Agent Security Scanner
Pricing
Pay per usage
Go to Apify Store
Agent Security Scanner
Scan AI agent repos, MCP servers, and coding-agent configs for unsafe eval, shell execution, package hallucinations, prompt injection, and MCP security risks.
Agent Security Scanner
Pricing
Pay per usage
Scan AI agent repos, MCP servers, and coding-agent configs for unsafe eval, shell execution, package hallucinations, prompt injection, and MCP security risks.
What kind of artifact should ProofLayer scan?
Git repository URL to clone when target is repository or mcpServer.
URL returning an MCP server.json-style manifest or agent config JSON.
Inline MCP manifest or AI client config JSON. Accepts either a JSON object or a JSON string.
Scanner coverage areas to include in the output metadata.
[ "all"]Only publish findings at or above this severity.
Include remediation guidance in dataset rows and summary output.
Use quick for fast rule-based repository results. Use analyzer for deeper per-file analysis with a higher runtime cost.
Include tests, demos, benchmarks, and fixtures in repository scans. Disabled by default to reduce noisy findings from intentionally vulnerable examples.
Maximum number of source files to scan for repository targets. Lower values finish faster on large repositories; maximum is 500.