Code

AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.

KATATAN E2E testing agent set — Playwright + KATATAN MCP integration

Chinese labor & service contract risk assessment with 25 categories and local law differences.

Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.

98 MCP tools for verifiable AI: citations, law, KYB, peer review, forecast, media provenance.

Janus concierge: ask about, price, check, and request a private Kinematic Drive over MCP.

An MCP server that mounts your skill directory and add deterministic entry for deployment

MCP server for DefectDojo: 24 tools with RBAC, HMAC audit chain, and SIEM forwarding

93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys.

Gemini-powered MCP server for code review analysis.

Single exec tool running caller Python in a network-isolated locked-down sandbox.

Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.

Freeze a corpus, check it for drift, keep a hash-chained audit ledger. Local-first, stdlib-only.

Contract testing and quality gates for spreadsheets created by AI agents.

Persistent Docker/SSH sandbox for AI agents: shell exec, file ops, audit log.

Run local prompt regression checks from prompt-response logs in AI coding assistants.

Keyless local MCP server for QA: standards retrieval, effort estimation, doc review, test analysis.

Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.

Architectural sensor for Python codebases.

Git diff and markdown review with a web UI plus MCP stdio for AI agents.