Cette page est affichée en anglais. Une traduction française est en cours.
MCP ConfigsMay 12, 2026·3 min de lecture

mcp-bridgekit — MCP stdio-to-HTTP Bridge + Dashboard

Expose any MCP stdio server as HTTP endpoints for web apps, with per-user session pooling and background jobs to survive 30s timeouts (Vercel/Cloudflare).

MCP Hub
MCP Hub · Community
Prêt pour agents

Cet actif peut être lu et installé directement par les agents

TokRepo expose une commande CLI universelle, un contrat d'installation, le metadata JSON, un plan selon l'adaptateur et le contenu raw pour aider les agents à juger l'adaptation, le risque et les prochaines actions.

Native · 94/100Policy : autoriser
Surface agent
Tout agent MCP/CLI
Type
Mcp
Installation
Docker
Confiance
Confiance : Established
Point d'entrée
docker run -d -p 8000:8000 mcp-bridgekit
Commande CLI universelle
npx tokrepo install db3b874d-1ff7-591b-ba3f-d025d44c25f2
Introduction

MCP BridgeKit solves the stdio/HTTP mismatch: it runs MCP servers as subprocesses and makes them callable from browsers and web backends, while providing a live dashboard for sessions and jobs.

Best for: Web chatbots that need MCP tools, multi-tenant tool access, and long-running tool calls

Works with: Python 3.11+; Redis for jobs/sessions (README mentions Redis); deployable to Vercel

Setup time: 20–40 minutes

Key facts (verified)

  • README table cites 30s gateway timeouts (Vercel/Cloudflare) and uses background jobs to handle slow tool calls.
  • Supports session pooling and notes “up to 100 concurrent” sessions in README problem table.
  • GitHub: 60 stars · 14 forks; pushed 2026-02-23 (GitHub API verified).

Main

If you’re turning MCP tools into a product surface, BridgeKit helps with three hard parts:

  • Isolation: run per-user sessions so one customer’s tool state can’t bleed into another’s.
  • Timeouts: turn slow calls into queued jobs; return a job id and let the client poll/stream status.
  • Ops: use the dashboard to observe active sessions, job backlog, and tool inventory during incidents.

README excerpt (verbatim)

MCP BridgeKit

Embeddable MCP stdio → HTTP bridge for web chatbots.

Turn any MCP stdio server into HTTP endpoints your web app can call. Per-user session pooling, real timeout handling with background job fallback, live dashboard.

Version MIT Python

Deploy with Vercel


Table of Contents


What Is MCP BridgeKit?

MCP (Model Context Protocol) is an open standard that lets AI applications connect to external tools and data sources. MCP servers communicate over stdio (stdin/stdout) — which means they run as local subprocesses and speak JSON-RPC over pipes.

The problem: Web applications (React, Next.js, Vue, mobile apps) can't spawn local subprocesses. They only speak HTTP. There's a protocol mismatch.

MCP BridgeKit is the bridge. It sits between your web app and MCP stdio servers, translating HTTP requests into stdio subprocess calls and streaming results back:

Your Web App  ──HTTP──▶  MCP BridgeKit  ──stdio──▶  MCP Server (tool)
                         (this project)

FAQ

Q: Why not call MCP tools directly from the browser? A: Browsers can’t spawn stdio subprocesses; BridgeKit bridges HTTP ↔ stdio.

Q: What about slow tools? A: README describes background-job fallback to avoid 30s gateway timeouts.

Q: How do I discover tools? A: README mentions a live GET /tools/{user_id} endpoint for discovery.

🙏

Source et remerciements

Source: https://github.com/mkbhardwas12/mcp-bridgekit > License: MIT > GitHub stars: 60 · forks: 14

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires