Sandbox
12 repos for tool-call · Cursor · CodingClear
LuD1161/
agentjail

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

92

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

411
VasiHemanth/
tokentelemetry

Token telemetry dashboard for AI autonomous and coding agents — tracks tokens, sessions, tool calls & reasoning across Hermes agent, Claude Code, Antigravity CLI, Codex & more. 100% local.

346
ddalcu/
mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

1.2k

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

3.7k

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

342
tathagat22/
plumb-mcp

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf — works on every plan including Free.

78

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

1.5k
MCP-Defender/
MCP-Defender

Desktop app that automatically scans and blocks malicious MCP traffic in AI apps like Cursor, Claude, VS Code and Windsurf.

257
SponsioLabs/SponsioFrameworks & SDKs

Deterministic safety solutions for probabilistic AI agents

440

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM.

209
DIDA-AI/
Dida-Hotel-MCP-Global

Official DIDA Hotel Booking MCP Server. 14-year travel tech data stack, 2M+ hotels at wholesale rates, 40+ LLM compatible. Free unlimited calls for businesses & individual devs. Filter by location, date, star grade, guests & tags; pull real-time room types, pricing & cancellation rules.

81