Skip to main content
Glama

Ein einzelnes scout-Binary bietet Ihnen ein vollständiges CLI, einen MCP-Server mit 66 Tools und eine Go-Bibliothek mit Gin-ähnlicher Middleware-Komposition.

brew install felixgeelhaar/tap/scout

Schnelleinstieg

# CLI — visible browser, one-shot commands
scout observe https://example.com          # structured page snapshot
scout markdown https://news.ycombinator.com # page as compact markdown
scout screenshot https://github.com         # save screenshot
scout extract https://example.com h1        # extract element text
scout frameworks https://react.dev          # detect React, Vue, etc.

# MCP Server — give AI agents browser superpowers
claude mcp add scout -- scout mcp serve

# Browser UI — conversational browser automation
scout ui serve --provider=ollama --model=mistral
cd ui && npm install && npm run dev  # open http://localhost:3000

Related MCP server: Browser-MCP Navigator

Installation

# Homebrew
brew install felixgeelhaar/tap/scout

# Direct binary
curl -fsSL https://raw.githubusercontent.com/felixgeelhaar/scout/main/install.sh | bash

# Go
go install github.com/felixgeelhaar/scout/cmd/scout@latest

# As a library
go get github.com/felixgeelhaar/scout

MCP-Server — 66 Tools

Einzelnes Binary, keine Laufzeitabhängigkeiten. Konfiguration in jedem MCP-Client:

claude mcp add scout -- scout mcp serve           # Claude Code
{"mcpServers": {"scout": {"command": "scout", "args": ["mcp", "serve"]}}}

Tool-Kategorien

Kategorie

Tools

Navigation

navigate, observe, observe_diff, observe_with_budget

Interaktion

click, click_label, type, hover, double_click, right_click, select_option, scroll_to, scroll_by, focus, drag_drop, dispatch_event

Formulare

fill_form, fill_form_semantic, discover_form

Extraktion

extract, extract_all, extract_table, auto_extract, scroll_and_collect, markdown, readable_text, accessibility_tree

Erfassung

screenshot, annotated_screenshot, pdf

Netzwerk

enable_network_capture, network_requests

Tabs

open_tab, switch_tab, close_tab, list_tabs

Frameworks

wait_spa, detect_frameworks, component_state, app_state

Wiedergabe

start_recording, stop_recording, save_playbook, replay_playbook

Intelligente Helfer

dismiss_cookies, check_readiness, suggest_selectors, session_history

Vision

hybrid_observe, find_by_coordinates

Batch

execute_batch

Iframe

switch_to_frame, switch_to_main_frame

Trace

start_trace, stop_trace

Diagnose

detect_dialog, detect_auth_wall, console_errors, compare_tabs, upload_file

Dienstprogramme

has_element, wait_for, configure, web_vitals, select_by_prompt

Alle Tools verfügen über MCP-Annotationen (ReadOnly, OpenWorld, ClosedWorld, Idempotent) für eine intelligente automatische Genehmigung. Schreibgeschützte Tools wie observe, extract und screenshot werden ohne Berechtigungsabfragen ausgeführt.

Laufzeitkonfiguration

Wechseln Sie zwischen Headless- und sichtbarem Browser, ohne neu zu starten:

Agent: configure(headless: false)   → browser window appears
Agent: navigate("https://...")       → watch it work
Agent: configure(headless: true)     → back to headless

Browser-UI

Eine konversationelle Benutzeroberfläche für Browser-Automatisierung. Geben Sie natürliche Sprache ein und beobachten Sie, wie der Browser in Echtzeit reagiert.

