agent-web MCP

A polite, robots.txt-respecting web reader that converts publicly reachable URLs into clean, LLM-ready markdown. It supports reading full pages, previews, and paid screenshot/PDF rendering via x402, while strictly honoring robots.txt and never bypassing anti-bot measures.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by FOOM

MCP endpoint (Streamable HTTP)

https://agent-web.foomworks.workers.dev/mcp

Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (5)

read_url
read_url_preview
render_preview
render_screenshot
render_pdf

5 of 5 have a description · 0 of 5 declare behavior hints · 5 of 5 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 12:56 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Fetch a URL and return clean LLM-ready markdown
Get a preview of the first 600 characters of markdown
Render a webpage as a PNG screenshot
Render a webpage as a PDF document

Source and maintenance

Community listingRegistry 0.2.1

mcp-registry: io.github.foomworks/agent-web@0.2.1 Source repository Project website

Maintenance checked: Nov 7, 2026, 12:20 AM UTC

Protocol and capabilities

Server: agent-web 0.9.0
MCP protocol negotiated in check: 2025-06-18
Tools: 5 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

A charter-clean web toolkit. read_url fetches one publicly reachable, server-rendered URL and returns LLM-ready markdown; read_url_preview returns the first ~600 characters; render_preview is a free discovery stub for the render lane. render_screenshot/render_pdf are PAID (x402, $1+) and return payment instructions, not data. All honor robots.txt, identify honestly, are read-only, and never bypass anti-bot/CAPTCHA/paywalls.

Tools

5 advertised

read_url

Advertised by the server during the last successful anonymous check.

Fetch one publicly reachable URL and return clean, LLM-ready markdown (title + page description + word count + markdown). HTML pages are extracted to markdown — including HTML tables, which become GitHub-flavored Markdown tables; URLs pointing straight at a Markdown or plain-text document (raw READMEs, llms.txt, docs) are passed through verbatim. Polite by design: honors the origin's robots.txt for our user-agent, identifies honestly, read-only GET, never bypasses anti-bot/CAPTCHA/paywalls. Free. JavaScript-rendered pages are not supported yet.

read_url input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "absolute http(s) URL of a publicly reachable HTML page"
    }
  }
}

read_url_preview

Advertised by the server during the last successful anonymous check.

Like read_url but returns only the page description + the first ~600 characters of the markdown (title + word count + a truncation flag) — a cheap way to check a page's relevance before pulling the full text. Free.

read_url_preview input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "absolute http(s) URL of a publicly reachable HTML page"
    }
  }
}

render_preview

Advertised by the server during the last successful anonymous check.

Free discovery stub for the screenshot/PDF render lane. Same robots/SSRF guards as read_url. Currently returns a 503 (no charge) until Cloudflare Browser Rendering is provisioned on this account.

render_preview input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "absolute http(s) URL of a publicly reachable page"
    }
  }
}

render_screenshot

Advertised by the server during the last successful anonymous check.

PAID (x402): returns x402 payment instructions for a PNG screenshot of a publicly reachable URL, rendered via a real, robots-respecting headless browser. Use render_preview (free) first. Currently soft-skips 503 until Cloudflare Browser Rendering is provisioned.

render_screenshot input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "absolute http(s) URL to screenshot"
    },
    "width": {
      "type": "integer",
      "description": "viewport width in pixels (default 1280)"
    },
    "fullPage": {
      "type": "boolean",
      "description": "capture the full scrollable page (default: viewport only)"
    }
  }
}

render_pdf

Advertised by the server during the last successful anonymous check.

PAID (x402): returns x402 payment instructions for a PDF render of a publicly reachable URL, via a real, robots-respecting headless browser. Currently soft-skips 503 until Cloudflare Browser Rendering is provisioned.

render_pdf input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "absolute http(s) URL to render to PDF"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 278 ms
95th percentile latency: 278 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 12:56 AM UTC · probe · passed · 278 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http agent-web-mcp https://agent-web.foomworks.workers.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add agent-web-mcp --url https://agent-web.foomworks.workers.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-web-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "agent-web-mcp": {
      "url": "https://agent-web.foomworks.workers.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "agent-web-mcp": {
      "type": "streamableHttp",
      "url": "https://agent-web.foomworks.workers.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-web-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "agent-web-mcp": {
      "type": "http",
      "url": "https://agent-web.foomworks.workers.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http agent-web-mcp https://agent-web.foomworks.workers.dev/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://agent-web.foomworks.workers.dev/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "agent-web-mcp": {
      "serverUrl": "https://agent-web.foomworks.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like agent-web MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows