150,000+ agents registered. Trust scores show their math.Explore →
Explorer/MCP/smithery/browser_tool
REMOTE

Browser tool

smithery/browser_tool

Composio enables AI Agents and LLMs to authenticate and integrate with various tools via function calling.

18 tools available ↓
The Journeyman
A reasonable amount of history and nothing concerning in the scan.
Time indexed (11mo)
18toolsRemote/ HTTP11moindexed
100% uptime · 340ms avgChecked Oct 15, 2026
Quality Score
59/95
Established
Risk Score
0/100
Clean
▸How is this calculated?
Quality Breakdown
Tenure15.9/20
330 days indexed
Capability18.5/25
Tools: 6.5/13 (18 tools)
Description: 5/5 ✓
Endpoint: 7/7 ✓
Adoption0/25
Use count: 0/20 (0 uses)
Multi-registry: 0/5 (1 registry)
Reliability25/25
Currently live: 10/10 ✓
Uptime history: 15/15 100% (51/51 checks)
Security scan: 0 pts in v1.0; ready to weight when coverage improves
Incomplete Data Cap (60)
Usage data is not available for this server. Quality is capped until adoption can be measured.
Risk
0— Clean
No signals detected.
The scanner shows
18 tools. Nothing caught our attention.
First indexed Nov 19, 2025
Server Profile
⚙
Tools catalogued
18
18 tools available. Full list below.
☁
Hosting
Remote / HTTP
Runs on the internet. No access to your filesystem, SSH keys, or environment variables.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
100%
Based on 48 checks. Average response: 340ms.
Publisher Verification
Not yet verified by the Official MCP Registry.
Endpoint
https://browser_tool.run.tools
Tools (18)
BROWSER_TOOL_COPY_SELECTED_TEXT
Copy currently selected text on the page to clipboard - ideal for extracting highlighted content, copying form data, or harvesting visible text selections.
BROWSER_TOOL_DRAG_AND_DROP
Execute precise drag and drop operations - essential for file uploads, list reordering, element moving, and complex UI interactions that require drag-based manipulation.
BROWSER_TOOL_FETCH_WEBPAGE
DECISION BRAIN: Essential for analysis, planning, and information gathering. PRIMARY USES: Understand page state, locate elements, verify changes, plan next actions FALLBACK ROLE: When screenshot blocked/fails, use this diligently for information FORMAT: html=element discovery & coordinates | markdown=content analysis HYBRID WORKFLOW: Use for decisions → AI agent for precision clicking
BROWSER_TOOL_GET_CLIPBOARD
Read current content from the system clipboard - essential for data transfer workflows, extracting copied text, and reading user-copied data for processing.
BROWSER_TOOL_KEYBOARD_SHORTCUT
Execute keyboard shortcuts and key combinations - essential for copy/paste, navigation, and application commands that agents need for efficient browser automation.
BROWSER_TOOL_MOUSE_CLICK
MANUAL PRECISION: Coordinate-based clicking - less efficient than AI agent for complex clicks. WHEN TO USE: Simple single clicks when you have exact coordinates BETTER ALTERNATIVE: Use PerformWebTask AI agent for complex/precise clicking PATTERN: FetchWebpage(html) → estimate coordinates → click → verify HINTS: Center ~(640,350) | Header ~y=150 | Content ~y=300-500 | SUCCESS RATE: 85%
Show all 18 tools ↓
BROWSER_TOOL_MOUSE_DOUBLE_CLICK
Execute a precise double click at specified screen coordinates - ideal for opening files, selecting text, or activating UI elements that require double click gestures.
BROWSER_TOOL_MOUSE_DOWN
Press and hold mouse button at coordinates - use for starting custom drag operations, text selections, or long-press interactions. Must be followed by MouseUp action to complete.
BROWSER_TOOL_MOUSE_MOVE
Move mouse cursor to precise coordinates without clicking - perfect for triggering hover effects, revealing tooltips, and positioning for subsequent interactions.
BROWSER_TOOL_MOUSE_UP
Release mouse button at coordinates - completes drag operations, text selections, and long-press interactions. Should be used after MouseDown to finish mouse button sequences.
BROWSER_TOOL_NAVIGATE
SESSION FOUNDATION: Always start here - creates browser session and navigates to URL. WORKFLOW: Navigate() → FetchWebpage() → Analysis/Planning → AI Agent or Manual interactions → Verify PROVIDES: Live debugUrl for user, initial page snapshot, persistent session TIP: Always show debugUrl to user before proceeding
BROWSER_TOOL_PASTE_TEXT
Paste text content at the current cursor position - perfect for filling forms, inserting data into text fields, or quick content insertion at focused elements.
BROWSER_TOOL_PERFORM_WEB_TASK
AI AGENT: BEST for precise clicking and complex interactions. PREFERRED FOR: Button clicks, form interactions, precise targeting (coordinates handled well) HYBRID WORKFLOW: Use after FetchWebpage analysis for informed AI interactions WHEN TO USE: Any clicking task, multi-step workflows, dynamic content STRATEGY: AI handles precision → regular tools for verification
BROWSER_TOOL_SCREENSHOT_WEBPAGE
Capture high-quality screenshot of any webpage with extensive customization options - perfect for archiving, visual documentation, full-page captures, and cross-device viewport testing.
BROWSER_TOOL_SCROLL
PAGE NAVIGATION: Smooth scrolling. USE: When target element not visible after FetchWebpage() DISTANCE: 200px=fine | 400px=sections | 800px=quick traverse ALWAYS: Scroll → FetchWebpage() → verify | SUCCESS RATE: 99%
BROWSER_TOOL_SET_CLIPBOARD
Store text content in the system clipboard for later paste operations - perfect for preparing data transfers, staging content for forms, or cross-application data sharing.
BROWSER_TOOL_TAKE_SCREENSHOT
VISUAL VERIFICATION: Capture screenshot - MUST BE CALLED ALONE in multi_execute. 🚨 CRITICAL: Screenshot cannot be combined with other tools in same multi_execute call FALLBACK: If screenshot blocked/fails, use FetchWebpage diligently for information USE: Debug UI, verify states, document results after page changes RENDERS: Inline visual feedback | SUCCESS RATE: 99%
BROWSER_TOOL_TYPE_TEXT
CONTROLLED INPUT: Human-like typing. PATTERN: Click to focus → TypeText() → verify SPEED: delay=0 (fast) | delay=50 (human-like) | delay=100+ (careful) Must focus input field first | SUCCESS RATE: 95%

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
More from smithery
LetsFG
Agent-native flight search. 102 airline connectors fire in parallel — Ryanair, EasyJet, Wizz Air, Southwest, AirAsia, Qantas, and 96 more — plus enterprise GDS/NDC providers (Amadeus, Duffel, Sabre, Travelport) through the LetsFG backend. One tool call scans the entire world for flights, including airlines your agent didn't know existed. Your agent doesn't need to build a flight integration. It doesn't need to scrape. Just add this MCP server and it can search and book flights in seconds. ### Why? Flight websites inflate prices with demand tracking, cookie-based pricing, and surge markup. The same flight is often **$20–$50 cheaper** through LetsFG — raw airline price, zero markup. ### How it works `search_flights` fires all relevant connectors in parallel on your machine + queries enterprise GDS sources in the cloud. Results come back merged, deduplicated, sorted by price. ~5 seconds for a full global search. ### Tools | Tool | What it does | Cost | |------|-------------|------| | `search_flights` | Search 400+ airlines | Free | | `search_hotels` | Search hotels worldwide | Free | | `resolve_location` | City/airport → IATA code | Free | | `get_agent_profile` | Your usage & profile | Free | | `unlock_flight_offer` | Confirm live price, reserve 30 min | Free | | `setup_payment` | Attach Stripe payment | Free | | `book_flight` | Book with real PNR + e-ticket | Ticket price only | **Search is free forever. Booking charges the raw airline ticket price via Stripe — we add zero margin.** `LETSFG_API_KEY` is optional. Without it, the server runs all 102 local connectors. With it, you also get 400+ airlines via enterprise GDS/NDC sources. ### Pricing - **Personal use** — completely free. Search, unlock, book. No limits. - **Commercial use** — 1% fee (min $1 USD) per booking, collected via Stripe Connect. Search and unlock are still free. - **First 1,000 GitHub stars** — star the repo and link your GitHub username to get free unlimited access (personal & commercial). No trial, no catch. ### Links - **GitHub:** [github.com/LetsFG/LetsFG](https://github.com/LetsFG/LetsFG) — full docs, 102 connector source code, architecture guide, agent integration tutorials - **API Docs:** [api.letsfg.co/docs](https://api.letsfg.co/docs) - **PyPI:** [pypi.org/project/letsfg](https://pypi.org/project/letsfg/) - **npm:** [npmjs.com/package/letsfg-mcp](https://www.npmjs.com/package/letsfg-mcp)
Zendesk
Manage support tickets, help center articles, and customer conversations. Track SLAs, assign agents, and search knowledge base content.
Postman
Test and debug APIs with collections, environments, and monitors. Run requests, inspect responses, and collaborate on API documentation.
GitHub Mapper
An MCP server that maps and analyzes GitHub repository structures, providing summary statistics and detailed file structures.
Oura Ring
Health and wellness tracking from your Oura Ring. Access sleep, activity, readiness, heart rate, stress, resilience, SpO2, and workout data. Manage webhook subscriptions for real-time updates.
Pagerduty
Integrate PagerDuty to manage incidents, schedules, and alerts directly from your application.
Similar servers
keycloak-source-mcp
An MCP server that enables AI assistants to navigate, search, and analyze local Keycloak source code to support developer customizations like SPIs and authenticators. It provides tools for searching classes, generating boilerplate code, detecting breaking changes between versions, and tracing dependencies.
MCP Web Research Server
The MCP Web Research Server enables real-time web research with Claude by integrating Google search, capturing webpage content and screenshots, and tracking research sessions.
JS Reverse MCP
An MCP server for JavaScript reverse engineering that enables AI to perform browser debugging, script analysis, and automated hook injection. It streamlines complex workflows like deobfuscation, network tracing, and risk assessment through direct browser integration.
Memory Store MCP Server
A lightweight, stateless MCP server utilizing Puppeteer for web searches, returning structured JSON results, easily integratable with other MCP-enabled systems.
devdoc
A documentation MCP server that crawls websites and Git repositories, stores them as Markdown, and provides tools to search and retrieve documentation for local LLMs and AI agents.
BerryRAG
A local vector database RAG system that integrates with Playwright MCP for web scraping, enabling users to build searchable knowledge bases from web content with multiple embedding providers and Claude-optimized context formatting.
Indexed from Smithery · Updates nightlyView on Smithery →