ContextBridge MCP server
✓ VerifiedCompresses, formats, and resumes AI conversation handoffs to preserve context across different AI platforms.
Also known as prateekg7/Context-Bridge, @contextbridge_ai/mcp
- Stars
- 3
- Tools
- 8
- Downloads, 30 days
- 222
- Latest version
- 0.1.3
- Last commit
- May 12, 2026
- License
- MIT
What is ContextBridge MCP?
ContextBridge is an MCP server. Compresses, formats, and resumes AI conversation handoffs to preserve context across different AI platforms. It exposes 8 tools, such as transcript, provider, model.
Summary generated from the project's README
About ContextBridge MCP server
Moving an active AI conversation from one platform to another without repeating yourself is what context-bridge enables. This tool allows developers and users to compress raw transcripts into structured blocks that capture goals, decisions, current states, and constraints. By preserving these details, you can hand off a session to a different model without losing progress or context.
Running as a stdio MCP server, it integrates with Claude Desktop and other agent runtimes. Users can set it up using a Bring Your Own Key approach with providers like OpenAI, Google, or Groq, or use a hosted lane via a specific URL. The server provides three primary tools: compress_context for turning transcripts into structured data, format_for_target for preparing that data for a specific destination, and resume_context to build a complete landing package for the new AI platform.
What you can do with it
- 1Transferring session progressCompress a long chat transcript into a structured block to move it to a different AI.
- 2Preparing platform-specific handoffsFormat a compressed context block specifically for use in ChatGPT or Gemini.
- 3Resuming work in new environmentsCreate a landing package that allows a new AI to pick up exactly where the previous one left off.
Written from the project's README. Every use case is checked against a quote from it.
How to install ContextBridge MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ContextBridge MCP in Claude Code
$ claude mcp add --env 'CONTEXTBRIDGE_HOSTED_API_KEY=<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>' --env 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' context-bridge -- npx -y @contextbridge_ai/mcpInstall ContextBridge MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"context-bridge": {
"command": "npx",
"args": [
"-y",
"@contextbridge_ai/mcp"
],
"env": {
"CONTEXTBRIDGE_HOSTED_API_KEY": "<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Install ContextBridge MCP in VS Code
.vscode/mcp.json
{
"servers": {
"context-bridge": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@contextbridge_ai/mcp"
],
"env": {
"CONTEXTBRIDGE_HOSTED_API_KEY": "<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Install ContextBridge MCP in VS Code CLI
$ code --add-mcp '{"name":"context-bridge","type":"stdio","command":"npx","args":["-y","@contextbridge_ai/mcp"],"env":{"CONTEXTBRIDGE_HOSTED_API_KEY":"<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>","OPENAI_API_KEY":"<YOUR_OPENAI_API_KEY>"}}'Install ContextBridge MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"context-bridge": {
"command": "npx",
"args": [
"-y",
"@contextbridge_ai/mcp"
],
"env": {
"CONTEXTBRIDGE_HOSTED_API_KEY": "<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Install ContextBridge MCP in Codex
$ codex mcp add context-bridge --env 'CONTEXTBRIDGE_HOSTED_API_KEY=<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>' --env 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' -- npx -y @contextbridge_ai/mcpInstall ContextBridge MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.context-bridge] command = "npx" args = ["-y", "@contextbridge_ai/mcp"] [mcp_servers.context-bridge.env] CONTEXTBRIDGE_HOSTED_API_KEY = "<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>" OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"
Install ContextBridge MCP in Gemini CLI
$ gemini mcp add -s user -e 'CONTEXTBRIDGE_HOSTED_API_KEY=<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>' -e 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' context-bridge npx -- -y @contextbridge_ai/mcpInstall ContextBridge MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"context-bridge": {
"command": "npx",
"args": [
"-y",
"@contextbridge_ai/mcp"
],
"env": {
"CONTEXTBRIDGE_HOSTED_API_KEY": "<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}ContextBridge MCP tools 8
Detected from the READMEtranscriptprovidermodelapiKeybaseUrlhostedApiKeycontext_blocktarget
Configuration
CONTEXTBRIDGE_HOSTED_API_KEYSecretOptional auth key for the hosted inference endpoint.
OPENAI_API_KEYSecretOptional BYOK API key for the OpenAI Responses or chat-completions lane.
CONTEXTBRIDGE_API_KEYCONTEXTBRIDGE_BASE_URLCONTEXTBRIDGE_HOSTED_MODELOptional hosted model identifier override.
CONTEXTBRIDGE_HOSTED_URLOptional hosted inference endpoint for the no-key lane.
CONTEXTBRIDGE_MODELCONTEXTBRIDGE_PROVIDERGOOGLE_API_KEYGOOGLE_BASE_URLGOOGLE_MODELGROQ_API_KEYGROQ_BASE_URLGROQ_MODELOPENAI_BASE_URLOPENAI_MODELOptional model override for the OpenAI BYOK lane.
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableprateekg7/context-bridge is public and reachablegithub.com/prateekg7/context-bridge ↗Pass
- Package names this repository as its source@contextbridge_ai/mcp names prateekg7/context-bridge as sourcenpmjs.com/package/@contextbridge_ai/mcp ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-05-12github.com/prateekg7/context-bridge ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @contextbridge_ai/mcpPass
- No critical advisory in the package or its dependencies100 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model8 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubContextBridge
ContextBridge is a context portability tool for AI conversations. This package publishes the MCP server surface: it compresses an in-progress conversation into a structured context block that preserves the user's goal, confirmed decisions, current state, open threads, artifacts, constraints, recent pivots, and suggested next step, then formats that handoff so another AI can continue without forcing the user to restate everything.
