Skip to content
MCP server

AgentLens Page Studio

Turns a public web page into citable passages and actions for AI assistants via MCP

Install
Platforms
API, Web
Runs
Remotely
Version
1.0.0
Listing updated
today

Similar MCP servers

About AgentLens Page Studio

AgentLens Page Studio is an MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.

The README-free listing centers on a hosted remote server rather than a downloadable package. Page Studio takes a public web page and builds a readable agent edition of it, splitting the content into passages an assistant can quote and links it can follow. Its owner-facing side lets a site see redacted questions and whether matches were found, when analytics is enabled.

A visitor or developer can try a question against the page, inspect the source text behind it, and then connect an MCP client that accepts remote Streamable HTTP servers. The server exposes tools for reading the page, finding evidence for a question and listing the actions available on it.

Booking, purchase and contact links are handed off to the destination site, so the agent sends the visitor there to complete the action rather than completing it itself. It suits site owners who want assistants to cite their pages accurately, and developers testing how an assistant reads a given website.

Install

Run in a terminal

claude mcp add --transport http page-studio https://isagentic.net/api/front-mcp

Add to Settings → Connectors → Add custom connector

https://isagentic.net/api/front-mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "page-studio": {
      "url": "https://isagentic.net/api/front-mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "page-studio": {
      "type": "http",
      "url": "https://isagentic.net/api/front-mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "page-studio": {
      "serverUrl": "https://isagentic.net/api/front-mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "page-studio": {
      "type": "http",
      "url": "https://isagentic.net/api/front-mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

What it does

Readable page passages
Converts a public page into passages that an assistant can cite.
Evidence search
Searches the page's own wording to find support for a question.
Action inspection
Lists the booking, purchase and contact links an agent can send visitors to.
Remote MCP endpoint
Connects to MCP clients through a Streamable HTTP server URL.
Redacted question analytics
Lets sites with analytics enabled see redacted questions and match outcomes.

Good for

  • Let an AI assistant cite a company's own pages accurately
  • Test how an assistant reads and searches a specific website
  • Route visitors from an assistant to a site's booking or purchase pages
  • Review which questions visitors ask about a page, with personal details redacted

AgentLens Page Studio FAQ

How do I connect it to an assistant?

Paste the edition URL into an MCP client that accepts a remote Streamable HTTP server. The server exposes tools to read the page, find evidence and list actions.

Does the agent complete bookings or purchases?

No. Booking, purchase and contact links open the destination site so the visitor can complete the action there.

How do I add AgentLens Page Studio to Claude Code?

Run this command in your terminal: claude mcp add --transport http page-studio https://isagentic.net/api/front-mcp

What are the best alternatives to AgentLens Page Studio?

The closest alternatives to AgentLens Page Studio are Parallel Search MCP, OnMap.me, Periscope MCP, WebCrawlerAPI and Stophy.

Where this comes from

  • Description: written from the project's website and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers