Scan public websites for privacy, cookie, tracker, consent, policy, and disclosure risk signals. Start instantly with zero-auth Light mode—no account or API key required.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.7/5 across 3 of 3 tools scored.
Each tool has a distinct role in the scan lifecycle: initiating, polling status, and retrieving results. No overlapping purposes; the workflow is clear.
All tools follow the same 'certscore_' prefix with verb_noun structure (scan_site, get_scan_status, get_scan_bundle). Consistent and predictable.
Three tools precisely cover the essential operations for a scanning service. The count is well-scoped without unnecessary additions.
The tool set covers the full scan lifecycle from initiation to result retrieval, including proper polling and final data access. No critical gaps for the intended functionality.
certscore_get_scan_bundleGet scan bundleACall after completed or completed_limited status. Every usable completed bundle returns a self-contained concise TextContent digest plus matching structuredContent, including canonical execution region (scanFrom) and timestamps when available. For a reused or retrieved existing scan, use only persisted scanFrom and timestamps; never infer its original region from the current request, the user's location, or a default, and report unavailable provenance as unavailable. The default summary includes the canonical report overview, up to five compact public-safe projected findings across the scan's observed domains, and bounded row-level pre-consent cookie/tracker evidence; detail=findings increases the default finding allowance, evidence adds bounded evidence digests and references, and full adds all available bounded sections. Every response declares finding and evidence total/returned/truncated counts, byte-budget metadata, omittedSections, retrieval URLs, and nextRecommendedMaxBytes when truncated. Enumerate only returned observations and projected findings. Treat criticality, priority, and confidence as CertScore metadata; regulatory review lenses are non-determinative CertScore review context, not legal severity, legal exposure, or a compliance determination. Missing consent-action evidence does not establish Accept, Reject, or Decline behavior. Do not extrapolate observed embeds, vendors, or requests into unobserved cookies, fingerprinting, tracking, or processing. The CertScore score covers observable scan signals only; do not infer unobserved technologies or legal compliance status, and never interpret no-go, not-observed, or limited coverage as proof of compliance.
| Name | Required | Description | Default |
|---|---|---|---|
| detail | No | Response detail. Defaults to summary; evidence and full opt into heavier retained context. | |
| scanId | Yes | Stable CertScore scan ID. | |
| maxBytes | No | Maximum serialized structured response size in bytes. Defaults to 50000. | |
| maxFindings | No | Maximum compact findings to return. Defaults to 5 for summary and 20 otherwise. | |
| maxPreConsentRows | No | Maximum compact pre-consent inventory rows to return. Defaults to 20. |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| noGo | No | |
| type | Yes | |
| error | Yes | |
| links | No | |
| score | Yes | |
| detail | Yes | |
| domain | Yes | |
| scanId | Yes | |
| status | Yes | |
| timing | Yes | |
| summary | Yes | |
| coverage | No | |
| findings | Yes | |
| scanFrom | Yes | |
| createdAt | Yes | |
| reportUrl | Yes | |
| riskLevel | Yes | |
| startedAt | Yes | |
| disclaimer | Yes | |
| fullReport | No | |
| provenance | Yes | |
| scoreLabel | Yes | |
| completedAt | Yes | |
| mcpMetadata | Yes | |
| scoreStatus | Yes | |
| scoreVersion | Yes | |
| scoreUpdatedAt | Yes | |
| evidenceSummary | No | |
| scanTimeSeconds | Yes | |
| findingsMetadata | Yes | |
| resultDisposition | No | |
| transportSecurity | Yes | |
| recommendedNextTool | Yes | |
| recommendedNextAction | Yes | |
| interpretationGuidance | Yes | |
| observationOnlyDisclaimer | Yes | |
| preConsentCookiesTrackers | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses detailed response structure (TextContent digest, structuredContent, scanFrom), truncation metadata, and interpretive constraints (e.g., no extrapolation, treat CertScore metadata as non-determinative). This goes far beyond the readOnly annotation and provides crucial guidance for correct usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured and front-loaded with the usage condition. It packs dense, non-redundant information, and each sentence earns its place given the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description comprehensively covers response contents, parameter effects, metadata, and interpretation rules, making it highly complete for a complex retrieval tool. It addresses all major aspects an agent would need.