Launch an AI agent from a pinned config, optionally adding integration tools, subscriptions, interaction handlers, and initial input atomically. Requires permissions.
Apache 2.0
671,094 tools. Updated 2026-10-17 22:01
"Adding web browsing and page reading capabilities to an agent" matching MCP tools:
- Extract web page content and convert it to clean, readable markdown format for analysis, bypassing paywalls and obtaining structured text data from websites.Apache 2.0
- Extract web page content and store it in agent memory for future recall. Use to save key facts, events, or how-to steps from any URL into ZeroDB.MIT
- Extract a web page's main content as Markdown, stripping boilerplate while keeping headings, lists, tables, and links for reading or LLM input.MIT
- Register an agent with its unique name, description, capabilities, and HTTP callback endpoint to make it discoverable and available for task delegation.MIT
- Explore agent capabilities and tool groups to identify available actions for workspaces, previews, builds, logs, and deployments.MIT
Matching MCP Servers
- FlicenseAqualityDmaintenanceEnables document conversion between PDF, DOCX, and Markdown formats to facilitate reading and editing complex files in AI tools like Claude Desktop or Cursor. It utilizes marker-pdf and pandoc to provide structured text versions of documents, helping to manage context and support unsupported file types.11-
- AlicenseAqualityCmaintenanceFetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.128 PyPIMIT
Matching MCP Connectors
Create, edit, preview, publish, and manage web pages from MCP-capable AI clients.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
- Determine the cost for an AI agent to access a web page without paying. Use before authorizing a payment.MIT
- Search the public web. Search Brave's public web results. limit (1-50, default 10) is honoured by reading up to 3 result pages; each successful result page read costs 3 credits, and optional page reads (5 credits each) remain scoped to…MIT
- Retrieve the A2A Agent Card for an organization to enable inter-agent discovery. This tool provides agent capabilities, endpoints, and authentication requirements for agent-to-agent communication.Apache 2.0
- Extract article text and metadata from any web page, removing ads and clutter for clean reading or AI processing.MIT
- Fetches a web page and converts it to clean Markdown for reading or analysis, removing scripts, styles, and ads while preserving tables, code blocks, and lists.MIT
- Look up an AI artifact's capabilities by name to evaluate it before adding to your stack.MIT
- Retrieve screenshots from web browsing sessions to review AI agent actions and page interactions during task execution.MIT
- Retrieve agent identity details including trust score, permissions, and capabilities by providing the agent identifier.MIT
- Search the public docs and research web headlessly, structuring the result page for follow-up browsing. Automatically selects search engine.Mozilla Public 2.0
- Fetch a web page and extract its main article content into clean Markdown with title and byline, stripping all noise for reliable reading.MIT
- Provision a phone number from a carrier pool and assign it to an agent. Specify country code, area code, and capabilities to constrain selection.MIT
- Review AI models from multiple providers, including capabilities, pricing, and web search costs, to pick the right one for your task.MIT
- Create an agent with a declared intent and USD budget, returning an agent_id for later task execution. Set capabilities and model to define what the agent can do before running goals.Apache 2.0
- Fetch a web page and extract its main content as plain text. Ideal for reading full articles from search result URLs.MIT
- Register an agent with identity metadata—type, trust level, and capabilities—to enable multi-agent operations in a knowledge graph memory server.MIT