Cyber Lens AI MCP Server
Enables security scanning of public Bitbucket repositories for exposed secrets, dependency vulnerabilities, suspicious code patterns, and trust posture issues.
Enables security scanning of public GitHub repositories for exposed secrets, dependency vulnerabilities, suspicious code patterns, and trust posture issues.
Enables security scanning of public GitLab repositories for exposed secrets, dependency vulnerabilities, suspicious code patterns, and trust posture issues.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cyber Lens AI MCP Server Scan this CLAW skill before I install it: https://clawhub.ai/skills/ontology"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cyber Lens AI MCP Server
Security scanning for AI assistants and agentic coding workflows.
A Model Context Protocol (MCP) server that gives AI assistants the ability to scan websites, public repositories, and Open CLAW skills for security vulnerabilities. It's purpose-built for the agentic coding era, with native support for scanning skill packages before you install them.
What It Does
When connected to an AI assistant (Claude Desktop, VS Code, etc.), this MCP server adds security scanning tools that the assistant can use during your conversation:
Scan a CLAW skill before installing it -- the server downloads the skill package, extracts it, and analyses the actual source code for dangerous patterns, hardcoded secrets, and permission issues
Scan a website in a local quick mode without an account, or use the full cloud scan when connected
Scan a public repository for exposed secrets, dependency vulnerabilities, suspicious code patterns, and trust posture issues
Check your remaining cloud scan quota before kicking off a batch of scans
Get remediation guidance with step-by-step fix instructions and code examples
Example Conversation
You: "I want to install this skill: https://clawhub.ai/skills/ontology"
Claude: I'll scan it for security issues first.
[PASS] CLAW Skill Security Scan: ontology v1.0.4
Security Score: 95/100
Files Analyzed: 5
Skill appears safe to install. Minor issues noted below.
1. [MEDIUM] File write operation
File: scripts/ontology.py:399
Fix: Ensure file writes are limited to expected directories.
The skill looks safe. It writes to the filesystem for its knowledge
graph storage, which is expected behaviour for this type of skill.Related MCP server: securityscan
Getting Started
1. Install
After the first npm release, the recommended install path is:
npx -y @shadoprizm/cyberlens-mcp-serverBefore that, or for local development and manual builds:
git clone https://github.com/shadoprizm/cyberlens-mcp-server.git
cd cyberlens-mcp-server
npm install
npm run build2. Add to Your AI Assistant
Claude Desktop -- add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"cyberlens": {
"command": "npx",
"args": ["-y", "@shadoprizm/cyberlens-mcp-server"]
}
}
}If you are running from a source checkout instead of npm:
{
"mcpServers": {
"cyberlens": {
"command": "node",
"args": ["/absolute/path/to/cyberlens-mcp-server/dist/index.js"]
}
}
}Claude Code -- add to your MCP settings or project configuration.
VS Code (Copilot/Continue) -- configure per your extension's MCP server settings.
3. Connect Your Account
Website tools work immediately without an account in local quick mode. That local mode covers roughly 15 core checks and returns results right away.
Connecting an account upgrades website scans to the full CyberLens cloud path with 70+ checks, scan history, and AI analysis. Repository and account-only tools still connect through the browser flow when needed.
When a repository or account-only tool needs an account, the MCP server:
opens the CyberLens browser flow automatically
sends the user to
cyberlensai.comto sign up or log inreceives the secure callback locally
saves the API key to
~/.cyberlens/mcp/config.jsoncontinues the original tool call automatically
You can also trigger the same flow explicitly:
You: "Connect my CyberLens account"This opens your browser to cyberlensai.com where you can sign up (free) or log in. Your API key is saved locally at ~/.cyberlens/mcp/config.json and used for all future scans.
Free accounts include 5 scans/month. No credit card required.
You can also set the
CYBERLENS_API_KEYenvironment variable in the MCP config instead of using the browser flow.
If a cloud website scan hits its monthly quota, the MCP server opens the CyberLens pricing page automatically and falls back to the local quick scan instead of hard-failing. Repository scans still require cloud quota.