The published npm artifact is the stdio MCP server for Claude Desktop, agent runtimes, and other MCP-compatible hosts. The browser extension runtime is developed in the same repository, but it is not part of this MCP Registry publishing flow.
Published Links
- npm package: @contextbridge_ai/mcp
- MCP Registry search: io.github.prateekg7/context-bridge
- MCP Registry API: latest version JSON
- Source repository: prateekg7/Context-Bridge
Install In Claude Desktop
Add this to your Claude Desktop MCP config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"contextbridge": {
"command": "npx",
"args": ["-y", "@contextbridge_ai/mcp"],
"env": {
"GROQ_API_KEY": "your_groq_api_key_here"
}
}
}
}
Or with OpenAI:
{
"mcpServers": {
"contextbridge": {
"command": "npx",
"args": ["-y", "@contextbridge_ai/mcp"],
"env": {
"OPENAI_API_KEY": "your_openai_api_key_here",
"OPENAI_MODEL": "gpt-4.1-mini"
}
}
}
}
For a hosted no-key lane instead of BYOK:
{
"mcpServers": {
"contextbridge": {
"command": "npx",
"args": ["-y", "@contextbridge_ai/mcp"],
"env": {
"CONTEXTBRIDGE_HOSTED_URL": "https://your-hosted-endpoint.example/v1",
"CONTEXTBRIDGE_HOSTED_MODEL": "mistralai/Mistral-7B-Instruct-v0.2"
}
}
}
}
Available MCP Tools
compress_context
Compresses a raw transcript into a structured context block.
Parameters:
transcript(string, required): the raw conversation transcript to compress.provider("openai" | "openai-chat" | "google" | "groq" | "custom" | "hosted", optional): provider override.model(string, optional): model override for the selected lane.apiKey(string, optional): BYOK API key override.baseUrl(string, optional): API base URL override.hostedApiKey(string, optional): optional auth key for the hosted lane.
format_for_target
Formats a compressed context block for a destination platform.
Parameters:
context_block(object, required): a validated ContextBridge compressed context block.target("claude" | "chatgpt" | "gemini", required): destination AI platform.
resume_context
Builds a destination-ready landing package from a compressed context block.
Parameters:
context_block(object, required): a validated ContextBridge compressed context block.target("claude" | "chatgpt" | "gemini", required): destination AI platform.
BYOK Setup
ContextBridge auto-selects the OpenAI Responses lane when a BYOK key is present.
Environment variables:
OPENAI_API_KEY=your_openai_api_key_here
OPENAI_MODEL=gpt-4.1-mini
OPENAI_BASE_URL=https://api.openai.com/v1
Additional supported provider overrides:
GOOGLE_API_KEY=your_google_api_key_here
GOOGLE_MODEL=gemini-2.5-pro
GOOGLE_BASE_URL=https://generativelanguage.googleapis.com/v1beta/openai
GROQ_API_KEY=your_groq_api_key_here
GROQ_MODEL=llama-3.3-70b-versatile
GROQ_BASE_URL=https://api.groq.com/openai/v1
CONTEXTBRIDGE_API_KEY=your_custom_api_key_here
CONTEXTBRIDGE_MODEL=your_custom_model_here
CONTEXTBRIDGE_BASE_URL=https://your-endpoint.example/v1
CONTEXTBRIDGE_PROVIDER=custom
Hosted Lane Setup
The hosted lane is the no-key path for end users who do not bring their own provider credentials.
Environment variables:
CONTEXTBRIDGE_HOSTED_URL=https://your-hosted-endpoint.example/v1
CONTEXTBRIDGE_HOSTED_MODEL=mistralai/Mistral-7B-Instruct-v0.2
CONTEXTBRIDGE_HOSTED_API_KEY=
Selection priority:
- Explicit
apiKeyoption passed into compression uses the OpenAI Responses BYOK lane. OPENAI_API_KEYuses the OpenAI Responses BYOK lane.CONTEXTBRIDGE_HOSTED_URLuses the hosted lane.
Contributing
Contributions are welcome. The highest-leverage areas are extraction quality evaluation, browser collector resilience, destination formatting quality, hosted-lane infrastructure, and real-world handoff testing across platforms.
License
MIT. See LICENSE.
ContextBridge MCP questions
How do I add ContextBridge MCP to Claude Code?
Run claude mcp add --env 'CONTEXTBRIDGE_HOSTED_API_KEY=<YOUR_CONTEXTBRIDGE_HOSTED_API_KEY>' --env 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' context-bridge -- npx -y @contextbridge_ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add ContextBridge MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does ContextBridge MCP provide?
It exposes 8 tools, including transcript, provider, model, apiKey, baseUrl.
What does ContextBridge do?
It compresses in-progress conversations into structured context blocks that preserve goals, decisions, state, and constraints for handoffs to other AI models.
How do I install it in Claude Desktop?
You can install it by adding the server configuration to your claude_desktop_config.json file using npx and providing the necessary environment variables.
Can I use it without providing my own API keys?
Yes, you can use a hosted lane by providing a CONTEXTBRIDGE_HOSTED_URL instead of bringing your own provider credentials.
Which AI platforms can I format context for?
The tool supports formatting and resuming context for Claude, ChatGPT, and Gemini.