securecode.run-tests
Run tests in sandbox for verification
How to use it
Project documentation lists securecode.run-tests for the SecureCode MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install SecureCode MCP
npx -y @securecode-ai/mcp@latest serve --workspace /path/to/your/projectOther tools in SecureCode MCP (16)
Add a project fact for faster investigations
Agent-mode deep scan with 20+ tools, structured proof, and sandbox verification
Sequential batch scan: map + architecture scout + scan top N files one at a time
Endpoint red-team testing (beta)
Clear all agent memory (or one FP by ID)
Clear all finding reviews for a workspace
Accept or reject a finding in the review queue
Generate a patch for a specific finding
View learned false positives and known facts
Build project map: endpoints, middleware, auth, architecture context
Dismiss a finding as FP — agent learns not to report it
Review the finding queue for a workspace
Scan code for vulnerabilities (AI pipeline)
Scan multiple files in one call
Scan lockfiles for known vulnerabilities (OSV/NVD)
Scan for hardcoded secrets and PII (local, no AI)