CertScore.ai MCP Light
REMOTE · MCP.CERTSCORE.AI · SCANNED SEP 21
Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability62
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1110 tokens (~277/item across 4 items; 4 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage96
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 86% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the CertScore.ai MCP Light server?
CertScore.ai MCP Light is a hosted endpoint at https://mcp.certscore.ai/mcp/light, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.certscore.ai
claude mcp add --transport http ai-certscore-mcp-light 'https://mcp.certscore.ai/mcp/light'
{
"mcpServers": {
"ai-certscore-mcp-light": {
"url": "https://mcp.certscore.ai/mcp/light"
}
}
} {
"servers": {
"ai-certscore-mcp-light": {
"type": "http",
"url": "https://mcp.certscore.ai/mcp/light"
}
}
} [mcp_servers.ai-certscore-mcp-light] url = "https://mcp.certscore.ai/mcp/light"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ai-certscore-mcp-light": {
"type": "remote",
"url": "https://mcp.certscore.ai/mcp/light",
"enabled": true
}
}
} openclaw mcp add ai-certscore-mcp-light --url 'https://mcp.certscore.ai/mcp/light' --transport streamable-http
mcp_servers:
ai-certscore-mcp-light:
url: "https://mcp.certscore.ai/mcp/light" {
"McpServers": {
"ai-certscore-mcp-light": {
"Transport": "http",
"Url": "https://mcp.certscore.ai/mcp/light"
}
}
} assistant mcp add ai-certscore-mcp-light -t streamable-http -u 'https://mcp.certscore.ai/mcp/light'
{
"mcpServers": {
"ai-certscore-mcp-light": {
"type": "http",
"url": "https://mcp.certscore.ai/mcp/light"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 15 Sept 26 0
- Tool “certscore_get_scan_bundle” rewrote its description, which is the text the model reads security
- 13 Sept 26 +12
- Stability: fail → pass ▲ security
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 246 → 271 ▼ functional
- Tool coverage: 100% → 86% ▼ functional
- New tool “certscore_get_report_evidence_page” functional
- 12 Sept 26 0
- Tool “certscore_get_scan_bundle” rewrote its description, which is the text the model reads security
- Server version: 0.2.20 → 0.2.21 functional
- 9 Sept 26 0
- Schema quality: 218 → 241 ▼ functional
- Server version: 0.2.19 → 0.2.20 functional
- “certscore_scan_site” added an optional parameter “taskContext” cosmetic
- 4 Sept 26 0
- Server version: 0.2.17 → 0.2.19 functional
- 3 Sept 26 −1
- Tool “certscore_get_scan_bundle” rewrote its description, which is the text the model reads security
- Server version: 0.2.16 → 0.2.17 functional
- 2 Sept 26 −14
- Stability: pass → fail ▼ security
- 1 Sept 26 +14
- Stability: fail → pass ▲ security
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 Sept 2026 · Probed https://mcp.certscore.ai/mcp/light
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=certscore.ai | CN=YE1,O=Let's Encrypt,C=US | 17 Aug 2026 | 15 Nov 2026 | ECDSA 256 | ECDSA-SHA384 | 5a14f28c09774818a1ceb7a16a518b8702c |
| SANs: *.certscore.ai, certscore.ai | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.certscore.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| certscore.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.certscore.ai/mcp/light | Verified | 200 | |
| http (plaintext) | http://mcp.certscore.ai/mcp/light | HTTPS enforced | 301 | https://mcp.certscore.ai:443/mcp/light |
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 →
certscore_get_report_evidence_page Get report evidence page ~210
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 including 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.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | – |
| scanId | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| coverage | object | yes | – |
| download | object | – | – |
| entries | array | yes | – |
| pagination | object | yes | – |
| reconstruction | string | yes | – |
| reportUrl | string | yes | – |
| scanId | string | yes | – |
| snapshot | string | yes | – |
| type | string | yes | – |
| version | number | yes | – |
No examples provided.