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already documents all parameters (100% coverage), but the description adds meaningful context for detail levels and truncation behavior, enriching the parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states this tool retrieves a completed scan bundle after a scan reaches completed/completed_limited status. It differentiates from siblings by focusing on full bundle retrieval, not status checks or scan initiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly conditions usage on scan completion status ('Call after completed or completed_limited status') and provides guidance for reused scans. However, it does not explicitly name sibling alternatives for status-only needs, so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
certscore_get_scan_statusGet scan statusAPoll with only the stable scanId returned by certscore_scan_site. Active responses include phase, heartbeat, estimated progress, stalled state, retry delay, and canonical scan provenance when available. Terminal responses include the CertScore score, risk, coverage, execution region (scanFrom), timestamps, report URL, and an explicit next action. For a reused or retrieved existing scan, use only persisted scanFrom and timestamps; never infer its original region from the current request, the user's location, or a default. Report unavailable provenance as unavailable. Stop polling at any terminal status.
| Name | Required | Description | Default |
|---|---|---|---|
| scanId | Yes | Stable CertScore scan ID returned by certscore_scan_site. |
| Name | Required | Description |
|---|---|---|
| url | No | |
| noGo | No | |
| type | No | |
| error | Yes | |
| jobId | No | |
| links | No | |
| phase | No | |
| score | No | |
| domain | No | |
| scanId | No | |
| status | No | |
| scan_id | No | |
| stalled | No | |
| coverage | No | |
| scanFrom | No | |
| createdAt | No | |
| reportUrl | No | |
| riskLevel | No | |
| startedAt | No | |
| provenance | Yes | |
| scoreLabel | Yes | |
| completedAt | No | |
| scoreStatus | No | |
| scoreVersion | No | |
| lastUpdatedAt | No | |
| phaseStartedAt | No | |
| scoreUpdatedAt | No | |
| lastHeartbeatAt | No | |
| progressPercent | No | |
| scanTimeSeconds | No | |
| resultDisposition | No | |
| retryAfterSeconds | No | |
| progressIsEstimate | No | |
| recommendedNextTool | Yes | |
| recommendedNextAction | Yes | |
| interpretationGuidance | Yes | |
| estimatedRemainingSeconds | No | |
| observationOnlyDisclaimer | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and idempotent behavior, but the description adds essential polling semantics: active vs terminal phases, provenance constraints (never infer region), and the requirement to report unavailable provenance as unavailable. This is rich behavioral context beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Five sentences each carry meaningful weight: invocation instruction, response payload breakdown, provenance caveat, reporting rule, and stop condition. The structure is well-organized and front-loaded with the key usage instruction, with no unnecessary fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Since an output schema exists, the description needn't explain return values. It covers the nuanced behaviors (polling, provenance, stop condition) and even addresses how to handle unavailable provenance, making it complete for a polling tool with this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter scanId is fully described in the schema (100% coverage). The description reinforces it must be the stable scanId returned by certscore_scan_site, adding the 'only' constraint and source clarity, which goes slightly beyond the schema's description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool polls scan status using a stable scanId from certscore_scan_site, and details both active and terminal response contents. This distinguishes it from siblings like certscore_scan_site (which initiates scans) and certscore_get_scan_bundle (which likely returns bundles).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit guidance to poll only with the stable scanId from certscore_scan_site and to stop at any terminal status. It also warns against inferring provenance for reused scans, giving clear invocation context. However, it does not explicitly discuss when to use alternative sibling tools, so it misses the top score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
