Search

The local security layer for coding agents. Use Claude Code, Codex, Cursor or OpenCode without exposing your secrets, your data or your systems. Open source, MIT, nothing leaves your machine.

Security for AI agents & MCP — map how MCP servers, skills, and memory chain into exposure paths. Toxic-flow detection, cross-surface graph, drift & policy-as-code. Local-only, no telemetry.

Authorization boundary and security regression testing for AI agent tool calls (MCP): decide on arguments against delegated authority, bind decisions to single-use grants, replay, and pin denials as CI tests. Experimental.

AI-first security scanner with 76 analyzers, 4,000+ detection rules, 508 FP filters (96.8% reduction), and 133 CVE detections for AI/ML, LLM agents, and MCP servers

MCP server that scans an MCP server's own authorization code for OAuth 2.1 anti-patterns named in the MCP spec's Security Considerations: token passthrough, missing audience validation, OAuth/OIDC discovery SSRF, missing PKCE, loose redirect_uri validatio

MCP server that gives AI agents 12 security tools powered by a multi-stage detection pipeline. Scans prompts, responses, SQL, file writes, and web searches for injection attacks, PII leaks, and policy violations. Session correlation engine with human-in-t

MCP server security scanner — static tool-poisoning / prompt-injection audit (OWASP LLM01/LLM08) + maintenance & supply-chain drift grade + continuous monitoring; plus a pre-trade Base token safety gate. Keyless x402 pay-per-call.

Open-source CLI scanner for agentic AI components such as skills, MCP servers, system prompts

CCS Runtime Evidence MCP Server — verify AI agent tool calls, issue tamper-evident evidence, audit MCP configs. For Claude Desktop, Cursor, Windsurf, and any MCP client.

Build-time security scanner for MCP servers

Atomic MCP tools for AppSec and AI Security engineers

Offline security checks for Model Context Protocol server configurations

🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️

A curated list of MCP security tools, frameworks, scanners, gateways, and resources.

Local-first, offline-by-default security posture scanner for MCP / local-agent setups.

Local-first, offline-by-default security posture scanner for MCP / local-agent setups.

Deterministic MCP Security Architecture. FrozenNamespace as Root of Trust for Model Context Protocol tool verification.

Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.

Offline security scanning for AI-generated code: seven open-source scanners in one MCP server.

Pipeline and workstation client of the security-review-mcp controller: gate, SARIF, trends, code and dependency scans