
Context Bridge
io.github.prateekg7Published by GitHub account prateekg7v0.1.3Updated Nov 3, 2026
Context portability MCP server for compressing, formatting, and resuming AI conversation handoffs.
Overview
Local MCP server that compresses an AI conversation into a structured context block and reformats it so another assistant can resume the work.
- What you can do
- Compress a raw conversation transcript into a structured context block capturing goal, decisions, state, open threads and next step
- Format a compressed context block for a destination platform such as Claude, ChatGPT or Gemini
- Build a destination-ready landing package from a context block so another assistant can continue
- Choose the inference lane per call: OpenAI, OpenAI chat, Google, Groq, custom or hosted
- When to use it
- Useful when you switch between AI assistants or start a fresh chat and want the goal, decisions and open threads carried over instead of restating everything. Also handy for keeping long conversations compact before handing them off.
- Requirements
- Runs locally over stdio, typically launched with npx from the npm package, so Node.js is needed. Compression needs a model provider: an OpenAI, Google or Groq API key, a custom endpoint, or a hosted endpoint URL. Keys are supplied through environment variables such as OPENAI_API_KEY or CONTEXTBRIDGE_HOSTED_API_KEY, or as per-call parameters. Network access to the chosen provider.
Installation
In SourceWeft
- Open Context Bridge in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
ContextBridge
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):
Or with OpenAI:
For a hosted no-key lane instead of BYOK:
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:
Additional supported provider overrides:
Hosted Lane Setup
The hosted lane is the no-key path for end users who do not bring their own provider credentials.
Environment variables:
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.
Source: README.md at commit 3303d21
Tools
0Version history
1- v0.1.3LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts