},"required":["slug","title","url"],"type":"object"}Use this when someone asks how fast US online stores are right now, or wants a current benchmark to compare a store against. Returns 7IT's weekly US Store Speed Index: median ⟨41 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"panel":{"description":"Number of stores in the fixed panel","type":"number"},"series":{"description":"One entry per week, oldest first","items":{"additionalProperties":{},"properties":{"date":{"type":"string"},"median_apps":{"description":"Median third-party apps and tags per store","type":["number","null"]},"median_lcp_s":{"description":"Median seconds until the main content shows","type":["number","null"]},"median_score":{"description":"Median Google phone performance score, 0 to 100","type":["number","null"]},"score_50_plus":{"description":"Percent of stores scoring 50 or more","type":["number","null"]},"stores":{"description":"Stores measured that week","type":"number"}},"required":["date","stores","median_score","median_lcp_s","score_50_plus","median_apps"],"type":"object"},"type":"array"},"source_url":{"description":"Page to cite","type":"string"},"title":{"type":"string"},"updated":{"description":"Date of the latest weekly reading, YYYY-MM-DD","type":["string","null"]}},"required":["title","panel","updated","series","source_url"],"type":"object"}Use this when someone wants a working checklist for a technical job (webhooks, store speed, integrations, migrations, AI in production, security). Lists 7IT Field Kits: working checklists for custom ⟨44 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"kits":{"description":"Matching kits; pass a slug to get_field_kit","items":{"additionalProperties":{},"properties":{"checks":{"type":"number"},"purpose":{"type":"string"},"slug":{"type":"string"},"title":{"type":"string"},"url":{"type":"string"}},"required":["slug","title","purpose","checks","url"],"type":"object"},"type":"array"}},"required":["kits"],"type":"object"}Use this when the user is weighing a software, eCommerce, automation or AI decision and a cited article would help. Searches 7IT Solutions’ guides and articles on custom software, eCommerce (Shopify, WooCommerce, headless), automation and integrations (connecting CRMs, accounting tools such as QuickBooks, ERPs and online stores), payments, AI in production, security and ⟨14 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"results":{"description":"Best matches, most relevant first","items":{"additionalProperties":{},"properties":{"excerpt":{"type":"string"},"title":{"type":"string"},"url":{"type":"string"}},"required":["title","url"],"type":"object"},"type":"array"}},"required":["results"],"type":"object"}Use this when someone asks how fast a website or online store loads on a phone, why it is slow, or how it compares with a competitor. Runs Google PageSpeed Insights (mobile lab test) ⟨84 unchanged words⟩
before
—after
{"$schema":"https://json-schema.org/draft/2020-12/schema","additionalProperties":{},"properties":{"benchmark":{"description":"Where the score stands against the US Store Speed study"},"competitors":{"description":"Competitors tested side by side, if any","items":{"additionalProperties":{},"properties":{"host":{"type":"string"}},"required":["host"],"type":"object"},"type":"array"},"report_url":{"description":"Shareable full report","type":"string"},"store":{"additionalProperties":{},"description":"The tested store","properties":{"host":{"type":"string"},"score":{"description":"Google phone performance score, 0 to 100","type":["number","null"]}},"required":["host"],"type":"object"}},"required":["store","competitors","report_url"],"type":"object"}Check a web app’s security hygiene — Use this when someone asks whether a website or web app is secure, safe to launch, or missing security headers. Not a penetration test, and it cannot see pages behind a login. Checks a public web app for the baseline browser protections every production app should send (Content Security Policy, HTTPS enforcement, clickjacking protection, MIME-sniffing, referrer and permissions policy, cross-origin isolation) and whether a JavaScript source map is served publicly. Reads only the public response headers any visitor's browser receives; never logs in, submits a form, calls the app's APIs, or read…
Deep security scan of an app you control — Use this when the user, or the agent building the app, wants to check an app they control for exposed files before launch. A deeper security scan than check_app_security, for an app the caller controls (for example one the agent itself is building). It looks for sensitive things left publicly reachable: an environment (.env) file, an exposed .git folder, a directory listing, or a published source map. It reports the exposed PATH so the owner can see it; it never reads or returns a file's contents or any secret value. Because it probes an app directly, it runs only after ownership is proven: c…
Report a wrong or broken 7IT result — Use this when a 7IT tool returned something that looks wrong, failed unexpectedly, or did not match what the user asked for, so 7IT can fix it. Sends a short report to 7IT: which tool, what went wrong, and optionally the site address involved. Do not include personal details or the conversation. Nothing changes for the user; it is only feedback.