AgentMD

Official2 tools

by djrobson5 · JavaScript

Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved

agentmd-mcp MCP Server

The io.github.djrobson5/agentmd MCP server converts PDF, DOCX, HTML, and URLs into clean, LLM-ready markdown. It preserves tables while stripping web-page boilerplate, producing output intended for agent ingestion. The project is described as “agentmd-mcp,” with two tools exposed by the server.

🛠️ Key Features

Convert PDF, DOCX, HTML, and URLs to markdown
Preserve tables
Strip web-page boilerplate
Provides a total of 2 tools

🚀 Use Cases

Prepare document content for agents that ingest documents continuously
Convert source formats that are difficult for language models into readable markdown

⚡ Developer Benefits

Produces clean, LLM-ready markdown
Maintains table structure during conversion

⚠️ Limitations

Supported inputs are limited to PDF, DOCX, HTML, and URLs (per description)

Captured live from the server via tools/list.

convert_url_to_markdown

Fetch a URL (web page, PDF, DOCX, etc.) and convert it to clean, LLM-ready markdown. Extracts the main article content from web pages and preserves tables. Supports reading only part of a large document: PDF page ranges, a heading outline, a single section, or a token cap.

Parameters5

url	string	required	The http(s) URL of the document or page to convert
pages	string	optional	PDFs only: 1-indexed, inclusive page ranges to convert, e.g. "1-3,5,8-" (an open-ended range runs to the last page). Ignored with a warning for non-PDF formats.
mode	string	optional	"full" (default) returns the document body. "outline" returns just the heading tree — each line is `- [#3] Heading text (~120 tokens)`. For a long document, call with mode: 'outline' first, then fetch only what you need with section: '#3' or a heading title.
section	string	optional	Return only one section: either "#<n>" using the index from a mode: 'outline' call (e.g. '#3'), or the heading text itself (case-insensitive; exact match wins, then prefix, then substring). Ignored when mode is 'outline'.
maxTokens	integer	optional	Cap the returned markdown at roughly this many tokens, cutting at a paragraph boundary. When the output is cut, the result starts with a `> Truncated: ~X of ~Y tokens` line — narrow with pages or section rather than raising this.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The http(s) URL of the document or page to convert"
    },
    "pages": {
      "description": "PDFs only: 1-indexed, inclusive page ranges to convert, e.g. \"1-3,5,8-\" (an open-ended range runs to the last page). Ignored with a warning for non-PDF formats.",
      "type": "string"
    },
    "mode": {
      "description": "\"full\" (default) returns the document body. \"outline\" returns just the heading tree — each line is `- [#3] Heading text (~120 tokens)`. For a long document, call with mode: 'outline' first, then fetch only what you need with section: '#3' or a heading title.",
      "type": "string",
      "enum": [
        "full",
        "outline"
      ]
    },
    "section": {
      "description": "Return only one section: either \"#<n>\" using the index from a mode: 'outline' call (e.g. '#3'), or the heading text itself (case-insensitive; exact match wins, then prefix, then substring). Ignored when mode is 'outline'.",
      "type": "string"
    },
    "maxTokens": {
      "description": "Cap the returned markdown at roughly this many tokens, cutting at a paragraph boundary. When the output is cut, the result starts with a `> Truncated: ~X of ~Y tokens` line — narrow with pages or section rather than raising this.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "url"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

convert_document_to_markdown

Convert a document you already have (PDF, DOCX, HTML, plain text) to clean, LLM-ready markdown. Pass the file contents as base64. Supports reading only part of a large document: PDF page ranges, a heading outline, a single section, or a token cap.

Parameters6

base64	string	required	Base64-encoded file contents
filename	string	optional	Original filename, e.g. report.pdf — helps format detection
pages	string	optional	PDFs only: 1-indexed, inclusive page ranges to convert, e.g. "1-3,5,8-" (an open-ended range runs to the last page). Ignored with a warning for non-PDF formats.
mode	string	optional	"full" (default) returns the document body. "outline" returns just the heading tree — each line is `- [#3] Heading text (~120 tokens)`. For a long document, call with mode: 'outline' first, then fetch only what you need with section: '#3' or a heading title.
section	string	optional	Return only one section: either "#<n>" using the index from a mode: 'outline' call (e.g. '#3'), or the heading text itself (case-insensitive; exact match wins, then prefix, then substring). Ignored when mode is 'outline'.
maxTokens	integer	optional	Cap the returned markdown at roughly this many tokens, cutting at a paragraph boundary. When the output is cut, the result starts with a `> Truncated: ~X of ~Y tokens` line — narrow with pages or section rather than raising this.

