FlowLens MCP

flowlens-mcp-server gives your coding agent (Claude Code, Cursor, Copilot, Codex) full browser context for in-depth debugging and regression testing.

How it works

• Record your browser flow using the FlowLens Chrome extension (user actions, network, console, storage, DOM events/screen recording).
• Share it with your coding agent via the FlowLens MCP server, giving the agent full access to the recording.
• Your agent inspects and analyzes the flow for debugging and insights — without spending time/tokens on reproducing the issue.

Demo

flowlens-roboshop-claude.mp4

Requirements

• FlowLens browser extension add to chrome and pin for ease of use
• pipx

Getting Started

To install:

pipx install flowlens-mcp-server

To upgrade to the latest version:

pipx upgrade flowlens-mcp-server

To check that the installation was successfully:

flowlens-mcp-server

Add FlowLens MCP server

Add the following config to your MCP client (ex: ~/.claude.json) under mcpServers:

"flowlens": {
  "command": "flowlens-mcp-server",
  "type": "stdio"
}

MCP Client configuration

Claude Code

Use the Claude Code CLI to add the FlowLens MCP server (guide):

claude mcp add flowlens --transport stdio -- flowlens-mcp-server

Cursor

Click the button to install:

Or install manually:

Go to Cursor Settings -> MCP -> New MCP Server. Use the config provided above.

Copilot / VS Code

Follow the MCP install guide, with the standard config from above. You can also install the FlowLens MCP server using the VS Code CLI:

code --add-mcp '{"name":"flowlens","command":"flowlens-mcp-server"}'

Codex

Use the Codex CLI to add the FlowLens MCP server configure MCP guide:

codex mcp add flowlens -- flowlens-mcp-server

Antigravity

Follow the Connecting Custom MCP Servers guide. Add the following config to the MCP servers config:

"flowlens": {
  "command": "flowlens-mcp-server"
}

Note:

The above setup only works with local flows. If you want to also connect to shareable flows, get your FLOWLENS_MCP_TOKEN from the FlowLens platform and add it to your relevant MCP config file:

"flowlens": {
  "command": "flowlens-mcp-server",
  "type": "stdio",
  "env": {
    "FLOWLENS_MCP_TOKEN": "YOUR_FLOWLENS_MCP_TOKEN"
  }
}

Usecases:

Bug reporting

• Use FlowLens to quickly report bugs with full context to your coding agent. You no longer need to copy-paste console logs, take multiple screenshots, or have the agent spend tokens on reproducing the issue.

Regression testing

• Use FlowLens to record your crticial user flows and ask your coding agent to auto test these flows or generate corresponding playwright test scripts

Shareable flows

• Share captured flows with your teammates on the FlowLens platform and debug with your coding agent by adding a generated access token in the MCP config. More on this here