Log inSubmit server
Context Bridge logo

Context Bridge

Compresses AI transcripts into structured handoffs and formats them for Claude, ChatGPT, or Gemini.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Context Bridge

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "context-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@contextbridge_ai/mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_VALUE_HERE",
        "OPENAI_MODEL": "YOUR_VALUE_HERE",
        "OPENAI_BASE_URL": "YOUR_VALUE_HERE",
        "GOOGLE_API_KEY": "YOUR_VALUE_HERE",
        "GROQ_API_KEY": "YOUR_VALUE_HERE",
        "CONTEXTBRIDGE_API_KEY": "YOUR_VALUE_HERE",
        "CONTEXTBRIDGE_HOSTED_URL": "YOUR_VALUE_HERE",
        "CONTEXTBRIDGE_HOSTED_MODEL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The context-bridge MCP server compresses ongoing AI conversations into structured handoff blocks that retain goals, decisions, state, open threads, artifacts, constraints, and next steps. It runs as a stdio package through npm and can use OpenAI, Google, Groq, a custom OpenAI-compatible endpoint, or a hosted endpoint. Use it when moving work between AI platforms would otherwise require manually restating the conversation. The server does not publish the repository’s browser extension runtime through this MCP package.

Use cases

  • Compress a long AI transcript into a reusable handoff
  • Move an active task from one AI platform to another
  • Format conversation context for Claude, ChatGPT, or Gemini
  • Resume work without manually restating prior decisions

Key features

  • Transcript compression into structured context blocks
  • Destination formatting for Claude, ChatGPT, and Gemini
  • Landing-package generation for resumed conversations
  • OpenAI, Google, Groq, custom, and hosted inference lanes
  • Stdio delivery through the published npm package

Tools3

What Context Bridge lets your agent do. Expand a tool for its parameters.

Self-reported~61 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

5/5 checks healthy over the last 46d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · @contextbridge_ai/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads159Package downloads in the last 30 days.
Last commit5mo agoMost recent push to the default branch.
Tools exposed3Callable tools this server registers over MCP.

How Context Bridge works

What context-bridge does

The context-bridge MCP server turns a raw conversation transcript into a structured context block for continuation elsewhere. The block is intended to preserve the parts of a working session that a second AI needs: the user’s objective, decisions already confirmed, current progress, unresolved topics, referenced artifacts, constraints, recent changes in direction, and a suggested next action.

After compression, the server can adapt that block for Claude, ChatGPT, or Gemini. It can also create a landing package designed to help the destination model resume the work without requiring the user to repeat the original discussion.

The published package is the stdio MCP server distributed through npm as @contextbridge_ai/mcp. The browser extension is maintained in the same repository but is not included in this MCP Registry publishing path.

How it works

The server exposes three MCP tools:

  • compress_context accepts a required transcript and produces a validated structured context block. Optional arguments can select a provider, model, API key, base URL, or hosted-lane key.
  • format_for_target accepts a context block and a required destination of claude, chatgpt, or gemini, then formats the handoff for that platform.
  • resume_context accepts the same kind of context block and destination, then creates a destination-ready landing package.

Compression can use an OpenAI Responses lane, Google, Groq, a custom provider, or a hosted endpoint. Provider selection can be supplied to the tool, while environment variables provide defaults. The documented priority uses an explicit compression key first, then OPENAI_API_KEY, then the hosted URL configuration.

The context-bridge MCP server communicates through stdio, so an MCP host starts it as a local process.

Setup and configuration

Install the package through an MCP client configuration and provide one supported inference route. An OpenAI setup can define OPENAI_API_KEY, OPENAI_MODEL, and OPENAI_BASE_URL. Google, Groq, and custom OpenAI-compatible endpoints have corresponding provider settings. The hosted route uses CONTEXTBRIDGE_HOSTED_URL and CONTEXTBRIDGE_HOSTED_MODEL, with an optional CONTEXTBRIDGE_HOSTED_API_KEY.

The tool arguments can override provider, model, API key, and base URL for an individual compression request. A hosted configuration is intended as a no-key path for users who do not supply their own provider credentials, although the hosted endpoint itself may optionally require an authentication key.

The project is licensed under MIT. The README provides no claim that transcripts are stored, encrypted, or processed locally; operators should evaluate the selected provider or hosted endpoint before sending conversation content.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Context Bridge

context-bridge is an MCP server that connects AI conversation transcripts to structured handoff workflows. Its main tools compress raw transcripts, format validated context blocks for Claude, ChatGPT, or Gemini, and build destination-ready packages so another AI can continue without requiring the user to restate the prior conversation.

Install it by adding `npx -y @contextbridge_ai/mcp` as the command and argument in your MCP client configuration. Claude Desktop uses a `contextbridge` server entry and an environment variable for an OpenAI, Groq, or hosted inference route.

context-bridge supports OpenAI, Google, Groq, custom OpenAI-compatible endpoints, and a hosted endpoint. Provider selection can be configured with environment variables or overridden in `compress_context` using its provider, model, API key, and base URL arguments.

context-bridge formats handoffs for Claude, ChatGPT, and Gemini. Both `format_for_target` and `resume_context` require a validated context block and one of those three destination values.

It describes the package as a stdio MCP server for Claude Desktop, agent runtimes, and other MCP-compatible hosts, so Cursor compatibility depends on its support for this server configuration.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewContext Bridge AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/context-bridge?style=directory)](https://allmcps.com/mcp/context-bridge)
HTML Embed
<a href="https://allmcps.com/mcp/context-bridge"><img src="https://allmcps.com/api/badge/context-bridge?style=directory" alt="Context Bridge on AllMCPs" /></a>