Enables coding agents to surgically harvest licensed upstream code, scaffold adapters behind canonical contracts, audit seams, verify live behavior, and promote or mount proven components while preserving the host architecture.

177 tools for AI agents. Turn Chrome into an MCP server — inspect DOM, automate clicks, audit security, mock APIs, extract data, download videos, schedule agents, monitor pages, self-improving recipes, full API collection management, business intelligence

CLI for the Guren framework: scaffolding (make:*, add), migrations, codegen, and the check, audit and gate commands a coding agent runs to verify its work.

Enables AI clients to build, solve and inspect LS-DYNA analyses, either by driving Ansys Mechanical through PyMechanical or by submitting and monitoring standalone keyword-deck runs. It also reads and audits solver output files such as glstat, binout, d3plot and ASCII histories, with results comparison and deck checks.

Enables AI clients and CLI users to query and modify multiple MySQL data sources routed by project and environment, with explicit environment binding, server-side read-only enforcement, hot-reloaded web configuration, and SQL execution auditing.

Enables AI clients to securely control Linux and WSL2 systems over Streamable HTTP with Bearer token authentication, supporting command execution, background jobs, file operations, Docker management, system inspection, and audit log access with safety confirmations and path protections.

Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.

Enables auditing GitHub Actions workflows for security problems directly from an MCP client, returning a risk score and findings with file:line evidence, attack narratives, and fixes. Also exposes the full rule catalog and a one-call demo that writes and scans a deliberately broken workflow.

Enables Claude and other MCP clients to safely query PostgreSQL data and perform limited order-status updates through scoped bearer tokens, read-only transactions, row caps, and an audit log.

Enables MCP clients such as Claude to search, tag, catalogue, ingest, audit, relocate, and repair a running Connecter asset library, including texture scanning and relinking, with dry-run plans and undoable journaled changes.

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

Open-source marketing skills for founders. Keyword research, growth strategy, social search audit, competitor analysis. Install with npx skills.

Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

Read-only Sinthoma clinical connector: patients, sessions and prep; OAuth consent and audit.