Koskamo

AgentRead MCP

AgentRead converts public web pages into clean Markdown, metadata, headings, and links for AI agents. It offers free URL inspection and paid extraction tools via x402 micropayments on Base, with no accounts or API keys required.

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.

AgentRead MCP logo, by omarhassanatefCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-01Published by omarhassanatef
MCP endpoint (Streamable HTTP)
https://agentread.omar-cv.workers.dev/mcp
Vendor documentation

What you can do with it

  • Inspect URL reachability and content type
  • Extract clean Markdown from public web pages
  • Extract structured metadata and links from URLs

Source and maintenance

Community listingRegistry 0.2.0
mcp-registry: io.github.omarhassanatef/agentread@0.2.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agentread 0.2.0
MCP protocol
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

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

AgentRead turns public web pages into clean, agent-friendly content. Call inspect_url (free) first to check a URL; extract_url and extract_url_structured are paid per successful call via x402 (USDC). Failed extractions are not charged.

Tools

3 advertised

inspect_url — Inspect URL (free)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Free, lightweight check of a public URL: reachability, HTTP status, final URL after redirects, content type, page title, and whether extraction is likely to work. Downloads at most a small prefix of the page.

inspect_url input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 1,
      "description": "Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."
    }
  },
  "additionalProperties": false
}
inspect_url output schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "schemaVersion",
    "operation",
    "requestedUrl",
    "normalizedUrl",
    "hostname",
    "reachable",
    "statusCode",
    "finalUrl",
    "redirects",
    "contentType",
    "contentLength",
    "isHtml",
    "title",
    "mayRequireJavaScript",
    "extractionSupported",
    "limitation"
  ],
  "properties": {
    "title": {
      "type": [
        "string",
        "null"
      ]
    },
    "isHtml": {
      "type": "boolean"
    },
    "finalUrl": {
      "type": [
        "string",
        "null"
      ]
    },
    "hostname": {
      "type": "string"
    },
    "operation": {
      "type": "string",
      "const": "inspect_url"
    },
    "reachable": {
      "type": "boolean"
    },
    "redirects": {
      "type": "integer"
    },
    "limitation": {
      "type": [
        "string",
        "null"
      ]
    },
    "statusCode": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ]
    },
    "contentType": {
      "type": [
        "string",
        "null"
      ]
    },
    "requestedUrl": {
      "type": "string"
    },
    "contentLength": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ]
    },
    "normalizedUrl": {
      "type": "string"
    },
    "schemaVersion": {
      "type": "string",
      "const": "1.0"
    },
    "extractionSupported": {
      "type": "boolean"
    },
    "mayRequireJavaScript": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
inspect_url annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true
}
extract_url — Extract URL (clean Markdown)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Fetch a public web page and return its main content as clean Markdown with title, description, headings and extraction metadata. Removes navigation, ads, cookie banners and scripts. Does not execute JavaScript. Paid via x402 ($0.003 per successful call; the first 5 successful calls per day are free). Returns JSON (structuredContent + text) with schemaVersion, operation, requestedUrl, finalUrl, title, description, markdown, headings[{level,text}], truncated, extraction{method,statusCode,contentType,charset,redirects,bytesFetched,characters,totalCharacters,words,warnings,durationMs}.

extract_url input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 1,
      "description": "Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."
    },
    "includeLinks": {
      "type": "boolean",
      "description": "Keep hyperlinks and images in the Markdown (default true). When false, link text is kept as plain text."
    },
    "maxCharacters": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 100,
      "description": "Maximum Markdown characters to return (default 20000, max 100000)."
    }
  },
  "additionalProperties": false
}
extract_url annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
extract_url_structured — Extract URL (structured)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Fetch a public web page and return structured data: page metadata (title, description, canonical URL, language, site name, byline), main content Markdown, ordered headings with levels, and links (text + URL). Deterministic HTML processing, no LLM. Paid via x402 ($0.005 per successful call; the first 5 successful calls per day are free). Returns JSON with schemaVersion, operation, requestedUrl, finalUrl, metadata{title,description,canonicalUrl,language,siteName,byline,publishedTime}, markdown, headings, headingsTruncated, links[{text,url}], linksTruncated, truncated, extraction{...}.

extract_url_structured input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 1,
      "description": "Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."
    },
    "includeLinks": {
      "type": "boolean",
      "description": "Keep hyperlinks and images in the Markdown (default true). When false, link text is kept as plain text."
    },
    "maxCharacters": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 100,
      "description": "Maximum Markdown characters to return (default 20000, max 100000)."
    }
  },
  "additionalProperties": false
}
extract_url_structured annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}

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
287 ms
95th percentile latency
287 ms

Maintenance history

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

  • · probe · passed · 287 ms · metadata changed · 3 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 agentread-mcp https://agentread.omar-cv.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 agentread-mcp --url https://agentread.omar-cv.workers.dev/mcp

Cursor

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

Cline

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

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentread-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentread-mcp": {
      "type": "http",
      "url": "https://agentread.omar-cv.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 agentread-mcp https://agentread.omar-cv.workers.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "agentread-mcp": {
      "url": "https://agentread.omar-cv.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": {
    "agentread-mcp": {
      "serverUrl": "https://agentread.omar-cv.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentRead 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 6,641