Agent
Discoverability

SystemAudit

Scan any public GitHub repository for security risks, structure and exposed credentials — a health score and plain-English findings, no sign-in.

View in the Claude registry
Integration details

Description

Ask Claude "Should I depend on github.com/lukeed/clsx?", "Compare these two libraries" or "Give me a due-diligence read of this repo". SystemAudit gives a security and code-health review of any public GitHub repository: a health score out of 100, the top risks in plain English, how the project is built, and how many potential hardcoded credentials it contains. Works on any public repository, with no sign-in and no account. Private repositories are refused by design: the connector holds no GitHub account access, which keeps it safe to point at any public repository. Scan private ones on systemaudit.dev. Built for the moment before you commit to a codebase: choosing an open-source dependency, running technical due diligence on an investment or acquisition, inheriting a repository, or sanity-checking code an AI tool generated. Three tools: scan_repository: health score, ranked risks, how the project is built, credential counts, and how many files were read out of how many exist. get_architecture: package ecosystem, architecture pattern, language mix, dependency count, circular imports and files nothing else imports. secrets_summary: potential hardcoded credentials and committed environment files, counted by severity. Honest by design. Every answer states how many files were read, so a clean result is never mistaken for a clean repository. The connector returns credential counts by severity only, never a file, line or value; the linked full report on systemaudit.dev shows locations for critical and high findings, as it does for any public repository scan. Your conversation stays yours: the connector receives only the repository you name. No code is executed, no file contents are returned, and we keep the resulting report, not a copy of the repository. Response times: an already-scanned repository answers from its saved result. A first scan reads the repository through the GitHub API, so larger repositories take longer. New scans are rate-limited.

Integration type
Connector
Verification status
Community connector
Platform
Claude
Category
Developer Tools

The broad Category that contains the Primary Subcategory.

Primary Subcategory
Application Security & Vulnerability Management

The Primary Subcategory used for this profile’s headline score.

Secondary Subcategories
None listed

Other Subcategories where the Integration is listed.

Access
No account required
First tracked
2026-09-27
Tool count
3
Market
US
Agent DiscoverabilityClaude Discoverability Score

Claude Connector discovery is coming soon

Community Connectors only appear in Claude’s registry.Once verified, organic discovery begins and we can calculate your score.Read more about Community Connector verification.

No spam. Unsubscribe any time.

What discovery looks like

Claude showing a list of relevant Connectors in a conversation

Claude can surface verified Connectors when they match a user’s Prompt.

1 scoredVerified connectors by score · Community connectors A–Z
Primary Subcategory
1CloudBees Unify MCP Server88/100
—ActiveLayerPending VerificationGet notified
—Affirmed AIPending VerificationGet notified
—AgentAvowPending VerificationGet notified
—AgentMart Site CheckPending VerificationGet notified
—AI Website SecurityPending VerificationGet notified
—Apiiro GuardianPending VerificationGet notified
—ArcjetPending VerificationGet notified
—AribotPending VerificationGet notified
—Assetnote MCPPending VerificationGet notified
—AssurlyPending VerificationGet notified
—AttackerViewPending VerificationGet notified
—ChronoloqPending VerificationGet notified
—DechoNetPending VerificationGet notified
—DepScoutPending VerificationGet notified
—EnokiPending VerificationGet notified
—FlawPilotPending VerificationGet notified
—FYEO Security ScannerPending VerificationGet notified
—GAdvisoryPending VerificationGet notified
—k9 Security Reachable RiskPending VerificationGet notified
—Kenwea NotaryPending VerificationGet notified
—Klisten ToolGuardPending VerificationGet notified
—MAVENS.mcpPending VerificationGet notified
—mcp.xfa.techPending VerificationGet notified
—MindFort MCPPending VerificationGet notified
—Orca SecurityPending VerificationGet notified
—PathToShipPending VerificationGet notified
—PillarPending VerificationGet notified
—Presend package checksPending VerificationGet notified
—PromptBrake Free ToolsPending VerificationGet notified
—RollcagePending VerificationGet notified
—SafeguardPending VerificationGet notified
—SecureNowPending VerificationGet notified
—SetRepo Security ScannerPending VerificationGet notified
—SpellwardenPending VerificationGet notified
—SubImagePending VerificationGet notified
—SystemAuditPending VerificationGet notified
—TechWatchAlertPending VerificationGet notified
—VibeDoctorPending VerificationGet notified
Tools

3 tools agents can invoke

Recommended guideHow to get your Claude Connector organically discoveredFollow the practical steps agents use to find, shortlist, and choose your Connector.Read guide
FAQs

SystemAudit Claude Connector FAQ

How the directory, categories and Discoverability Score work.

Read the methodology
How do I improve SystemAudit's Claude Connector discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are SystemAudit alternatives on Claude?

As of 2026-11-02, SystemAudit competes with CloudBees Unify MCP Server, ActiveLayer, Affirmed AI, AgentAvow, AgentMart Site Check, AI Website Security, Apiiro Guardian, Arcjet and 33 more in Claude Application Security & Vulnerability Management, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.