# Start the AG-UI server (Go backend)
scout ui serve --provider=ollama --model=mistral    # local, no API key
scout ui serve --provider=claude                     # needs ANTHROPIC_API_KEY
scout ui serve --provider=openai --model=gpt-4o     # needs OPENAI_API_KEY
scout ui serve --provider=groq --base-url=https://api.groq.com/openai --model=llama-3.3-70b-versatile

# Start the Vue frontend
cd ui && npm install && npm run dev                  # http://localhost:3000

Die UI streamt AG-UI-Protokollereignisse über SSE:

  • Chat-Panel mit Markdown-Rendering und Quick-Action-Pills

  • Live-Browser-Viewport mit Screenshot-Streaming und URL-Leiste

  • Aktivitäts-Timeline, die Tool-Aufrufe in Echtzeit anzeigt

  • Stopp-Taste, um den Stream mitten im Prozess abzubrechen

Der Go-Server übernimmt die Agenten-Schleife: Das LLM entscheidet, welche Scout-Tools aufgerufen werden sollen, führt sie aus und streamt Browser-Status-Deltas zurück an das Frontend. Unterstützt jeden OpenAI-kompatiblen Endpunkt über --base-url.

Agent-Paket

High-Level Go-API für KI-Agenten. Strukturierte Ausgabe, automatisches Warten, Goroutine-sicher.

session, _ := agent.NewSession(agent.SessionConfig{Headless: true})
defer session.Close()

// Navigate and observe
session.Navigate("https://example.com")
obs, _ := session.Observe()               // links, inputs, buttons, text + action costs

// DOM diff — only what changed (saves 50-80% tokens)
session.Click("#submit")
_, diff, _ := session.ObserveDiff()
// diff.Classification: "modal_appeared"
// diff.Summary: "Modal/dialog appeared: Login required"

// Semantic form filling — no CSS selectors
session.FillFormSemantic(map[string]string{
    "Email": "user-example", "Password": "secret",
})

// Visual grounding — click by number, not selector
result, _ := session.AnnotatedScreenshot()  // numbered labels on elements
session.ClickLabel(7)                        // click element [7]

// Multi-tab coordination
session.OpenTab("pricing", "https://example.com/pricing")
session.SwitchTab("default")

// Framework detection (19 frameworks)
frameworks, _ := session.DetectedFrameworks() // ["react", "nextjs"]
state, _ := session.ComponentState("#app")    // read React/Vue state

// Network capture — read API responses directly
session.EnableNetworkCapture("/api/")
captured := session.CapturedRequests("/api/users")

// Action replay — record once, replay without LLM
session.StartRecordingPlaybook("login-flow")
// ... do stuff ...
pb, _ := session.StopRecordingPlaybook()
agent.SavePlaybook(pb, "login.json")
// Later: session.ReplayPlaybook(pb)  // 100x cheaper

// Persistent profiles
session.SaveProfile("session.json")   // cookies + localStorage
session.LoadProfile("session.json")

// Content distillation (5 levels)
session.Markdown()          // ~2-8KB compact markdown
session.ReadableText()      // ~1-4KB main content only
session.AccessibilityTree() // ~1-4KB semantic tree
session.ObserveWithBudget(500) // fit in ~500 tokens

Kernbibliothek

Gin-ähnliche Engine/Context/Group/HandlerFunc mit Middleware-Komposition:

engine := browse.Default(browse.WithHeadless(true))
engine.MustLaunch()
defer engine.Close()

engine.Use(middleware.Stealth())
engine.Use(middleware.Retry(middleware.RetryConfig{MaxAttempts: 3}))
engine.Use(middleware.Timeout(30 * time.Second))

admin := engine.Group("admin", middleware.BasicAuth("admin", "secret"))
admin.Task("export", func(c *browse.Context) {
    c.MustNavigate("https://app.example.com/admin")
    table, _ := c.ExtractTable("#users")
    c.Set("data", table)
})

engine.RunGroup("admin")

Middleware

Kategorie

Middleware

Resilienz

Retry, Timeout, CircuitBreaker, RateLimit, Bulkhead

Authentifizierung

BearerAuth, BasicAuth, CookieAuth, HeaderAuth

Anti-Erkennung

Stealth (10 Patches: webdriver, plugins, WebGL, etc.)