certscore_scan_siteScan siteAInspectUse CertScore.ai to scan a public website for observable privacy and consent signals, including pre-consent cookies and browser storage, third-party trackers, consent-banner and CMP behavior, TLS/transport security, privacy-policy disclosures, GDPR/ePrivacy transparency findings, and applicable CCPA/CPRA review signals. Starts or reuses a public-web scan with a 25-second total tool-call budget by default; scan creation time is deducted from completion waiting. If status is queued, running, or finalizing, retain scanId and poll certscore_get_scan_status using only that scanId. Stop polling at completed, completed_limited, failed, expired, or rate_limited. For usable completion, call certscore_get_scan_bundle. No-go and limited coverage are observations, never proof of compliance.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public URL or domain to scan. | |
| scanFrom | No | Optional execution region for a newly queued scan. Omit when the user did not request a jurisdiction or regional perspective; use eu_de or eu_ie for explicit EU/GDPR/ePrivacy requests and california for explicit California/CCPA/CPRA requests. Do not use multiple regions unless comparison is requested, and do not infer EU from consent or California from a U.S. user location. | |
| freshness | No | Prefer latest for ordinary website checks so an eligible recent completed scan can be reused and new-scan allowance is not consumed unnecessarily; CertScore may still start a scan when no suitable result exists. Use refresh only when the user explicitly requests a fresh, new, or repeated scan; ordinary check, scan, audit, inspect, review, or assess wording alone does not request refresh. | |
| maxWaitSeconds | No | Total wall-clock budget for scan creation plus optional completion waiting. Defaults to 25 seconds. Creation time is deducted from polling; budget exhaustion returns the accepted active scan and stable scanId without an error. | |
| waitForCompletion | No | Wait for a completed scan resource within this tool call's wall-clock budget. Defaults to true. Set false only for an explicitly asynchronous workflow. |
| Name | Required | Description |
|---|---|---|
| noGo | No | |
| type | Yes | |
| error | Yes | |
| jobId | No | |
| links | No | |
| score | No | |
| domain | No | |
| scanId | No | |
| status | Yes | |
| coverage | No | |
| scanFrom | No | |
| createdAt | No | |
| reportUrl | No | |
| riskLevel | No | |
| startedAt | No | |
| provenance | Yes | |
| scoreLabel | Yes | |
| completedAt | No | |
| scoreStatus | No | |
| scoreVersion | No | |
| scoreUpdatedAt | No | |
| scanTimeSeconds | No | |
| demoSubstitution | No | |
| resultDisposition | No | |
| recommendedNextTool | Yes | |
| recommendedNextAction | Yes | |
| interpretationGuidance | Yes | |
| observationOnlyDisclaimer | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses operational behaviors beyond annotations: it explains the 25-second default budget, that creation time is deducted from waiting, and that budget exhaustion returns an active scan without error. It also emphasizes that non-completion statuses are observations, not compliance proof, providing critical context. No contradiction with annotations (readOnlyHint false, openWorldHint true).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficient and front-loaded with the core purpose, followed by workflow details. Every sentence adds value—there is no fluff, and it avoids repetition of schema fields. It is sufficiently detailed without being bloated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 params, 2 enums, polling workflow), the description provides a complete picture: it covers scan initiation, reuse, polling status, completion handling, and caveats about compliance. The output schema exists, so return values need not be described. The description fully equips an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of parameters with detailed descriptions for each, so the description's role is minimal. While the overall workflow references parameters like maxWaitSeconds and freshness, it does not add per-parameter nuance beyond what the schema already provides. Thus, it meets the baseline but doesn't elevate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: to scan a public website using CertScore.ai for observable privacy and consent signals, with a specific list of signals. It distinguishes itself from siblings by explicitly mentioning when to use certscore_get_scan_status for polling and certscore_get_scan_bundle for results, making it unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers explicit usage guidance, including when to poll with certscore_get_scan_status, when to stop polling, and when to call certscore_get_scan_bundle for completion. It also warns about 'No-go and limited coverage' interpretations, and provides clear regions for scanFrom and freshness preferences, ensuring the agent selects the correct approach.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
