

Live Web Page Browser
Core Utility
Available ActionsEach successful request consumes credits as outlined below.
get_url_html_content5crget_url_markdown5crget_url_screenshot5cr
Details
Fetch any webpage and return the live version. Return options include markdown only, html, and screen shot images, allowing you to return only what your agent needs, using minimal context and tokens. Live search bypasses search restrictions built in to many well known agents. Enables seamless agentic website access for AI assistants and large language models and provides AI agents with programmatic web interaction capabilities including HTML content retrieval, intelligent Markdown conversion, and screenshot capture—all through simple, structured tool commands. it delivers a secure, low-latency solution for headless browser automation at the edge. This MCP server transforms how AI agents perceive and interact with the live web, enabling real-time content extraction, web scraping, and visual page capture without requiring vision models or complex browser infrastructure.
Use Cases
Real-Time Research & Information Gathering, Competitive Intelligence & Market Monitoring, Content Verification & Fact-Checking, Visual Documentation & Change Detection, Data Extraction for RAG Pipelines, Automated Form Pre-Population & Workflow Prep, Accessibility & Content Summarization
Dynamic MCP Setup
Connect once through AgentPMT Dynamic MCP, then use approved tools from the same agent connection.
30 Second Setup
STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections.
npm install -g @agentpmt/mcp-routeragentpmt-setupHosted Streamable HTTPS
MCP endpoint for browser-based apps like ChatGPT, Claude, Grok, or any time you want a streamable connection with no local install.
https://api.agentpmt.com/mcpConfig Example
Use the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.
{
"mcpServers": {
"agentpmt": {
"type": "streamable-http",
"url": "https://api.agentpmt.com/mcp",
"headers": {
"Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
"x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
}
}
}
}Need client videos, organization controls, audit details, and the full feature overview?
More About Dynamic MCPFrequently Asked Questions
How do I connect this tool to an external agent?
You can install the local MCP server by opening a terminal and running:
Install commands
npm install -g @agentpmt/mcp-router
agentpmt-setupThis will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.
Alternatively you can connect to the hosted version with this config block, no installation required:
Hosted MCP config
{
"mcpServers": {
"agentpmt": {
"type": "streamable-http",
"url": "https://api.agentpmt.com/mcp",
"headers": {
"Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
"x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
}
}
}
}View MCP Connection Instructions for more details.
How does an external agent use this tool?
After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent:
Agent prompt
Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get_instructions' so you know how to use the tool search interface. Then call action 'get_schema' with tool_id 69644454288e0324fa542102 ("Live Web Page Browser"). After reading the schema and any returned instructions, tell me what this tool can do, what inputs it needs, and what you need from me before running it. Do not call action 'call_tool' until I confirm the request and provide the required parameters.
The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT.







