What is Minibridge?
Minibridge is a security layer that integrates with ARC to secure agent‑to‑MCP interactions. It performs integrity checks, blocks hidden‑prompt phrases, detects tool‑shadowing, and redacts credentials in outbound content.
@acuvity
基本信息
Repository holding sources for all mcp-servers managed by Acuvity
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
ARC (Acuvity Runtime Container) is a secure, streamlined Docker runtime designed specifically for hosting MCP servers. It provides isolated execution, built-in runtime protection via Minibridge, and simplified remote connectivity, making it ideal for deploying agentic systems in enterprise environments.
Add your MCP server to ARC by opening a GitHub issue with the source link and runtime configuration. Acuvity handles secure containerization, Minibridge integration, SBOM validation, and remote support. Deployment can be done via Docker or Kubernetes with Helm charts.
Minibridge is a security layer that integrates with ARC to secure agent‑to‑MCP interactions. It performs integrity checks, blocks hidden‑prompt phrases, detects tool‑shadowing, and redacts credentials in outbound content.
ARC enforces least‑privilege with non‑root users, uses a read‑only filesystem, pins container versions, and automatically validates SBOMs to prevent compromised deployments.
Minibridge handles HTTP/SSE, WebSockets, and other protocols natively, providing built‑in remote connectivity without custom configuration.
You contribute by opening a GitHub issue using the provided template, including your app’s source link and runtime environment variables or CLI arguments. Acuvity then handles secure containerization and integration.
No, ARC works independently. Some advanced features like full policy management, authorization controls, and deep multimodal analysis are available only with the Acuvity Platform.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Model Context Protocol Servers
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
MCP Toolbox for Databases is an open source MCP server for databases.
评论