certscore_get_scan_bundle Get scan bundle ~308
Returns the completed or completed-limited CertScore evidence bundle for a stable scanId as concise TextContent and matching structuredContent. Available sections include the canonical report overview, bounded projected findings, pre-consent cookie and tracker evidence, coverage limitations, persisted execution provenance, and retrieval URLs. Detail tiers and byte budgets control the bounded response, with explicit returned, total, truncated, and omitted-section metadata. Accept and Reject results distinguish registered decisions from retained after-click facts. Their execution reports succeeded for a completed click and bounded observation, and succeeded_with_confirmation when the consent decision is also verified. Optional afterAction summaries remain useful when registration is unconfirmed; absent or failed capture remains explicitly limited. Consume canonical findings for any scoring effect. Results are automated public-web observations, not legal advice, certification, or a compliance determination.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | Response detail. Defaults to summary; evidence and full opt into heavier retained context. |
| maxBytes | integer | – | Requested serialized structured response budget in bytes. The full profile defaults to 50000. MCP Light defaults to and applies a transport-safe 25000-byte ceiling; larger Light requests are clamped… |
| maxFindings | integer | – | Maximum compact findings to return. Defaults to 5 for summary and 20 otherwise. |
| maxPreConsentRows | integer | – | Maximum compact pre-consent inventory rows to return. Defaults to 20. |
| scanId | string | yes | Stable CertScore scan ID. |
| Name | Type | Req | Description |
|---|---|---|---|
| completedAt | string|null | yes | – |
| coverage | – | – | – |
| createdAt | string|null | yes | – |
| detail | string | yes | – |
| disclaimer | string|null | yes | – |
| domain | string | yes | – |
| error | – | yes | – |
| evidenceSummary | object | – | – |
| evidenceUrlTemplate | string | – | – |
| findings | array | yes | – |
| findingsMetadata | object | yes | – |
| fullReport | object | – | – |
| gpcResponse | – | – | – |
| interpretationGuidance | object | yes | – |
| links | object | – | – |
| mcpMetadata | object | yes | – |
| noGo | – | – | – |
| observationOnlyDisclaimer | string | yes | – |
| postAcceptObservation | – | – | – |
| postRefusalObservation | – | – | – |
| preConsentCookiesTrackers | object | – | – |
| provenance | object | yes | – |
| recommendedNextAction | string | yes | – |
| recommendedNextTool | – | yes | – |
| reportUrl | string|null | yes | – |
| resultDisposition | – | – | – |
| riskLevel | string|null | yes | – |
| scanFrom | – | yes | – |
| scanId | string | yes | – |
| scanTimeSeconds | number|null | yes | – |
| score | – | yes | – |
| scoreLabel | string | yes | – |
| scoreStatus | string | yes | – |
| scoreUpdatedAt | string|null | yes | – |
| scoreVersion | string|null | yes | – |
| startedAt | string|null | yes | – |
| status | string | yes | – |
| summary | object | – | – |
| timing | object | – | – |
| transportSecurity | – | yes | – |
| type | string | yes | – |
| url | string|null | yes | – |
No examples provided.
certscore_get_scan_status Get scan status ~104
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.
| Name | Type | Req | Description |
|---|---|---|---|
| scanId | string | yes | Stable CertScore scan ID returned by certscore_scan_site. |
| Name | Type | Req | Description |
|---|---|---|---|
| completedAt | string|null | – | – |
| coverage | – | – | – |
| createdAt | string|null | – | – |
| domain | string|null | – | – |
| error | – | yes | – |
| estimatedRemainingSeconds | – | – | – |
| gpcResponse | – | – | – |
| interpretationGuidance | object | yes | – |
| jobId | string | – | – |
| lastHeartbeatAt | string|null | – | – |
| lastUpdatedAt | string | – | – |
| links | object | – | – |
| noGo | object | – | – |
| observationOnlyDisclaimer | string | yes | – |
| phase | string | – | – |
| phaseStartedAt | string|null | – | – |
| postAcceptObservation | – | – | – |
| postRefusalObservation | – | – | – |
| preConsentPreview | object | – | – |
| progressIsEstimate | boolean | – | – |
| progressPercent | integer | – | – |
| provenance | object | yes | – |
| recommendedNextAction | string | yes | – |
| recommendedNextTool | – | yes | – |
| reportUrl | string|null | – | – |
| resultDisposition | string | – | – |
| retryAfterSeconds | – | – | – |
| riskLevel | string|null | – | – |
| scanFrom | – | – | – |
| scanId | string|null | – | – |
| scanTimeSeconds | number|null | – | – |
| scan_id | string|null | – | – |
| score | – | – | – |
| scoreLabel | string | yes | – |
| scoreStatus | string | – | – |
| scoreUpdatedAt | string|null | – | – |
| scoreVersion | string|null | – | – |
| stalled | boolean | – | – |
| startedAt | string|null | – | – |
| status | string | – | – |
| type | string | – | – |
| url | string|null | – | – |
No examples provided.
