Minibridge

Created By
acuvitya year ago
Make your MPC servers secure and production ready
Overview

What is Minibridge?

Minibridge is a tool that acts as a bridge between Model Context Protocol (MCP) servers and external clients, facilitating secure communication and integration with the Acuvity Platform.

How to use Minibridge?

To use Minibridge, you can start it in various modes: as an all-in-one process, backend, or frontend. For example, to start everything as a single process, run: minibridge aio --listen :8000 -- npx -y @modelcontextprotocol/server-filesystem /tmp.

Key features of Minibridge?

  • Acts as a secure gateway for MCP servers.
  • Supports WebSocket-based communication.
  • Integrates with a Policer for advanced user authentication and authorization.
  • Maintains compatibility with future MCP protocol changes.

Use cases of Minibridge?

  1. Connecting agents to MCP servers securely.
  2. Facilitating data streams between backend and frontend applications.
  3. Enabling role-based access control through Policer integration.

FAQ from Minibridge?

  • Is Minibridge compatible with all MCP servers?

Yes, it is compatible with any compliant MCP server using protocol version 2024-11-05, with support for version 2025-03-26 in progress.

  • How does Minibridge ensure security?

Minibridge can be configured with TLS and client certificates to secure communications.

  • What is the current status of Minibridge?

Minibridge is still under active development, and several features are planned for future releases.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
acuvity
Star
26
Language
Go
License
Apache-2.0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago