Skip to content
Cisco
CiscoAI Security

Cisco IDE AI Security Scanner

Trust, but verify — security scanning for MCP servers, agent skills, and AI-generated code.

Your AI agents pull in MCP servers, run skills, and generate code — but how do you know what they're actually doing? Cisco AI Security Scanner watches the supply chain around your AI tools and catches threats before they land: hidden instructions, data exfiltration, prompt injection, vulnerable patterns, and more.

Works in VS Code, Cursor, Windsurf, and Antigravity.

Join Discord | Cisco AI Defense


How It Works

Get protected in three steps.

1. Install — Install from the VS Code Marketplace or via VSIX. The Setup Wizard walks you through initial configuration.

2. Configure — Choose your analyzers — YARA and behavioral analysis run out of the box. Optionally add an LLM provider, Cisco AI Defense, or VirusTotal for deeper analysis.

3. Scan — Run Scan All (MCP + Skills) from the Command Palette, or let auto-scan handle it. Review findings in the sidebar, dashboard, or Problems panel.


Command Reference

All commands are accessible via the Command Palette (Cmd/Ctrl+Shift+P).

Scanning

CommandDescription
Scan All (MCP + Skills)Scan all MCP configs and skills in a single pass
Scan All MCP ConfigurationsScan MCP configurations only
Scan Global MCP ConfigurationsScan IDE-level MCP configs only
Scan Workspace MCP ConfigurationsScan project-level MCP configs only
Scan This MCP Config FileScan a specific MCP config file (context menu)
Scan All SkillsScan all discovered skills
Scan Global SkillsScan IDE-level skills only
Scan Workspace SkillsScan project-level skills only
Scan This SkillScan a specific skill (context menu)
Refresh ConfigurationsRefresh the list of discovered MCP configurations
Refresh SkillsRefresh the list of discovered skills
Refresh FindingsRefresh the current security findings
Refresh AnalyzersRefresh the state of the analysis engines
Refresh SettingsRefresh the extension settings view
Refresh HistoryRefresh the scan history list
Refresh AllowlistRefresh the allowlist view

Skill Specific

CommandDescription
Trust This SkillAdd a skill to the allowlist
View Skill DetailsView detailed information about a discovered skill
Show Skill DetailsShow details for a specific skill in the UI
Show Skill Finding DetailsShow details for a specific security finding in a skill
Open File at FindingOpen the skill file directly to the line containing the finding
Configure Scan PolicyOpen the interactive scan policy editor

Configuration

CommandDescription
Configure LLM ProviderSelect your LLM provider and enter your API key
Configure Cisco AI DefenseEnter your Cisco AI Defense API key
Configure VirusTotal APIEnter your VirusTotal API key
Configure AnalyzerQuick-toggle analyzers on or off
Open SetupOpen the extension setup interface
Open Setup WizardRe-run the initial setup wizard
Open Extension SettingsOpen VS Code settings filtered to scanner settings
Test LLM ConnectionVerify your LLM API key and endpoint are working
Toggle SettingQuick toggle for boolean settings
Select Setting ValueQuick selection for enum settings

Results and Reports

CommandDescription
Open Security DashboardVisual summary with severity breakdown and quick actions
Show Scan ResultsShow the most recent scan results in the sidebar
Show Finding DetailsOpen detailed view for a specific security finding
Export Scan ReportExport results as JSON, Markdown, or CSV
Compare with Previous ScanSee new, resolved, and unchanged findings
Open Custom YARA Rules FolderOpen the directory for custom rules
Show Scan HistoryBrowse past scan results

Allowlist

CommandDescription
Add to AllowlistSuppress findings for a trusted server, tool, or skill
Remove from AllowlistRe-enable scanning for an allowlisted item
Remove ServerRemove a flagged server from the MCP config
View Tool DetailsView detailed information about a discovered tool

CodeGuard

CommandDescription
Configure CodeGuard RulesSelect IDEs and rule categories to inject
Inject Rules NowWrite selected rules into IDE agent config
Remove All RulesRemove all injected CodeGuard rules
Show Injection StatusSee which rules are currently active
Reset Injection ConsentReset the prompt asking for permission to inject rules

Watchdog

CommandDescription
Toggle File ProtectionEnable or disable Watchdog globally
Add File to WatchlistMonitor a custom file path
Remove File from WatchlistStop monitoring a specific file
View Diff Against SnapshotSee what changed since the last snapshot
Restore File from SnapshotRevert a file to its last known-good state
Accept Current File StateAccept the current content as the new baseline
Re-Snapshot All FilesTake fresh snapshots of all monitored files
Restore All Modified FilesRevert all modified files at once
Configure PresetsToggle which file protection presets are active
RefreshRefresh the Watchdog status view
Show Activity LogView the history of file changes and Watchdog actions
Check Protection StatusCheck the current protection status
Clear All SnapshotsRemove all stored snapshots and start fresh

Troubleshooting

CommandDescription
Toggle Debug ModeEnable verbose logging for troubleshooting
Show History DetailsShow detailed information about a historical scan
Show Extension LogsOpen the output channel with scanner logs
Reset Python EnvironmentRebuild the Python virtual environment and reinstall scanners
Clear All Stored Data & KeysRemove all cached data, API keys, and scan history
Clear Scan HistoryRemove all stored scan history

Security and Privacy

  • Secure Credential Storage — API keys stored in your OS keychain via VS Code's SecretStorage API
  • No Tool Execution — Analyzes descriptions only; never executes MCP tools or runs skill code
  • Privacy-First VirusTotal — Only file hashes sent by default; file upload is opt-in
  • Minimal Network Access — Requests only made for configured analyzers (YARA and behavioral analysis are fully local)
  • No Source Code Transmission — Your source code never leaves your machine; only MCP tool descriptions and skill definitions are sent to configured analysis services