MCP server and CLI that tells your coding agent what it is about to break: blast radius, dead code, and health for any local codebase. Runs entirely on your machine.
Find vulnerabilities and insecure patterns in code.
MCP server and CLI that tells your coding agent what it is about to break: blast radius, dead code, and health for any local codebase. Runs entirely on your machine.
Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.
Bounded conventions map and local-pattern discovery for AI coding agents. Local-first MCP server with AST-backed hybrid search.
MCP server & CLI: codebase index + cache for Claude Code, Cursor, OpenAI Codex, Google Antigravity/Gemini. Model Context Protocol tools (codetree_read, codetree_search, …), hooks on Claude, rules on other IDEs. Token savings, SQLite index, symbol search,
MCP server that exposes PHPStan as tools, for several PHP projects at once
Enterprise certification for codebases with multi-agent security, reliability, and quality audits
Security scanner for AI agent packages — CLI + MCP server
Scan MCP server source code and Agent Plugins 1.0 packages for patterns that break under the final 2026-07-28 Model Context Protocol specification, plus the Python and TypeScript SDK v1→v2 migrations.
Run Offensive360 SAST scans (60+ languages) on local code; findings with file/line and fixes
Roslyn MCP server: semantic .NET/C# intelligence - analysis, refactoring, tests, IL inspection.
Deprecated shim: forwards to @cognium/mcp-server, which now serves these tools via circle-ir-ai/mcp
Safety-first context & orchestration engine for AI coding agents. MCP server with mandatory research pipeline, knowledge graph, impact analysis, decision memory, and safety guard — works with any MCP client.
Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +23. Local. Deterministic.
MCP security scanner — 55 tools for runtime inspection, static analysis, config audit, dependency analysis. OWASP MCP Top 10 compliance. OAuth, TLS, fuzz testing, prompt injection, tool mutation detection. 100% local, zero external API calls.
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Dependency graph and blast-radius analysis for local TypeScript/JavaScript repos.
React codebase semantics for AI agents, with a VS Code visualizer you both share. Free, local.
Zero-trust MCP file writes, native code intelligence, graph retrieval, hooks, and agent skills
Pre-install security scanner for AI agent skills (local stdio MCP). Offline static scan; no upload.
Deterministic code map for AI coding agents: a tree-sitter call graph with exact file:line over MCP.