Netzwerk

BlockResources, WaitNetworkIdle

Dienstprogramme

ScreenshotOnError, SlowMotion, Viewport

CLI

Das CLI verwendet standardmäßig einen sichtbaren Browser (--headless zum Ausblenden):

scout navigate <url>                  # page info as JSON
scout observe <url>                   # structured observation
scout markdown <url>                  # compact markdown
scout screenshot <url> [--output f]   # save screenshot
scout pdf <url> [--output f]          # save PDF
scout extract <url> <selector>        # extract text
scout eval <url> <expression>         # run JavaScript
scout form discover <url>             # discover form fields
scout frameworks <url>                # detect frameworks
scout watch <url> [--interval=5s]     # live-watch page changes
scout pipe <command> [selector]       # batch process URLs from stdin
scout record <url> [--output f]       # interactive recording → playbook
scout mcp serve                       # start MCP server
scout version                         # print version

Architektur

scout/
├── browse.go, engine.go, context.go   # Gin-like API
├── page.go, selection.go              # CDP page & element interaction
├── recorder.go                        # Video recording (screencast → MP4/GIF)
├── middleware/                        # stealth, resilience, auth, network
├── agent/                             # AI agent API (50+ methods)
│   ├── session.go                     # Session lifecycle, Navigate, Click, Type
│   ├── observe.go, diff.go            # Observe, ObserveDiff, cost estimation
│   ├── content.go                     # Markdown, ReadableText, AccessibilityTree
│   ├── form.go                        # DiscoverForm, FillFormSemantic, MatchFormField
│   ├── annotate.go                    # AnnotatedScreenshot, ClickLabel
│   ├── network.go                     # EnableNetworkCapture, CapturedRequests
│   ├── spa.go                         # DetectedFrameworks, ComponentState, GetAppState
│   ├── tabs.go                        # OpenTab, SwitchTab, CloseTab, ListTabs
│   ├── playbook.go                    # StartRecording, ReplayPlaybook, SavePlaybook
│   ├── interact.go                    # Hover, DragDrop, SelectOption, ScrollTo
│   ├── profile.go                     # CaptureProfile, ApplyProfile, SaveProfile
│   ├── selector.go                    # Playwright :text() selector translation
│   ├── budget.go                      # ObserveWithBudget, EstimateTokens
│   ├── nlselect.go                    # SelectByPrompt, fuzzy NL element matching
│   ├── batch.go                       # ExecuteBatch, sequential multi-action
│   ├── vision.go                      # HybridObserve, FindByCoordinates
│   ├── trace.go                       # StartTrace, StopTrace, action tracing
│   ├── iframe.go                      # SwitchToFrame, SwitchToMainFrame
│   └── vitals.go                      # WebVitals (LCP/CLS/INP)
├── internal/cdp/                      # WebSocket CDP client (context-aware)
├── internal/launcher/                 # Chrome process management
├── cmd/scout/                         # CLI + MCP server (66 tools)
└── docs/                              # Landing page (GitHub Pages)

Lizenz

MIT

A
license - permissive license
Not graded
quality - not tested
A
maintenance

Maintenance

Maintainers
2hResponse time
3dRelease cycle
43Releases (12mo)
Commit activity
Issues opened vs closed

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    Not graded
    quality
    B
    maintenance
    An MCP server that lets AI assistants drive real Chromium browsers — navigate, click, type, read pages, run OCR, and record network traffic. 43 tools, credentials stay local, zero telemetry.
  • A
    license
    B
    quality
    A
    maintenance
    A lightweight 30KB MCP browser automation server that uses raw Chrome DevTools Protocol to enable AI agents to browse the web, take screenshots, interact with elements, and capture live page events like console logs and network requests.
    26
    337
    13
    MIT

View all related MCP servers

Related MCP Connectors

  • Screenshot, diff, audit and sitemap-capture any web page — 5 MCP tools for AI agents.

  • Live browser debugging for AI assistants — DOM, console, network via MCP.

  • AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/klarlabs-studio/scout'

If you have feedback or need assistance with the MCP directory API, please join our Discord server