Development tooling MCP server with process management, proxy, and frontend diagnostics
A Model Context Protocol (MCP) server for development tooling, providing process management, proxy capabilities, and frontend diagnostics. It exposes MCP-enabled endpoints to coordinate model contexts, run tooling processes, and surface real-time frontend health checks.
π οΈ Key Features
Process management for development tooling
MCP-compatible interface for model context coordination
Built-in proxy support
Frontend diagnostics exposure
π Use Cases
Manage AI-assisted development workflows with centralized MCP communication
Route and inspect model context data through a proxy layer
Monitor frontend health and diagnostics in MCP-enabled environments
β‘ Developer Benefits
Standard MCP protocol integration for tooling
Clear separation of process management, proxying, and diagnostics
Grounded in a concise readme excerpt for quick onboarding
β οΈ Limitations
Limited source material; further feature specifics may require direct repository reference
agnt is a new kind of tool designed for the age of AI-assisted development. It acts as a bridge between your AI coding agent and the browser, extending what's possible during vibe coding sessions.
When you're in the flow with Claude Code, Cursor, or other AI coding tools, agnt lets your agent:
See what you see - Screenshots, DOM inspection, and visual debugging
Hear from you directly - Send messages from the browser to your agent
Sketch ideas together - Draw wireframes directly on your UI
Debug in real-time - Capture errors, network traffic, and performance metrics
Test on any device - Tunnel to phones and BrowserStack with full instrumentation
Extend its thinking window - Structured data uses fewer tokens than your descriptions
Demo
Three rounds of blind terminal automation can't fix a button that's half off-screen. One pass with eyes on the live page can β full demo (1:40).
Sketch Demo
Draw wireframes directly on your running app, then send them to your AI agent
The Vision: Extending Your Agent's Capabilities
Traditional AI coding assistants are blind to what's happening in the browser. They can write code, but they can't:
See the visual result of their changes
Know when JavaScript errors occur
Understand layout issues you're experiencing
Receive feedback without you typing it out
agnt changes this. It creates a bidirectional channel between your browser and your AI agent:
One-shot: agnt skills β install the agnt agent skills and register the
MCP server in a single command. It uses Vercel's open skills CLI
to fetch the skills, then wires up MCP:
bash
agnt skills # install for Claude Code + register the MCP server
agnt skills --agent cursor # install the skills for a different agent
Under the hood it runs npx -y skills add standardbeagle-tools/agnt --all -a claude-code, then claude mcp add agnt -s user -- agnt mcp (for other agents
it prints the MCP config to add). Requires Node.js (npx) on PATH.
As PTY Wrapper (Enhanced Terminal)
Wrap your AI tool for overlay features:
bash
agnt run claude --dangerously-skip-permissions
agnt run cursor
agnt run aider
This adds a terminal overlay menu (Ctrl+P) and enables the browser-to-terminal message bridge.
First-Run Setup (auto-configures a new project)
The first time you run agnt run claude in a project that has no .agnt.kdl,
agnt drives a one-time setup run before your coding session:
bash
cd my-new-project # no .agnt.kdl yet
agnt run claude
What happens:
Setup phase β Claude launches in setup mode and configures the project:
it detects the stack (Go / Node / Python / β¦), registers your dev-server
script(s) and a reverse proxy, and writes a .agnt.kdl. If the
agnt:setup-project skill isn't installed, Claude tells you the exact
install step (/plugin marketplace add standardbeagle/agnt then
/plugin install agnt).
Relaunch β when setup exits, agnt relaunches Claude into a normal coding
session with autostart enabled, replaying your original arguments. Your dev
servers and proxy come up automatically.
bash
# Pass a task through β it's replayed verbatim into the relaunched session:
agnt run claude -- "add a /healthz endpoint"
If you decline setup (no .agnt.kdl gets written), agnt records a timestamped
marker and won't nudge again until the re-nudge window elapses (default 7 days,
configurable via setup { renudge-ttl-days 7 } in .agnt.kdl). A successful
setup is remembered permanently.
Setup also works for other agents β each gets install instructions tailored to
its own skill/command mechanism (see
docs/agent-support-matrix.md).
agnt init β configure without launching a session
Prefer to set the project up on its own? agnt init runs only the setup phase
(no relaunch) and exits once .agnt.kdl is written:
bash
agnt init # configure with claude
agnt init gemini # configure with a different agent
A successful agnt init records the permanent marker too, so a later
agnt run skips straight to the coding session.
Channel Mode (Beta β Claude Code only)
Beta / Experimental: Channel mode requires a forked MCP SDK and a development flag in Claude Code. Behavior and schema may change.
Claude Code v2.1.80+ can receive real-time browser errors, diagnostics, and user interactions as push events in context -- without the PTY wrapper. Add channel { enabled true } to .agnt.kdl and launch with claude --dangerously-load-development-channels server:agnt. See the Channel Mode section in CLAUDE.md for full schema, event format, and the channel_reply tool for sending messages back to the browser overlay.
Core Features
1. Browser Superpowers
Start a proxy and your agent gains eyes into the browser:
Tunnel management: cloudflare/ngrok for mobile testing
daemon
Manage background daemon service
watch
Stream daemon events via agnt monitor
channel_reply
Send messages to developer's browser overlay (channel mode only)
Browser API (50+ Functions)
The proxy injects window.__devtool with powerful diagnostics:
Element Inspection
javascript
__devtool.inspect('#element') // Full element analysis
__devtool.getPosition('#element') // Bounding box and position
__devtool.isVisible('#element') // Visibility check
Visual Debugging
javascript
__devtool.highlight('.items') // Highlight elements
__devtool.mutations.highlightRecent() // Show recent DOM changes
__devtool.screenshot('name') // Capture screenshot
Accessibility
javascript
__devtool.auditAccessibility() // Full a11y audit with score
__devtool.getContrast('#text') // Color contrast check
__devtool.getTabOrder() // Tab navigation order
Interactions
javascript
__devtool.interactions.getLastClick() // Last click details
__devtool.interactions.getLastClickContext() // Full click context
__devtool.selectElement() // Interactive picker
Sketch Mode
javascript
__devtool.sketch.open() // Enter sketch mode
__devtool.sketch.save() // Save and send to agent
__devtool.sketch.toJSON() // Export sketch data
Responsive Mode
javascript
__devtool.responsive.open() // Open the interactive width workbench
__devtool.responsive.setWidth(414) // Drive the frame to a width (320β1920)
__devtool.responsive.getState() // Read current width + detected layout shifts