_ registry / mcp http-sse · checked 56m ago

bmmd

https://bm.md

Registry code: 99a52493dea964b6

api record

Markdown processing server with tools for rendering, linting, parsing, and text extraction, optimized for Chinese publishing platforms like WeChat, Zhihu, and Juejin.

from a public catalogue that lists it, not from the operator

endpoint
https://bm.md/mcp
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is bmmd live?
Yes — it answered the hub's last check (checked 56m ago). It answered 98% of checks over the last 30 days.
Is bmmd free to use?
Not measured yet.
What tools does bmmd have?
4 tools: render, extract, lint, parse.
Is bmmd safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
98.1%

90 days 98.3%· all time 98.3%

latency
1,051ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 297 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· HTTP 522
  • down → live
_ what it is for
topic
documents & files conversion
used for
  • render markdown to styled html
  • lint and fix markdown
  • convert html to markdown
  • extract plain text from markdown
takes → gives
text, web pages → text, web pages
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
4 never probed 0 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • render reads unknown never probed

    将 Markdown 内容渲染为适用于不同平台的 HTML 片段。支持 GFM 语法、数学公式（KaTeX）、代码高亮，并自动将 CSS 样式内联到元素上，确保在微信公众号等富文本编辑器中正确显示。

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "markdown"
  ],
  "properties": {
    "breaks": {
      "type": "boolean",
      "default": false,
      "description": "是否将段落内的软换行转换为 HTML 换行，不影响代码块"
    },
    "markdown": {
      "type": "string",
      "maxLength": 5242880,
      "description": "要渲染的 Markdown 源文本，支持 GFM（GitHub Flavored Markdown）语法、数学公式（$..$ 或 $$..$$）"
    },
    "platform": {
      "enum": [
        "html",
        "wechat"
      ],
      "type": "string",
      "default": "html",
      "description": "目标发布平台。wechat 会进行微信公众号适配，html 使用通用 HTML 输出"
    },
    "codeTheme": {
      "enum": [
        "catppuccin-frappe",
        "catppuccin-latte",
        "catppuccin-macchiato",
        "catppuccin-mocha",
        "kimbie-dark",
        "kimbie-light",
        "panda-syntax-dark",
        "panda-syntax-light",
        "paraiso-dark",
        "paraiso-light",
        "rose-pine",
        "rose-pine-dawn",
        "tokyo-night-dark",
        "tokyo-night-light"
      ],
      "type": "string",
      "default": "kimbie-light",
      "description": "代码块高亮主题 ID"
    },
    "customCss": {
      "type": "string",
      "default": "",
      "maxLength": 50000,
      "description": "自定义 CSS 样式，在主题样式之后应用。选择器需约束在 #bm-md 下，例如：#bm-md h1 { color: red; }"
    },
    "mermaidTheme": {
      "enum": [
        "",
        "catppuccin-latte",
        "catppuccin-mocha",
        "dracula",
        "github-dark",
        "github-light",
        "nord",
        "nord-light",
        "one-dark",
        "solarized-dark",
        "solarized-light",
        "tokyo-night",
        "tokyo-night-light",
        "tokyo-night-storm",
        "zinc-dark"
      ],
      "type": "string",
      "default": "",
      "description": "Mermaid 流程图主题 ID，空字符串表示使用默认主题"
    },
    "footnoteLabel": {
      "type": "string",
      "default": "Footnotes",
      "maxLength": 50,
      "description": "GFM 脚注区域标题"
    },
    "markdownStyle": {
      "enum": [
        "kami",
        "bauhaus",
        "blueprint",
        "botanical",
        "newsprint",
        "retro",
        "sketch",
        "terminal",
        "forest-review",
        "navy-vellum",
        "rose-nocturne",
        "solar-catalog",
        "triad-paper",
        "field-tablet",
        "public-square",
        "pixel-orbit"
      ],
      "type": "string",
      "default": "kami",
      "description": "Markdown 排版样式 ID"
    },
    "referenceTitle": {
      "type": "string",
      "default": "References",
      "maxLength": 50,
      "description": "外部链接参考区域标题"
    },
    "infographicTheme": {
      "enum": [
        "default",
        "dark",
        "hand-drawn"
      ],
      "type": "string",
      "default": "default",
      "description": "Infographic 信息图主题 ID"
    },
    "infographicPalette": {
      "enum": [
        "antv",
        "spectral"
      ],
      "type": "string",
      "default": "antv",
      "description": "Infographic 信息图配色 ID"
    },
    "enableFootnoteLinks": {
      "type": "boolean",
      "default": true,
      "description": "是否将文中链接自动转换为脚注形式，便于阅读时查看原始链接"
    },
    "openLinksInNewWindow": {
      "type": "boolean",
      "default": true,
      "description": "是否为所有外部链接添加 target=\"_blank\"，在新窗口打开"
    }
  }
}
    arguments 141 lines
  • extract reads unknown never probed

    从 Markdown 文档中提取纯文本内容，移除所有格式标记（如标题符号、链接、图片、代码块等）。适用于字数统计、文本分析、生成摘要、或作为语音朗读的输入。

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "markdown"
  ],
  "properties": {
    "markdown": {
      "type": "string",
      "maxLength": 5242880,
      "description": "要提取文本的 Markdown 源文本"
    }
  }
}
    arguments 14 lines
  • lint reads unknown never probed

    使用 markdownlint 规则对 Markdown 内容进行规范校验，并自动修复可修复的问题。包括：统一标题层级、修复列表缩进、规范空行、移除行尾空格等。

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "markdown"
  ],
  "properties": {
    "markdown": {
      "type": "string",
      "maxLength": 5242880,
      "description": "要校验和修复的 Markdown 源文本"
    }
  }
}
    arguments 14 lines
  • parse reads unknown never probed

    将 HTML 内容反向转换为 Markdown 格式。适用于从网页复制内容、导入已有文章、或将富文本转换为 Markdown 进行编辑。会自动清理不安全的 HTML 标签。

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "html"
  ],
  "properties": {
    "html": {
      "type": "string",
      "maxLength": 5242880,
      "description": "要转换的 HTML 源代码，可以是完整文档或 HTML 片段"
    }
  }
}
    arguments 14 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 99a52493dea964b6.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/99a52493dea964b6/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/99a52493dea964b6/badge.svg)](https://brick.blue/agent/99a52493dea964b6?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.