🌉 Bridge

Every message, for everyone.

Bridge is an AI agent that makes Slack workspaces accessible for teammates who are blind, dyslexic, neurodivergent, or working in a second language — automatically, and privately.

Slack · Bolt for JavaScript · Google Gemini · Model Context Protocol · Node.js 18+ · MIT License

Built for the Slack Agent Builder Challenge — Agent for Good track.

💙 The problem

Slack is where work happens — but not equally for everyone. Over 1.3 billion people live with a disability, and millions more work in a second language. Every day, in every workspace:

• A blind teammate hits a wall at every screenshot posted without a description.

• A dyslexic engineer rereads a jargon-dense announcement four times and still isn't sure what to do.

• A teammate working in their third language quietly drops out of a fast-moving thread.

They don't need a separate tool. They need the conversation itself to include them. That's Bridge.

Related MCP server: Gemini MCP Server

✨ What it does

🔒 Privacy by design: simplifications and translations are delivered ephemerally — only the person who asked ever sees them. Nobody is publicly marked as needing an accommodation.

🧠 What makes it an agent, not a chatbot

Bridge's assistant runs an autonomous tool-use loop. You ask one question; Gemini decides which tools to call, in what order, and chains them — no hard-coded paths.

You:  "Find where we decided the launch date and explain it simply in Hindi."

Bridge (thinking, live status shown in Slack):
  → 🔍 search_messages          (Real-Time Search API)
  → 📖 read_channel_history
  → ✍️ simplify_text             (via MCP)
  → 🌍 translate_text            (via MCP)
  → ✅ replies in plain Hindi, with a citation to the original message

🏗️ Architecture

Bridge deliberately uses all three of the challenge's qualifying technologies:

1. ⚡ Slack AI capabilities — a first-class AI assistant: assistant threads, suggested prompts, and live "thinking" status updates.

2. 🔌 MCP server integration — Bridge's accessibility engine (simplify_text, translate_text, describe_image) runs as a standalone MCP server. The Slack agent discovers and calls it as an MCP client at runtime — and because it's standard MCP over stdio, the same server plugs into Claude Desktop, IDEs, or any other MCP client unchanged. Accessibility tools that work beyond Slack.

3. 🔍 Real-Time Search API — assistant.search.context grounds every answer in real workspace messages, so the agent cites sources instead of hallucinating.

All natural-language work — reasoning, vision (alt-text), simplification, translation — is powered by Google Gemini.

🚀 Quick start

Prerequisites: Node.js 18+, a Slack workspace where you can install apps, and a free Google AI Studio API key.

# 1. Clone & install
git clone https://github.com/<you>/bridge.git
cd bridge
npm install

# 2. Configure
cp .env.example .env      # then fill in the 4 values (see below)

# 3. Run
npm start

You should see:

🔌 MCP connected: bridge-accessibility server exposing [simplify_text, translate_text, describe_image]
⚡ Bridge is running (Socket Mode)

Create the Slack app (2 minutes)

1. Go to api.slack.com/apps → Create New App → From a manifest.

2. Pick your workspace and paste the contents of manifest.json. Create.

3. Basic Information → App-Level Tokens → generate a token with the connections:write scope → this is SLACK_APP_TOKEN.

4. Install App → copy the Bot User OAuth Token (SLACK_BOT_TOKEN) and the Signing Secret from Basic Information.

Your .env

SLACK_BOT_TOKEN=xoxb-...
SLACK_APP_TOKEN=xapp-...
SLACK_SIGNING_SECRET=...
GEMINI_API_KEY=...        # from aistudio.google.com/apikey (free tier)

🎮 Try it

🧩 Use the accessibility engine outside Slack

Because the engine is a real MCP server, you can add it to Claude Desktop (or any MCP client) and get the same tools anywhere:

// claude_desktop_config.json
{
  "mcpServers": {
    "bridge-accessibility": {
      "command": "node",
      "args": ["<path-to-repo>/src/mcp-server.js"],
      "env": { "GEMINI_API_KEY": "..." }
    }
  }
}

📁 Project structure

src/
├── app.js          # Slack app — assistant, shortcuts, /bridge, auto alt-text
├── agent.js        # Autonomous tool-use loop (Gemini) + MCP client
├── mcp-server.js   # Bridge Accessibility MCP server (simplify/translate/describe)
├── gemini.js       # Gemini calls, accessibility-tuned prompts
└── prefs.js        # Per-user language preferences
manifest.json       # Paste-ready Slack app configuration
architecture.png    # Architecture diagram

🛠️ Built with

Node.js · Bolt for JavaScript (Socket Mode) · Slack AI assistant threads · Model Context Protocol (server + client) · Real-Time Search API · Google Gemini

🌱 Roadmap

• 🎙️ Voice-note transcription & summarization

• 📖 Per-user reading-level personalization

• 🤟 Sign-language avatar clips for key announcements

• 🏪 One-click install via the Slack Marketplace

📜 License

MIT — free to use, adapt, and build on. Accessibility should be.

Accessibility isn't a feature you add later. With Bridge, it's built into the conversation itself.

🌉 Bridge — every message, for everyone.