FlowLens MCP Server
Enables coding agents to access recorded browser flows (user actions, network, console, etc.) for debugging and regression testing without reproducing issues.
README
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 <a href="https://chromewebstore.google.com/detail/jecmhbndeedjenagcngpdmjgomhjgobf?utm_source=github-repo" target="_blank" rel="noopener noreferrer">FlowLens Chrome extension</a> (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
<video src="https://github.com/user-attachments/assets/fd73f2e6-6a7d-4518-b0db-62b8c6e6c99a" autoplay loop muted playsinline></video>
Requirements
- <a href="https://chromewebstore.google.com/detail/jecmhbndeedjenagcngpdmjgomhjgobf?utm_source=github-repo" target="_blank" rel="noopener noreferrer">FlowLens browser extension</a> 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
<details> <summary>Claude Code</summary> Use the Claude Code CLI to add the FlowLens MCP server (<a href="https://docs.anthropic.com/en/docs/claude-code/mcp" target="_blank" rel="noopener noreferrer">guide</a>):
claude mcp add flowlens --transport stdio -- flowlens-mcp-server
</details>
<details> <summary>Cursor</summary>
Click the button to install:
<img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Install in Cursor">
Or install manually:
Go to Cursor Settings -> MCP -> New MCP Server. Use the config provided above.
</details>
<details> <summary>Copilot / VS Code</summary> Follow the MCP install <a href="https://code.visualstudio.com/docs/copilot/chat/mcp-servers#_add-an-mcp-server" target="_blank" rel="noopener noreferrer">guide</a>, 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"}'
</details>
<details> <summary>Codex</summary> Use the Codex CLI to add the FlowLens MCP server <a href="https://github.com/openai/codex/blob/main/docs/advanced.md#model-context-protocol-mcp" target="_blank" rel="noopener noreferrer">configure MCP guide</a>:
codex mcp add flowlens -- flowlens-mcp-server
</details>
<details> <summary>Antigravity</summary> Follow the <a href="https://antigravity.google/docs/mcp" target="_blank" rel="noopener noreferrer">Connecting Custom MCP Servers guide</a>. Add the following config to the MCP servers config:
"flowlens": {
"command": "flowlens-mcp-server"
}
</details>
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 <a href="https://flowlens.magentic.ai/flowlens/setup-wizard?tool=vscode" target="_blank" rel="noopener noreferrer">FlowLens platform</a> 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.