mcpbeat Sign in

CertScore.ai MCP Light MCP Server

answering

CertScore.ai MCP Light is answering right now. Last checked 8 min ago. It exposes 4 tools. Last commit 7 Nov 2026.

Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS.

Uptime history 91 days of history · worst day 93%
91 days agonow
100.0%
Uptime 24h
91 of 91 checks
4
Tools
read from the server
586 ms
Response time
average over 24h
0
Stars
last commit 7 Nov 2026

What changed 73

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 14 August 2026. No other catalogue keeps this.

7 Nov a tool changed version
3 Nov a tool changed version
2 Nov a tool changed version
30 Oct a tool description was rewritten certscore_get_report_evidence_page
30 Oct a tool changed the parameters it asks for certscore_get_report_evidence_page
17 Oct a tool changed version
15 Oct a tool changed version
14 Oct a tool description was rewritten2 times that day certscore_get_report_evidence_page
14 Oct a tool changed version2 times that day
14 Oct a tool changed the parameters it asks for certscore_get_report_evidence_page
and 63 more, back to 14 August 2026

What the code does

We read the source, 2 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        "https://ad.doubleclick.net/activity;src=4448269;type=bbycom;cat=BBY-S0;rcb=2;ord=4654468581826;npa=0;auiddc=1743222283.1777067241;u3=not_provided;u5=null;u6=anonymous;u7=en-US;u14=undefined;u15=undefined;u16=not_provided;u18=not_provided;u19=not_provided;u20=not_provided…
Builds a database query by concatenation apps/web/components/marketing/homepage-findings-overview.tsx:15
  const select = (index: number) => {
    setActive((index + HOMEPAGE_SHOWCASE.length) % HOMEPAGE_SHOWCASE.length);
 subprocess.run(['python3',str(p/'analyze_session_replay.py')],check=True,stdout=subprocess.DEVNULL)
COPY .npmrc package.json pnpm-lock.yaml pnpm-workspace.yaml turbo.json tsconfig.base.json ./

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

run in your terminal
claude mcp add mcp-light --transport http https://mcp.certscore.ai/mcp/light
Settings → Connectors → Add custom connector, then paste this address
https://mcp.certscore.ai/mcp/light
~/.codex/config.toml
[mcp_servers.mcp-light]
url = "https://mcp.certscore.ai/mcp/light"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp-light": {
      "url": "https://mcp.certscore.ai/mcp/light"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mcp-light": {
      "type": "http",
      "url": "https://mcp.certscore.ai/mcp/light"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

