I’ve been exploring how to share web app bugs with coding agents more effectively. Tools like the Chrome DevTools MCP or Cursor’s browser focus on letting the agent reproduce the issue itself, but often I’ve already found the bug and just need a way to show the agent the exact context.
So we built FlowLens, an open-source MCP server + Chrome extension that captures browser context and lets coding agents inspect it as structured, queryable data.
The extension can:
- record specific workflows, or
- run in a rolling session replay mode that keeps the last ~1 minute of DOM / network / console events in RAM.
If something breaks, you can grab the “instant replay” without reproducing anything.
The extension exports a local .zip file containing the recorded session.
The MCP server loads that file and exposes a set of tools the agent can use to explore it.
One thing we focused on is token efficiency. Instead of dumping raw logs into the context window, the agent starts with a summary (errors, failed requests, timestamps, etc.) and can drill down via tools like:
- search_flow_events_with_regex
- take_flow_screenshot_at_second
It can explore the session the way a developer would: searching, filtering, inspecting specific points in time.
Everything runs locally; the captured data stays on your machine.
So we built FlowLens, an open-source MCP server + Chrome extension that captures browser context and lets coding agents inspect it as structured, queryable data.
The extension can:
- record specific workflows, or
- run in a rolling session replay mode that keeps the last ~1 minute of DOM / network / console events in RAM.
If something breaks, you can grab the “instant replay” without reproducing anything.
The extension exports a local .zip file containing the recorded session.
The MCP server loads that file and exposes a set of tools the agent can use to explore it.
One thing we focused on is token efficiency. Instead of dumping raw logs into the context window, the agent starts with a summary (errors, failed requests, timestamps, etc.) and can drill down via tools like:
- search_flow_events_with_regex
- take_flow_screenshot_at_second
It can explore the session the way a developer would: searching, filtering, inspecting specific points in time.
Everything runs locally; the captured data stays on your machine.
repo: https://github.com/magentic/flowlens-mcp-server