Raw schema

{
  "type": "object",
  "properties": {
    "base64": {
      "type": "string",
      "description": "Base64-encoded file contents"
    },
    "filename": {
      "description": "Original filename, e.g. report.pdf — helps format detection",
      "type": "string"
    },
    "pages": {
      "description": "PDFs only: 1-indexed, inclusive page ranges to convert, e.g. \"1-3,5,8-\" (an open-ended range runs to the last page). Ignored with a warning for non-PDF formats.",
      "type": "string"
    },
    "mode": {
      "description": "\"full\" (default) returns the document body. \"outline\" returns just the heading tree — each line is `- [#3] Heading text (~120 tokens)`. For a long document, call with mode: 'outline' first, then fetch only what you need with section: '#3' or a heading title.",
      "type": "string",
      "enum": [
        "full",
        "outline"
      ]
    },
    "section": {
      "description": "Return only one section: either \"#<n>\" using the index from a mode: 'outline' call (e.g. '#3'), or the heading text itself (case-insensitive; exact match wins, then prefix, then substring). Ignored when mode is 'outline'.",
      "type": "string"
    },
    "maxTokens": {
      "description": "Cap the returned markdown at roughly this many tokens, cutting at a paragraph boundary. When the output is cut, the result starts with a `> Truncated: ~X of ~Y tokens` line — narrow with pages or section rather than raising this.",
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "base64"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

README.md3 KBView on GitHub

agentmd-mcp

MCP server for AgentMD — convert PDF, DOCX, HTML, and URLs into clean, LLM-ready markdown, with tables preserved and web-page boilerplate stripped.

Agents ingest documents constantly, and most document formats are hostile to language models. This gives your agent three tools that turn any of them into markdown it can actually read.

Install

Get a free API key (50 conversions, no card) at https://www.getagentmd.com — or fully programmatically:

bash

curl -X POST https://www.getagentmd.com/api/v1/keys/free \
  -H "Content-Type: application/json" -d '{"email": "you@example.com"}'

Then:

Claude Code

bash

claude mcp add agentmd --env AGENTMD_API_KEY=<your-key> -- npx -y agentmd-mcp

Any MCP client (mcp.json / claude_desktop_config.json):

json

{
  "mcpServers": {
    "agentmd": {
      "command": "npx",
      "args": ["-y", "agentmd-mcp"],
      "env": { "AGENTMD_API_KEY": "<your-key>" }
    }
  }
}

Docker

bash

docker build -t agentmd-mcp .
docker run -i --rm -e AGENTMD_API_KEY=<your-key> agentmd-mcp

The image runs the stdio server, so pass -i; the API key is supplied at run time with -e rather than baked into the image. To wire the container into an MCP client:

json

{
  "mcpServers": {
    "agentmd": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "AGENTMD_API_KEY", "agentmd-mcp"],
      "env": { "AGENTMD_API_KEY": "<your-key>" }
    }
  }
}

Remote (no install) — the hosted server speaks streamable HTTP directly:

bash

claude mcp add --transport http agentmd https://www.getagentmd.com/api/mcp \
  --header "Authorization: Bearer <your-key>"

Tools

Tool	Use it for
`convert_url_to_markdown`	A web page or a document at an http(s) URL
`convert_file_to_markdown`	A document on the local filesystem, by path
`convert_document_to_markdown`	Document bytes you already hold, as base64

All three return markdown, prefixed with the detected title and any warnings.

Supported formats

PDF — text extraction (scanned/image-only PDFs return a warning; OCR is on the roadmap)
DOCX — headings, lists, and tables preserved
HTML / URLs — main-article extraction, GFM tables, links resolved to absolute URLs
Markdown / plain text — normalized passthrough

Limit: 25 MB per document.

Configuration

Variable	Required	Purpose
`AGENTMD_API_KEY`	yes	Your API key
`AGENTMD_BASE_URL`	no	Point at a different deployment (self-hosting, staging)

Pricing

First 50 conversions free (per email, no card). After that, $0.002 per successful conversion, billed monthly. No per-seat licensing — you pay for calls your agents actually make.

License

MIT (this client shim). The hosted service has its own terms.

Install

Tools (2)

convert_url_to_markdownconvert_document_to_markdown

Configuration

Environment variables

AGENTMD_API_KEYrequiredsecret

API key from https://www.getagentmd.com

AGENTMD_BASE_URL

Override the API base URL (self-hosting or staging)

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agentmd": {
      "command": "npx",
      "args": [
        "-y",
        "agentmd-mcp@0.1.4"
      ],
      "env": {
        "AGENTMD_API_KEY": "<YOUR_AGENTMD_API_KEY>",
        "AGENTMD_BASE_URL": "<YOUR_AGENTMD_BASE_URL>"
      }
    }
  }
}

agentmd-mcp MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

convert_url_to_markdown

convert_document_to_markdown

agentmd-mcp

Install

Tools

Supported formats

Configuration

Pricing

License

Install

Configuration

Related servers