Available Tools
Account
Tool | Description | Requires API Key |
| Opens browser to sign up/log in and saves your API key locally | No |
| Shows your current plan and remaining website/repository scan quota; auto-connects on first use if needed | Yes |
CLAW Skill Scanning
Tool | Description | Requires API Key |
| Download and analyse a CLAW Hub or direct skill package for security issues | No |
| Validate a skill manifest against security best practices | No |
Website & Repository Scanning
Tool | Description | Requires API Key |
| Local quick website scan without an account; full cloud scan when connected; local fallback if website cloud quota is exhausted | No for local, Yes for full cloud |
| Public repository security scan for GitHub, GitLab, Bitbucket, and supported ZIP targets; auto-connects on first use if needed | Yes |
| Retrieve detailed findings from a completed cloud scan; auto-connects on first use if needed | Yes |
| Local quick website score without an account; full cloud score when connected | No for local, Yes for full cloud |
Intelligence & Guidance
Tool | Description | Requires API Key |
| Built-in local remediation playbooks for common CWEs and vulnerability classes | No |
| Honest report of the MCP server's local checks and live cloud endpoints | No |
How Skill Scanning Works
When you provide a CLAW skill URL, the MCP server:
Resolves the URL -- accepts Claw Hub pages (
https://clawhub.ai/skills/skill-name), direct download links (https://*.convex.site/api/v1/download?slug=name), or any URL pointing to a skill zipDownloads the skill package to a temporary directory
Extracts and analyses every file in the package:
Checks
_meta.jsonandSKILL.mdfor completenessScans all source code (Python, JavaScript, TypeScript, shell scripts, config files) for dangerous patterns
Detects hardcoded secrets,
eval()usage, shell command execution, insecure HTTP requests, file deletion operations, pickle deserialisation, and moreIdentifies unpinned dependencies
Catalogues all external URLs the skill communicates with
Returns a security score (0-100) with detailed findings, file locations, and fix recommendations
Cleans up all temporary files
This entire process runs locally -- no API key is required and your code is never sent to an external server.
Website Scan Modes
scan_website and get_security_score now have two honest modes:
Local Quick Scan -- works without an account, returns immediately, and covers roughly 15 core website checks such as HTTPS, security headers, server disclosure, insecure forms, and inline-script indicators
Full Cloud Scan -- requires a connected CyberLens account, runs 70+ checks, keeps cloud scan history, and includes richer analysis
If a user asks for a full or database website scan without an account, the MCP server still returns the local quick scan and says that the requested cloud-only mode was not available.
If a connected user runs out of website cloud quota, CyberLens falls back to the local quick scan automatically and opens the pricing page with an upgrade link.
Accepted URL Formats
https://clawhub.ai/skills/ontology --> Resolves automatically
https://clawhub.ai/author/skill-name --> Resolves automatically
https://*.convex.site/api/v1/download?slug=x --> Direct downloadArchitecture
src/
index.ts MCP server, tool handlers, output formatting
auth.ts Browser-based connect flow, config file management
client.ts REST API client for live scan and quota endpoints
remediation-guides.ts Local CWE and vulnerability remediation guidance
schemas.ts Zod input validation schemas
skill-scanner.ts Local CLAW skill analyser (download, extract, scan)
skill-validation.ts Local CLAW manifest validation
transparency.ts Local transparency report for scan coverageKey design decisions:
No Supabase SDK -- pure REST calls with
fetchandX-API-KeyheaderTruthful cloud surface -- the MCP server only exposes cloud-backed tools that are supported by the live public API (
/scan,/scan/{id},/quota)Stdio transport -- runs as a subprocess of the AI assistant, communicates via stdin/stdout
Useful without API key -- skill scanning, website quick scans, manifest validation, remediation guidance, and transparency reporting work locally; connecting an account upgrades website scans to the full cloud path and unlocks repository scanning
Browser-based auth -- same secure connect flow as the CyberLens OpenClaw skill (CSRF-protected, short-lived exchange codes, HTTPS-only)
Development
# Build
npm run build
# Watch mode
npm run dev
# Run directly (for testing)
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | node dist/index.jsEnvironment Variables
Variable | Required | Default | Description |
| No | -- | API key (alternative to browser connect flow) |
| No |
| API endpoint override |
Publishing
This repository is prepared for npm + MCP Registry publication as:
npm package:
@shadoprizm/cyberlens-mcp-serverMCP server name:
io.github.shadoprizm/cyberlens-mcp-server
Typical release flow:
# 1. Bump the version
npm version patch
# 2. Publish the package to npm
npm publish
# 3. Authenticate with the MCP Registry
mcp-publisher login github
# 4. Publish server.json to the MCP Registry
mcp-publisher publishThe registry metadata lives in the root server.json file and the npm ownership check uses the mcpName field in package.json.
