Minibridge

Created By
verifiableba year ago
Make your MPC servers secure and production ready acuvity, mcp, mcp-gateway, mcp-server, modelcontextprotocol, mtls, security
Overview

what is Minibridge?

Minibridge is a backend-to-frontend bridge that secures and streamlines communication between Agents and Model Context Protocol (MCP) servers, ensuring safe exposure of MCP servers to the internet.

how to use Minibridge?

To use Minibridge, you can start it as a single process or as separate backend and frontend components. For example, to start everything as a single process, run: minibridge aio --listen :8000 -- npx @modelcontextprotocol/server-filesystem /tmp. You can also connect using HTTP clients or WebSocket clients depending on your setup.

key features of Minibridge?

  • Secure communication between agents and MCP servers.
  • Integration with Policers for agent authentication and content analysis.
  • SBOM (Software Bill of Materials) generation for integrity checks.
  • Support for both HTTP and WebSocket protocols.

use cases of Minibridge?

  1. Securing MCP servers for public access.
  2. Authenticating agents through various Policers.
  3. Validating the integrity of MCP servers using SBOM.

FAQ from Minibridge?

  • Can Minibridge secure any MCP server?

Yes! Minibridge is designed to work with any MCP server, providing a secure communication layer.

  • Is Minibridge easy to set up?

Yes! Minibridge can be set up quickly using command-line instructions provided in the documentation.

  • What is a Policers?

Policers are services that can be integrated with Minibridge to handle authentication, authorization, and request analysis.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
verifiableb
Star
0
Language
Go
License
Apache-2.0 license

Recommend Servers

View All
Payai X402 Tools

8 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago