Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-network-analyzer capture network traffic from example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Network Analyzer captures browser network traffic, analyzes API patterns, and exposes the workflow through an MCP server for AI clients.
CLI package (npm) | Issues | Security
Short command: netcap
Full command: mcp-network-analyzer
Capture real browser traffic with Playwright-backed sessions
Discover API endpoints, auth patterns, and request/response shapes
Expose analysis tools through MCP for AI-assisted workflows
Run locally with a focused CLI and straightforward setup
Related MCP server: Kaboom Browser AI Devtools MCP
pnpm add -g mcp-network-analyzer
netcap setup
netcap install
netcap statusFor local development and workspace setup, continue below.
Package | Description | Published |
| npm / GitHub | |
| private | |
| workspace-only |
pnpm install
pnpm build:all
pnpm type-check:allSee packages/cli/README.md for installation and usage.
Quick start:
cd packages/cli
pnpm run build
pnpm link --global
netcap setup
netcap installnetcap is the short alias for mcp-network-analyzer.
See packages/pro/README.md for server deployment.
cd packages/pro
pnpm run setup
pnpm run dev # development mode
pnpm run start # productionpnpm install # link workspace packages
pnpm build:all # build in dependency order
pnpm type-check:all # check types across all packages
pnpm clean:all # remove all dist/ directoriesLocal testing instructions are in docs/TESTING.md.
Public launch checklist is in docs/PUBLIC_RELEASE_STEPS.md.
See CONTRIBUTING.md for development workflow and pull request expectations.
MIT — see LICENSE
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Live browser debugging for AI assistants — DOM, console, network via MCP.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Scrape, crawl and search the web for AI agents via MCP.
A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,