certscore_scan_site Scan site ~350
Creates a public-website privacy scan or reuses an eligible recent completed scan. Coverage includes pre-consent storage, trackers, consent and CMP signals, privacy-policy disclosures, transport security, and GDPR/ePrivacy or CCPA/CPRA review signals. The response contains a stable scanId, lifecycle status, retry timing, and sometimes a bounded preliminary preConsentPreview; preliminary data contains no final findings or score. Results are automated public-web observations, not legal advice, certification, or a compliance determination. Tool and workflow documentation: https://certscore.ai/developers/mcp.
| Name | Type | Req | Description |
|---|---|---|---|
| freshness | string | – | Scan freshness policy. latest allows eligible recent completed-result reuse when available; refresh requests a new scan. Defaults to latest. |
| maxWaitSeconds | integer | – | Deprecated compatibility field; accepted but ignored. The bounded preliminary-preview wait is controlled by CertScore and never waits for scan completion. |
| scanFrom | string | – | Optional execution region for a newly queued scan: eu_de, eu_ie, california, or the service default when omitted. |
| taskContext | object | – | Optional caller-declared purpose and integration ID/version for usage research. Only include questionSummary when the user knowingly agrees to share a brief non-sensitive question for product improve… |
| url | string | yes | Public URL or domain to scan. |
| waitForCompletion | boolean | – | Deprecated compatibility field; accepted but ignored. certscore_scan_site never waits for a new scan to finish, though MCP Light may briefly wait within a bounded preview window for preliminary pre-c… |
| Name | Type | Req | Description |
|---|---|---|---|
| completedAt | string|null | – | – |
| coverage | – | – | – |
| createdAt | string|null | – | – |
| demoSubstitution | object | – | – |
| domain | string|null | – | – |
| error | – | yes | – |
| gpcResponse | – | – | – |
| interpretationGuidance | object | yes | – |
| jobId | string | – | – |
| links | object | – | – |
| noGo | object | – | – |
| observationOnlyDisclaimer | string | yes | – |
| postAcceptObservation | – | – | – |
| postRefusalObservation | – | – | – |
| preConsentPreview | object | – | – |
| provenance | object | yes | – |
| recommendedNextAction | string | yes | – |
| recommendedNextTool | – | yes | – |
| reportUrl | string|null | – | – |
| resultDisposition | string | – | – |
| riskLevel | string|null | – | – |
| scanFrom | string | – | – |
| scanId | string|null | – | – |
| scanTimeSeconds | number|null | – | – |
| score | – | – | – |
| scoreLabel | string | yes | – |
| scoreStatus | string | – | – |
| scoreUpdatedAt | string|null | – | – |
| scoreVersion | string|null | – | – |
| startedAt | string|null | – | – |
| status | – | yes | – |
| type | string | yes | – |
No examples provided.
What is the CertScore.ai MCP Light server?
CertScore.ai MCP Light is listed in the public MCP registry as ai.certscore/mcp-light. Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS. This page covers its hosted endpoint (https://mcp.certscore.ai/mcp/light).
Is the CertScore.ai MCP Light server safe to use?
CertScore.ai MCP Light scores 82 out of 100 on VerifyMCP. 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 CertScore.ai MCP Light server expose?
CertScore.ai MCP Light exposes 4 tools: certscore_scan_site, certscore_get_scan_status, certscore_get_report_evidence_page, certscore_get_scan_bundle. Their descriptions and schemas cost roughly 972 tokens of context every time the server is loaded.
Does the CertScore.ai MCP Light server require authentication?
No. We connected to CertScore.ai MCP Light without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the CertScore.ai MCP Light server still maintained?
CertScore.ai MCP Light is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.