`extract_headings`

Pack: markdown · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/extract_headings for the schema, then POST the same URL with its arguments for the data.

Extract the ATX heading outline (# … ######) as {level, text} entries (keyless, offline).

Parameters

Name	Type	Required	Description
`markdown`	string	yes	The Markdown text.

Example call

Arguments

{
  "markdown": "# Introduction\n## Getting Started\n### Installation\n## Usage\n# Conclusion"
}

curl

curl -X POST https://gateway.pipeworx.io/markdown/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"extract_headings","arguments":{"markdown":"# Introduction\n## Getting Started\n### Installation\n## Usage\n# Conclusion"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('extract_headings', {
  "markdown": "# Introduction\n## Getting Started\n### Installation\n## Usage\n# Conclusion"
});

More examples

{
  "markdown": "# Main Title\n## First Section\n### Subsection\n## Second Section"
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://pipeworx.io/mcp"
    }
  }
}

Connect to just the markdown pack

{
  "mcpServers": {
    "markdown": {
      "url": "https://gateway.pipeworx.io/markdown/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

extract_headings