CyberLens AI
Server Details
Review saved CyberLens website and repository scans through read-only OAuth tools.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- CyberLens AI
- Claude
- –
TDQS
Scored across 6 tools
Each tool maps to a distinct action: profile identification, single-scan retrieval, scan listing, link building, and two explanatory tools. The only mild friction is between explain_website_check and preview_sample_scan, but the descriptions explicitly separate a real user-supplied check from an illustrative demo, so misselection is unlikely.
All six tools follow a clean verb_noun snake_case pattern (get_my_profile, list_my_scans, open_website_scanner, etc.). The 'my_' prefix is applied consistently to account-scoped tools, which is a meaningful distinction rather than an inconsistency.
Six tools is a well-scoped surface for a read-only companion to a web security scanner. Every tool has a distinct job (identity, scan status, scan listing, scan initiation link, sample preview, check explanation) with no filler.
The read-only lifecycle is covered (identify account, list scans, get scan status, launch a new scan via link), but there is no way to retrieve actual findings or per-check results, which is central to a security-scanning domain. The deliberate exclusion is documented, yet it leaves agents at a dead end when asked 'what failed?'.
Available Tools
6 toolsexplain_website_checkExplain how to fix a website security checkARead-onlyInspect
Explain the first fix and verification step for a supported header or security.txt check the user supplies from their report. This tool does not retrieve report findings or determine whether a check failed.
Inputs: check (required).
get_my_profileGet connected CyberLens accountARead-onlyInspect
Identify the CyberLens account connected to this session.
Inputs: no named parameters. Returns: id, email
get_my_scanGet my CyberLens scan summaryARead-onlyInspect
Retrieve status, score, and available test counts for one scan owned by the connected CyberLens account. A legacy repository record with a zero total and no assessed count has no reliable test count; do not say that zero tests ran. Does not expose raw findings, secrets, or database connection details.
Inputs: scan_id (required).
list_my_scansList my recent CyberLens scansARead-onlyInspect
List up to 25 recent website and repository scans owned by the connected CyberLens account, with status and available score. Does not start a scan.
Inputs: limit.
open_website_scannerOpen CyberLens with a website ready to scanARead-onlyInspect
Create a link to the CyberLens website scanner with the user-supplied website filled in. The user reviews the target and starts the scan on CyberLens. This tool only builds a link.
Inputs: website (required).
preview_sample_scanTry a sample website fix planARead-onlyInspect
Show an illustrative website check and a practical fix without a CyberLens account or a real scan.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only scan of a public GitHub repo for leaked secrets, with a 0-100 grade.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes.
Synthetic UX reviews, findings, evidence images, and repair prompts. OAuth required.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables read-only, evidence-led security audits of GitHub-hosted source code through explicit workflow primitives: repository reconnaissance, coverage-ledger planning, heuristic candidate leads, structured findings validation, independent verification gates, and JSON/Markdown report generation. It never clones, executes, or probes the target code, and marks runs incomplete until coverage and reviewer-verification gates pass.14AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceRead-only observation of a single live URL: parses static HTML to report security posture, forms, links, accessibility signals, and leaks, with described fixes. SSRF-gated and safe, never executes JavaScript.123 npmMIT
- AlicenseAqualityBmaintenanceExposes read-only repository scanning across architecture, security, performance and product lenses, citation verification of findings against a working tree or git revision, and HTML/SARIF/Markdown dossier rendering as MCP tools for assistants such as Claude and Cursor.31Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables read-only, source-backed vulnerability investigations, recent intelligence discovery, CVE/package evidence review, and observed-change timelines through cached MCP tools covering briefings, CISA KEV, EPSS, GitHub advisories, and OSV records.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.