certscore
certscore_get_report_evidence_page
For a focused question, use section=cmp, cms, consent, gpc, policy, tracking, transport, forms or accessibility. This returns selected retained report sections plus shared scan, score, findings and coverage context. CMP includes all 13 criteria with their assessment results and retained comparisons; CMS includes platform/version evidence and existing advisories. Policy also includes retained privacy-choice controls, unverified link candidates and notice passages; California-focused reports include their shared privacy section. detailedEvidence carries shared display wording, counts and cross-links; these audit rows are not additional findings. Use reviewFocus=gdpr_eprivacy or ccpa_cpra to match the corresponding web/PDF/Word view; omit it to retain the scan default. Preserve reviewFocus and section on cursor continuation; unselected or not-returned fields are not evidence of absence. Use workpaper=tracking separately for the starting-page tracking inventory, privacy choices/notices and GPC evidence, with JSON and CSV downloads. Never combine section and workpaper. The workpaper selector also applies to every continuation request. Otherwise retrieve scan report display content as paginated JSON, without internal diagnostic JSON downloads. The response also offers a single-file full JSON download; private JSON download links expire after five minutes and need no OAuth header; use pagination if your host blocks file downloads. Repeated display records use reportContentRef JSON Pointers. Includes evidence tables, full-site page and resource inventories, all retained additional-page form fields, form snapshot download references, and retained limitations. Snapshot images are downloaded separately from the returned URLs, with OAuth bearer authentication for workspace scans. Available on OAuth and Light. Start with scanId; follow pagination.nextCursor until complete. Pages share a snapshot; restart if it changes. Each entry has a JSON Pointer path and value; oversized strings use numbered parts. Export completion is not complete observation coverage. Use the concise scan bundle for summaries; use this tool for exhaustive report evidence. No new scan is created.
certscore_get_scan_bundle
Main answer for a completed or completed-limited scan: canonical findings, next steps, supporting evidence, score, date/region, coverage and report URL. An existing scanId is enough; no new scan is created. The evidence index describes response delivery, never evidence absence. Optional next actions lead to deeper report tables, tracking workpapers and JSON/CSV exports. Use detail=evidence for request examples and policy candidates, including scans with no findings; detail=full adds bounded retained context. Preserve returned/total counts and omission metadata. Accept/Reject execution succeeded means a completed click and bounded observation; succeeded_with_confirmation additionally verifies the consent decision. Retained after-click facts remain distinct from registered decisions. Absent or failed capture remains explicitly limited. Use canonical findings for scoring effects. A later missing finding does not prove a fix. Results are automated public-web observations, not legal advice, certification, or a compliance determination.
certscore_get_scan_status
Returns lifecycle status for a stable CertScore scanId. Active responses include phase, heartbeat, estimated progress, retryAfterSeconds, and sometimes a bounded preliminary preConsentPreview. Terminal responses include completion status, CertScore score and risk metadata when available, coverage, persisted execution region and timestamps, report URL, and a next-action field. Preliminary observations are distinct from completed findings.
certscore_scan_site
Use for a user-requested website launch review, vendor assessment, cookie/tracker inventory, consent/GPC investigation or privacy-policy review. A public URL or domain is enough. Creates a privacy scan or reuses an eligible recent completed scan; default freshness=latest saves new-scan quota. Use refresh only for an explicitly requested fresh scan or post-fix recheck. Retain scanId, poll certscore_get_scan_status only while active at retryAfterSeconds, then read certscore_get_scan_bundle. A preliminary preConsentPreview is not final findings or totals. Coverage includes pre-consent storage, trackers, consent and CMP signals, privacy-policy disclosures, transport security and GDPR/ePrivacy or CCPA/CPRA review signals. Results are automated observations, not legal advice, certification, or a compliance determination. https://certscore.ai/developers/mcp.

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

get_scan_bundle
removed 14 Aug 2026
get_scan_status
removed 14 Aug 2026
scan_site
removed 14 Aug 2026

Endpoints

URLTransportStateLatencyChecked
https://mcp.certscore.ai/mcp/light streamable-http answering 293 ms 8 min ago

Alternatives to CertScore.ai MCP Light

same job, measured the same way
Privacy
by thegridwork

Audit websites for GDPR, CCPA, and ePrivacy compliance — trackers, consent, and policies.

56 installs/wk local only
Katla
by katla

GDPR/CCPA cookie consent: scan sites for cookies, track consent rates, generate privacy policies.

answering
PageGuard MCP
by pageguard

Privacy compliance scanning for AI coding tools. Detects tracking tech, cookies, and data gaps.

48 installs/wk local only
PrivacyPill
by lovable-privacy-pill-consent-studio

GDPR cookie banners with Consent Mode v2, plus a free scan of what loads before consent.

9 tools answering
ConsentLayer
by consentlayer

Cookie consent for GDPR/CCPA: scan sites for trackers, configure consent banners, get install code.

answering
CookieInspector
by cookieinspector

Check what a site's cookie banner really blocks: CMP, trackers, cookies before consent.

9 tools answering
CertScore.ai
by certscore

MCP server for CertScore.ai public website risk-signal workflows.

543 installs/wk answering
ConsentStack
by consentstack

Set up GDPR and CCPA cookie consent: create a site, publish a banner, scan and categorize trackers.

answering

CertScore.ai MCP Light — questions

Answers built from our own checks of this server.

What can CertScore.ai MCP Light do?
It exposes 4 tools, read directly from the server on our last check. Among them: certscore_get_report_evidence_page, certscore_get_scan_bundle, certscore_get_scan_status, certscore_scan_site. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is CertScore.ai MCP Light working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 586 ms. The bar chart above shows every period we have measured.
Did CertScore.ai MCP Light ever remove tools?
Yes. get_scan_bundle, get_scan_status, scan_site are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
How do I connect CertScore.ai MCP Light?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does CertScore.ai MCP Light need an API key?
No. CertScore.ai MCP Light completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is CertScore.ai MCP Light?
It answers our handshake in 586 ms on average, which is faster than 18% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is CertScore.ai MCP Light open source?
We cannot say either way: written in TypeScript, 0 stars on GitHub and 2 open issues, but we could not determine the licence, and without one the code is not open source by default.