MCP servers for repositories, version control, CI, error tracking, sandboxes and code execution. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
MCP server that lets AI agents vent friction into .vents/ markdown files in your repo
Self-hosted WCAG 2.1 compliance scanning, remediation tracking, and AI agent integration via MCP
Xcode MCP server - build, test, run, and manage simulators from Claude Code
Zero Setup. Zero API Keys. Expose your local authenticated CLIs as MCP tools.
CLI installer for UserDispatch feedback widget + MCP server
MCP server for Email, Calendar & Contacts — Google, Microsoft 365, Zoho, IMAP/SMTP, CalDAV, CardDAV
Page Lens MCP: API key + npx. Remote board/eval tools plus local capture.
terrarium: disposable VirtualBox VMs from the CLI or over MCP, for you and your AI agent. Bundles the Windows binary.
Python client for a2al: spawn a2ald and call its REST API (health, agents, resolve, fetch, tunnel, …)
UCAI — The ABI-to-MCP Server Generator. Convert smart contract ABIs to AI-ready MCP servers.
Installable MCP bridge for AdaptOrch
An MCP server for Azure DevOps pipelines.
MCP server for security vulnerability scanning and detection
Static code analysis + knowledge-graph for AI coding agents — 12 MCP tools, 13 languages, cut token costs by 87–92 %
Apache AGE MCP Server
MCP工具构建基础库
Failure memory CLI and MCP server for AI coding agents
Local MCP server that saves work-in-progress checkpoints so any AI agent can resume a multi-step plan exactly where a previous session was cut off.
Deterministic evaluation tools for AI coding agents, exposed as an MCP server.
MCP server and library: read/write files, run commands, list files — with strict prompts for user-provided LLMs.
Local MCP server + CLI letting multiple MCP clients (Claude Code, OpenCode, Gemini CLI, …) exchange messages over a shared SQLite bus with audit logging.
Persistent memory and AI briefings for coding agents — drop-in MCP server
strace for AI agents. Capture and replay every tool call, LLM request, and decision point.
Connect AI agents across any network — no public IP needed. P2P encrypted, NAT-traversing, zero-config on LAN.