Koskamo

Readmd MCP

Readmd MCP is a remote server that converts web pages into clean, LLM-ready Markdown. It extracts main content, metadata, outlines, and token counts, supporting single or batch URL reading while respecting robots.txt and charging only for successful reads.

Visit Readmd

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.

Readmd MCP logo, by ReadmdVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-02Operated by Readmd
MCP endpoint (Streamable HTTP)
https://readmd.canisell.xyz/mcp
Vendor documentation

What its tools do

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

Read-only (4)

4 of 4 have a description · 4 of 4 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to canisell.xyz ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Extract main content from URLs as clean Markdown
  • Get metadata and outlines for web pages
  • Batch read up to 10 URLs for RAG preparation
  • Preview page content and token counts for free

Source and maintenance

Vendor evidenceRegistry 0.1.0
mcp-registry: xyz.canisell/readmd@0.1.0Project website

Protocol and capabilities

Server
readmd 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
4 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.

Readmd: Web page to clean, LLM-ready Markdown for AI agents: main-content extraction, metadata, outline, token counts and RAG chunks. $0.001 per page, $0.005 for 10. Free tools: about, preview_url. Paid tools cost USDC via x402; clients without an x402 wallet get the payment terms and the paid HTTP URL instead.

Tools

4 advertised

read_url — Read a web page as Markdown (paid)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Read a web page as clean Markdown for an LLM. Fetches the URL (robots.txt respected), extracts the main content (drops navigation, headers, footers, sidebars, cookie banners) and returns GitHub-flavoured Markdown with headings, lists, tables, code blocks (with language) and absolute links, plus metadata (title, description, author, published/modified dates, site name, language, canonical URL, image), an outline of headings, word count and a token estimate. Options: mode=full for the whole page, links=false to save tokens, images=true, include_links=true for the link list, max_tokens to truncate, chunk_tokens to get RAG-ready chunks with heading paths. Also converts native Markdown, plain text, JSON and RSS/Atom feeds. Never charged when it fails: unreachable or 4xx/5xx targets, robots.txt disallow, unsupported types (PDF, images) and empty/JavaScript-only pages return an error and are not settled. $0.001 per page. Costs $0.001 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.

read_url input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 4,
      "description": "Public http(s) URL of the page to read."
    },
    "mode": {
      "enum": [
        "main",
        "full"
      ],
      "type": "string",
      "description": "\"main\" (default): the article / main content only, without navigation, headers, footers, sidebars and cookie banners. \"full\": the whole page body."
    },
    "links": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "enum": [
            "0",
            "1",
            "true",
            "false"
          ],
          "type": "string"
        }
      ],
      "description": "Keep inline links as [text](url) in the Markdown. Default true; false saves tokens."
    },
    "images": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "enum": [
            "0",
            "1",
            "true",
            "false"
          ],
          "type": "string"
        }
      ],
      "description": "Keep images as ![alt](src). Default false."
    },
    "max_tokens": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 100,
      "description": "Truncate the Markdown to about this many tokens, at a paragraph boundary (`truncated` tells you). Default: no limit (400k characters max)."
    },
    "chunk_tokens": {
      "type": "integer",
      "maximum": 8000,
      "minimum": 100,
      "description": "Also return `chunks`: the Markdown split at headings/paragraphs into pieces of at most about this many tokens, each with its heading path. For RAG."
    },
    "include_links": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "enum": [
            "0",
            "1",
            "true",
            "false"
          ],
          "type": "string"
        }
      ],
      "description": "Also return `links`: every link in the content as {url, text} (up to 500). Default false."
    }
  }
}
read_url annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
read_urls — Read up to 10 web pages as Markdown (paid)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Read up to 10 web pages as clean Markdown in one call, in parallel: the same output as /v1/read for each URL, with a per-URL ok/error. $0.005 per call (= $0.0005 per page at 10 URLs). Charged only if at least one URL is read successfully. Costs $0.005 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.

read_urls input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "urls"
  ],
  "properties": {
    "mode": {
      "enum": [
        "main",
        "full"
      ],
      "type": "string",
      "description": "\"main\" (default): the article / main content only, without navigation, headers, footers, sidebars and cookie banners. \"full\": the whole page body."
    },
    "urls": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 2048,
        "minLength": 4
      },
      "maxItems": 10,
      "minItems": 1,
      "description": "Up to 10 public http(s) URLs, read in parallel."
    },
    "links": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "enum": [
            "0",
            "1",
            "true",
            "false"
          ],
          "type": "string"
        }
      ],
      "description": "Keep inline links as [text](url) in the Markdown. Default true; false saves tokens."
    },
    "images": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "enum": [
            "0",
            "1",
            "true",
            "false"
          ],
          "type": "string"
        }
      ],
      "description": "Keep images as ![alt](src). Default false."
    },
    "max_tokens": {
      "type": "integer",
      "maximum": 100000,
      "minimum": 100,
      "description": "Truncate the Markdown to about this many tokens, at a paragraph boundary (`truncated` tells you). Default: no limit (400k characters max)."
    },
    "chunk_tokens": {
      "type": "integer",
      "maximum": 8000,
      "minimum": 100,
      "description": "Also return `chunks`: the Markdown split at headings/paragraphs into pieces of at most about this many tokens, each with its heading path. For RAG."
    },
    "include_links": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "enum": [
            "0",
            "1",
            "true",
            "false"
          ],
          "type": "string"
        }
      ],
      "description": "Also return `links`: every link in the content as {url, text} (up to 500). Default false."
    }
  }
}
read_urls annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
about — About Readmd (free)
Advertised by the server during the last successful anonymous check.
Advertised read-only

Free. What Readmd does, prices of the paid tools and HTTP endpoints, and links to docs.

about input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
about annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
preview_url — Preview a web page as Markdown (free)
Advertised by the server during the last successful anonymous check.
Advertised read-only

Free. Fetches a URL and returns its title, metadata, outline, word and token counts and the first 500 characters of the clean Markdown. Use read_url (paid, $0.001) for the full text.

preview_url input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "minLength": 4,
      "description": "Public http(s) URL"
    }
  }
}
preview_url annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

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. 2026-11-02: 2 of 2 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
737 ms
95th percentile latency
737 ms

Maintenance history

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

  • · probe · passed · 737 ms · metadata changed · 4 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 readmd-mcp https://readmd.canisell.xyz/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 readmd-mcp --url https://readmd.canisell.xyz/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable readmd-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "readmd-mcp": {
      "url": "https://readmd.canisell.xyz/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "readmd-mcp": {
      "type": "streamableHttp",
      "url": "https://readmd.canisell.xyz/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start readmd-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "readmd-mcp": {
      "type": "http",
      "url": "https://readmd.canisell.xyz/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 readmd-mcp https://readmd.canisell.xyz/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": {
    "readmd-mcp": {
      "url": "https://readmd.canisell.xyz/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": {
    "readmd-mcp": {
      "serverUrl": "https://readmd.canisell.xyz/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Readmd 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 7,692

Do you run Readmd MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing