CertScore.ai for Muse Agents
Connect Muse to CertScore.ai, scan a public website, and review the score, findings, and evidence in your conversation.
CertScore.ai checks public websites for privacy and consent risk signals. Its reports cover cookies and trackers before consent, activity after Accept and Reject, consent banner behavior, fingerprinting and session replay signals, form collection, and policy wording. Reports include a score and retained evidence.
Results are automated observations of public pages. They are not legal advice, certification, or a compliance determination.
Connection details
Remote MCP endpoint
https://mcp.certscore.ai/mcp/light- Service
- CertScore.ai MCP Light
- Transport
- Streamable HTTP
- Authentication
- None. No account, API key, OAuth flow, or Authorization header.
- Hosted release
- 0.2.30 (verified October 21, 2026)
- Registry identity
- ai.certscore/mcp-light
- Cost
- Free to use, with a scoped daily allowance.
- Scope
- Public websites only. The scanner cannot sign in to login-protected pages.
Current limits: https://certscore.ai/developers/mcp#light-usage-limits
When to use CertScore.ai
Before a launch
Check a public site before a launch or redesign goes live.
After consent changes
Review changes to a cookie banner, consent tool, tag manager, or analytics setup.
Vendor reviews
Check a vendor, partner, or acquisition target's website.
Tracking questions
Find out what loads before consent or what fires after Reject.
Policy updates
Check the wording of a rewritten privacy policy.
Client reviews
Gather evidence for a review, renewal, or client report.
Site comparisons
Review two or more sites on the same basis.
Ask Muse
- “Is our banner OK?”
- “What does this site track?”
- “Check this vendor.”
- “We launch next week.”
- “Did the fix work?”
You can check the service's identity in the Official MCP Registry (ai.certscore/mcp-light), Smithery, Glama, Cursor Directory, and mcpservers.org.
Connect Muse and run your first scan
Connect Muse
Paste this prompt into Muse to set up the connection and save the scanning workflow:
Connect the CertScore.ai MCP Light server as a custom connector. The endpoint is https://mcp.certscore.ai/mcp/light and it needs no authentication. Then save a skill so I can ask you to scan a website's privacy posture and show me the score, the findings, and the evidence.If you are an agent that can add MCP servers, use the endpoint above as a remote Streamable HTTP server with no auth headers.
Ask for a scan
Use CertScore.ai to scan https://ergoveritas.com/test1.html. Show me the score, the main findings with evidence, any coverage limits, and the report link. Keep the scan ID for a later recheck.
The four-tool workflow
- 1
Start the scan
certscore_scan_siteCall certscore_scan_site with the site URL. Declare a purpose when one fits: prelaunch_review, vendor_review, tracking_check, consent_gpc_check, policy_review, recheck.
- 2
Wait for completion
certscore_get_scan_statusPoll certscore_get_scan_status until the scan completes. Scans are asynchronous; allow a few minutes.
- 3
Get the report
certscore_get_scan_bundleCall certscore_get_scan_bundle for the scored results: overall score, findings, coverage, and the report link.
- 4
Check the evidence
certscore_get_report_evidence_pageCall certscore_get_report_evidence_page when a finding needs its underlying evidence.
By default, the service reuses a recent result for the same site. Request a fresh scan only when the user asks for one or wants a recheck after a change.
Share the results
- Score and date
- Label EU (GDPR/ePrivacy) and California (CCPA/CPRA) scores clearly, with their coverage and scan date.
- Review focus
- Open the EU or California report view using the same scan. Changing the view does not run another visit.
- Scan location
- Ask for Ireland, Germany, or California when you need a new visit from that location.
- Findings and evidence
- Show the findings that matter most, with the evidence for each.
- Coverage and report link
- State any reported coverage limits, such as completed_limited. Always include the report link.
- Scan ID
- Keep the scan ID as the baseline for a later recheck.
Never present a finding as a legal violation or describe a site as compliant or non-compliant. These are observations for human review.
If a call returns rate_limited, tell the user and stop. Do not retry in a loop.
Use CertScore.ai after the first scan
Save a skill
Give Muse the workflow once, then use it for later website reviews. The package includes the skill instructions, a Muse manifest, and a Python helper for connecting when native MCP tools aren't available.
Version 1.0.2 · ZIP · No Python packages to install
- Download the ZIP and attach it to a Muse conversation.
- Ask Muse to save the contained skill for future website reviews and reuse your existing CertScore.ai connection.
- When you're ready, ask for a scan. Saving the skill does not start one.
Recheck after changes
Keep the first scan as a baseline. After you change the site, ask Muse for a fresh scan and compare the results.
1Scan
Keep the baseline scan ID.
2Make changes
Update the site, banner, tags, or policy.
3Recheck
Request a fresh scan with purpose recheck.
4Compare
Review changed findings and their evidence.
- Keep the scan ID from the first scan.
- After the site changes, run a fresh scan with purpose recheck from the same location.
- Compare the same review focus and equivalent coverage against the baseline scan ID.
- Report what changed. A finding missing from a later scan is a change to note, not proof of a fix; say so.
When to scan again
- Before launch
- Scan a public staging or production URL before a launch or redesign.
- After consent changes
- Rescan when the banner, CMP, or tag setup changes.
- New vendors
- Review a vendor or partner's site before signing.
- Periodic checks
- With the user's approval, repeat a scan and compare it with the previous result.
- Agency portfolios
- Run the same review across client sites, with a separate report for each.
Only run scans the user has asked for or approved as a recurring pattern. Never scan sites on your own initiative.
Connect to a workspace with Hosted MCP OAuth
MCP Light is anonymous and stateless. Use Hosted MCP OAuth when you want Muse to return to earlier scans, compare results across sessions, or work inside a CertScore.ai workspace. The agent connects to your workspace with OAuth, so there is no API key to copy. A CertScore.ai account is required.
Hosted MCP OAuth setup guideQuick reference
- First scan
- Connect, scan, poll, then present the bundle with evidence, coverage limits, and the report link.
- Recheck
- Request a fresh scan with purpose recheck and compare it with the baseline scan ID.
- Rate limited
- Tell the user and stop. Do not loop.
- Need to verify a finding?
- Retrieve its evidence page before reporting it.