Related Projects
CyberLens OpenClaw Skill -- the OpenClaw skill version with the same scanning capabilities
CyberLens -- the full platform with browser-based scanning, dashboards, and reporting
OpenClaw -- the open skill ecosystem for AI agents
License
Available Tools
10 toolsconnect_accountA
Connect your CyberLens account to this MCP server.
Opens your browser to cyberlensai.com where you can sign up for free or log in. After authorizing, your API key is securely saved locally.
Free accounts get 5 scans/month. No credit card required.
If you already have an API key, you can also set the CYBERLENS_API_KEY environment variable instead. Cloud tools can also launch this flow automatically the first time repository or account-only tools need an account.
Inputs: no named parameters.
get_account_quotaA
Get your CyberLens account quota and remaining cloud scans.
Returns:
Current plan name
Total scans used, limit, and remaining
Website scan usage
Repository or skill scan usage
Use this to confirm your account is connected and check how many cloud scans remain. If no account is connected yet, the MCP server will launch the CyberLens browser flow automatically before checking quota.
Inputs: no named parameters.
get_remediation_guideA
Get detailed remediation guidance for a specific vulnerability or CWE.
Returns:
Explanation of the vulnerability
Step-by-step fix instructions
Code examples (before/after)
Testing procedures
Prevention strategies
Uses a built-in local guide library, so it still works even when no cloud guidance endpoint is available.
Inputs: cwe_id (required), context.
get_scan_resultsA
Retrieve detailed findings from a completed security scan.
Returns:
Overall security score (0-100)
List of vulnerabilities with severity levels
CWE classifications
Specific recommendations for each finding
CVE references where applicable
Remediation guidance links
Use this after initiating a full cloud scan with scan_website or scan_repository. Local quick website scans return findings immediately and do not produce a scan ID. If no account is connected yet, the MCP server will connect first and then retrieve the cloud scan result.
Inputs: scan_id (required), severity_filter.
get_scan_transparencyA
Get an honest transparency report for this MCP server.
Returns:
Current MCP server version
Local check inventory and category counts
Which live cloud API endpoints this server actually uses
Recent changes to the MCP scan surface
Use this to understand exactly what this server checks locally and which cloud features are live.
Inputs: include_changelog.
get_security_scoreA
Get a quick security rating for a website.
Returns:
Overall security score (0-100)
Grade (A-F)
Key metrics summary
Quick wins for improvement
Without an account, this uses the local quick website scanner. With an account, this uses the full CyberLens cloud path. If cloud website quota is exhausted, CyberLens falls back to the local quick score automatically.
Inputs: url (required).
scan_claw_skillA
Scan an Open CLAW skill or plugin from CLAUDE Hub before installation.
Runs locally in the MCP server and understands CLAW skill packaging, manifest permissions, and AI agent security models.
Performs comprehensive security analysis on:
CLAUDE Hub skill/plugin download links
Skill manifest files
Embedded code and dependencies
Checks for:
Hardcoded secrets and API keys in skill code
Vulnerable npm/pip dependencies
Insecure file operations
Suspicious network requests
Unsafe eval() or code injection patterns
Privilege escalation risks
Data exfiltration patterns
Permission scope appropriateness
Use this BEFORE installing any CLAW skill to ensure it's safe for your environment.
