Koskamo

AgentScrape MCP

AgentScrape MCP provides six tools for AI agents to scrape web pages, extract structured data, take screenshots, retrieve metadata, manage browser sessions, and run workflows, all secured via x402 payments on Base USDC without requiring API keys or signup.

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.

AgentScrape MCP logo, by hshintelligenceCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by hshintelligence
MCP endpoint (Streamable HTTP)
https://agent-scrape.healingsunhaven.workers.dev/mcp
Vendor documentation

What its tools do

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

Not annotated (6)

6 of 6 have a description · 0 of 6 declare behavior hints · 2 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Scrape any URL to markdown, html, text, or json
  • AI-powered structured extraction using Groq and Llama 4 Scout
  • Take PNG screenshots with viewport control
  • Extract title, OG, Twitter, and JSON-LD metadata

Source and maintenance

Community listingRegistry 0.6.1
mcp-registry: io.github.hshintelligence/agent-scrape@0.6.1Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agent-scrape 0.6.0
MCP protocol negotiated in check
2025-11-25
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

6 advertised

scrape_webpage
Advertised by the server during the last successful anonymous check.

Scrape any webpage and return content as markdown, html, text, or json. Pay-per-call web scraping for AI agents.

scrape_webpage input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL to scrape (http or https)"
    },
    "format": {
      "enum": [
        "markdown",
        "html",
        "text",
        "json"
      ],
      "type": "string",
      "description": "Output format (default: markdown)"
    },
    "wait_ms": {
      "type": "number",
      "description": "Milliseconds to wait after page load (max 10000)"
    },
    "viewport": {
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ],
      "type": "string",
      "description": "Viewport size (default: desktop)"
    },
    "wait_for": {
      "type": "string",
      "description": "CSS selector to wait for before extracting"
    }
  }
}
scrape_webpage annotations
{
  "title": "Scrape Webpage"
}
extract_structured_data
Advertised by the server during the last successful anonymous check.

AI-powered structured data extraction from any webpage using natural language. Returns JSON matching your prompt or schema.

extract_structured_data input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url",
    "prompt"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL to extract from"
    },
    "prompt": {
      "type": "string",
      "description": "Natural language description of what to extract"
    },
    "schema": {
      "type": "object",
      "description": "Optional JSON schema for the response",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "wait_ms": {
      "type": "number"
    },
    "wait_for": {
      "type": "string"
    }
  }
}
extract_structured_data annotations
{
  "title": "Extract Structured Data"
}
screenshot_webpage
Advertised by the server during the last successful anonymous check.

Capture a PNG screenshot of any webpage. Supports desktop, mobile, and tablet viewports, plus full-page mode.

screenshot_webpage input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string"
    },
    "wait_ms": {
      "type": "number"
    },
    "viewport": {
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ],
      "type": "string"
    },
    "wait_for": {
      "type": "string"
    },
    "full_page": {
      "type": "boolean",
      "description": "Capture full scrollable page (default: false)"
    }
  }
}
screenshot_webpage annotations
{
  "title": "Screenshot Webpage"
}
extract_metadata
Advertised by the server during the last successful anonymous check.

Extract page metadata: title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, and all meta tags.

extract_metadata input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string"
    }
  }
}
extract_metadata annotations
{
  "title": "Extract Page Metadata"
}
create_browser_session
Advertised by the server during the last successful anonymous check.

Create a stateful browser session that persists cookies and localStorage across multiple scrape/workflow calls.

create_browser_session input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "ttl_seconds": {
      "type": "number",
      "description": "Session TTL (default 1800, max 7200)"
    }
  }
}
create_browser_session annotations
{
  "title": "Create Browser Session"
}
run_workflow
Advertised by the server during the last successful anonymous check.

Execute a multi-step browser workflow atomically: navigate, click, type, wait, scroll, screenshot, extract, evaluate. Up to 20 steps.

run_workflow input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "steps"
  ],
  "properties": {
    "steps": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "action"
        ],
        "properties": {
          "ms": {
            "type": "number"
          },
          "url": {
            "type": "string"
          },
          "text": {
            "type": "string"
          },
          "action": {
            "enum": [
              "navigate",
              "click",
              "type",
              "wait_for",
              "wait_ms",
              "scroll",
              "screenshot",
              "extract",
              "extract_ai",
              "evaluate"
            ],
            "type": "string"
          },
          "format": {
            "enum": [
              "markdown",
              "html",
              "text"
            ],
            "type": "string"
          },
          "prompt": {
            "type": "string"
          },
          "script": {
            "type": "string"
          },
          "selector": {
            "type": "string"
          },
          "full_page": {
            "type": "boolean"
          }
        }
      },
      "description": "Ordered list of workflow steps to execute"
    },
    "viewport": {
      "enum": [
        "desktop",
        "mobile",
        "tablet"
      ],
      "type": "string"
    },
    "session_id": {
      "type": "string"
    },
    "persist_session": {
      "type": "boolean"
    }
  }
}
run_workflow annotations
{
  "title": "Run Browser Workflow"
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

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
664 ms
95th percentile latency
664 ms

Maintenance history

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

  • · probe · passed · 664 ms · metadata changed · 6 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 agentscrape-mcp https://agent-scrape.healingsunhaven.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 agentscrape-mcp --url https://agent-scrape.healingsunhaven.workers.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentscrape-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentscrape-mcp": {
      "url": "https://agent-scrape.healingsunhaven.workers.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentscrape-mcp": {
      "type": "streamableHttp",
      "url": "https://agent-scrape.healingsunhaven.workers.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentscrape-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentscrape-mcp": {
      "type": "http",
      "url": "https://agent-scrape.healingsunhaven.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 agentscrape-mcp https://agent-scrape.healingsunhaven.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-scrape.healingsunhaven.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": {
    "agentscrape-mcp": {
      "serverUrl": "https://agent-scrape.healingsunhaven.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentScrape 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
See all 8,364