Execute a one-time web browsing task using an agent that operates the browser like a person. Provide a start URL and task description to get a task_id for polling progress.
Apache 2.0
510,032 tools. Updated 2026-09-03 17:32
"A tool for browsing the web" matching MCP tools:
- Search the public docs and research web headlessly, structuring the result page for follow-up browsing. Automatically selects search engine.Mozilla Public 2.0
- Retrieve official documentation for a specific MTA:SA function or event using its canonical name. Avoid manual web browsing for accurate, cached results.GPL 3.0
- Choose a cost-effective reliable web perception route for a task, reducing costs before reading, browsing, or using screenshots.MIT
- Open Drizzle Studio to browse and manage the database through a web interface.
- Sets the active browsing context for subsequent tool calls, using a contextId to target a specific page.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceA Model Context Protocol server that provides real-time web search capabilities to AI assistants through pluggable search providers, currently integrated with the Brave Search API.516MIT
- FlicenseAqualityCmaintenanceA read-only MCP server that helps customers discover products, select flavors, check inventory and food info, and access official purchase links for Sifang Nuo Mi.7
Matching MCP Connectors
Japanese agriculture policy, subsidies and rice advance payments. 日本の農業政策・補助金・米の概算金
Base 主网去中心化支付路由+金库：查 NAV、构造路由支付 calldata、金库存取、绑定引路人分账。存款安全·引路人激励·消费即升值，全部链上可核验。
- Search the web via DuckDuckGo, crawl pages for content, and fetch news articles. Save results to disk using harvest to avoid high context costs.MIT
- Search the web and get clean, structured results with titles and snippets, bypassing anti-bot restrictions.MIT
- Lists memories in chronological order with pagination for browsing recent activity. Optionally filter by keyword.MIT
- Find the right DC Hub tool for your task by browsing tool families with when-to-use guidance. Filter by keyword to see relevant tools and their schemas.MIT
- Search the web and obtain concise result snippets without fetching full pages. Ideal for quick lookups when you only need brief information, avoiding the overhead of a comprehensive search.MIT
- Retrieve stored memories in chronological order for browsing or auditing purposes, with pagination support for efficient navigation.MIT
- Filter job postings by status, department, office, or date range, and sort results for easy browsing.MIT
- List candidates with filters for email, date ranges, and sorting. Use for simple browsing or exact email lookups.MIT
- Extract factual claims from documents or explicit statements, search the live web for supporting evidence, and retrieve source URLs with a keyword-overlap score. Optionally generate a cited PDF verification report.MIT
- List all stored transcriptions with titles, durations, dates, and file paths for browsing what has already been transcribed.MIT
- Fetch your browsing tasks with optional status filter and cursor pagination. Monitor task execution status, then call get_browsing_task_result for authoritative results.Apache 2.0
- Check browsing task status and result by providing its task ID. Poll until status is succeeded or failed to get the final outcome.Apache 2.0
- Search across your workspace memories, documents, and browsing history using hybrid dense and sparse retrieval with reranking for relevant results.MIT
- Search the web for a query, then retrieve complete page content from the top results to provide detailed, in-depth information for comprehensive research.MIT