Examples:
CLAUDE Hub URL: https://clawhub.ai/username/skill-name
Plugin download: https://*.convex.site/api/v1/download?slug=skill-name
Inputs: skill_url (required).
scan_repositoryA
Scan a public repository for secrets, dependency risks, and suspicious code patterns.
Uses the live CyberLens cloud repository scanner for:
Public GitHub, GitLab, and Bitbucket repositories
Supported CLAUDE Hub or direct ZIP download URLs
Checks for:
Exposed secrets and credentials
Vulnerable dependencies
Suspicious or risky code behavior
Trust posture and repository hygiene signals
Artifact and package reputation issues
Returns a scan ID that can be used with get_scan_results to retrieve findings. If no account is connected yet, the MCP server will open the CyberLens browser flow automatically and then continue the scan.
Inputs: repository_url (required), depth, branch.
scan_websiteA
Scan a website for security vulnerabilities with a local quick mode and a full cloud mode.
Without a connected account, the MCP server runs a local quick scan immediately. That local mode covers roughly 15 core checks such as HTTPS, security headers, basic form issues, inline scripts, and server disclosure.
With a connected account, CyberLens starts the full cloud scan with 70+ checks. That path returns a scan ID you can use with get_scan_results.
If cloud website quota is exhausted, CyberLens falls back to the local quick scan automatically and opens the upgrade page.
Inputs: url (required), scan_type, database_connection.
validate_claw_skillA
Validate a CLAW skill manifest and configuration for security best practices.
Checks:
Skill manifest.json structure and required fields
Permission scopes (are they minimal?)
External API dependencies
File system access patterns
Environment variable usage
Plugin isolation safety
Use this before publishing a skill to CLAUDE Hub or for CI/CD validation.
Inputs: manifest_json (required), skill_code.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have distinct purposes, but scan_claw_skill and validate_claw_skill both target CLAW skill security and enumerate overlapping checks, making them easy to confuse. scan_website and get_security_score also overlap somewhat since both perform website scanning and return a security rating, though the descriptions do clarify the difference between full findings and a quick score.
All tool names follow a consistent snake_case verb_noun pattern: scan_<target> for scanning tools, get_<thing> for retrieval tools, plus connect_account and validate_claw_skill. There are no mixed naming conventions or vague verbs.
Ten tools is well-scoped for a security scanning server covering website, repository, and skill scanning along with account management, quota, results, remediation, and transparency. Each tool has a recognizable role and the set does not feel bloated.
The core scanning lifecycle is covered: account connection, quota checks, initiating scans for websites/repos/skills, retrieving results, getting remediation guidance, and inspecting server transparency. Minor gaps exist, such as no scan history or explicit scan-status polling, but the main workflows are complete enough for agents.
Maintenance
Related MCP Connectors
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
Scan websites and code for security, performance and SEO issues from your AI assistant.
Security scanner for AI-written code: SAST, secrets, dependencies, IaC, containers and DAST.
Authorized security scans, evidence, fix prompts and retests for AI-built web apps.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to scan project dependencies and Infrastructure as Code files for security vulnerabilities and misconfigurations. It also provides automated fixing capabilities to remediate identified security issues.183MIT
- FlicenseNot gradedqualityDmaintenanceScans OpenClaw/ClawHub skills for security vulnerabilities before installation. Detects prompt injection, data exfiltration, credential theft and RCE risks. Autonomous AI-to-AI flow with zero human intervention required.-
- AlicenseAqualityBmaintenanceVet ClawHub skills before installing them; detects prompt-injection, exfiltration, and other security issues, outputting a risk score with per-finding evidence.739 PyPIMIT

AgentAuditofficial
AlicenseAqualityDmaintenanceEnables AI agents to scan MCP servers and AI packages for vulnerabilities, prompt injection, and supply chain attacks.788 npmAGPL 3.0