read_pdf
Extract text content, metadata, and page counts from PDF files using relative paths or URLs within your project context.
Instructions
Reads content/metadata from PDFs. Paths must be relative to the project root. Project root can be set via: 1) --root command line argument, 2) PDF_READER_MCP_ROOT environment variable, or 3) process.cwd() (default). Absolute paths in the path parameter are rejected.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sources | Yes | An array of PDF sources to process, each can optionally specify pages. | |
| include_full_text | Yes | Include the full text content of each PDF (only if 'pages' is not specified for that source). | |
| include_metadata | Yes | Include metadata and info objects for each PDF. | |
| include_page_count | Yes | Include the total number of pages for each PDF. |