read_document

MCP tool from Go Docs MCP by drolosoft

Reads the extracted text content of a document. Automatically falls back to OCR if the document is image-based/scanned and pdftotext returns empty text.

How to use it

read_document is exposed by the Go Docs MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the read_document tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Go Docs MCP

$go install github.com/drolosoft/go-docs-mcp@latest

FULL GO DOCS MCP LISTING

Other tools in Go Docs MCP (18)

extract_images

Extracts images from a document as base64-encoded data. Returns up to 10 images per call.

extract_tables

Extracts tables from a document as structured data.

filename

string

get_document_metadata

Returns full document metadata.

get_document_outline

Extracts the document outline (table of contents / bookmarks) as a structured list.

get_document_summary

Returns the text from the first 3 pages of a document as a quick summary.

language

string

list_documents

Lists all documents in the configured directory with format detection.

list_formats

Lists all supported document formats and their dependency status.

Multi-format

PDF, TXT, MD, CSV, DOCX, and images from one server

ocr_document

Forces OCR on a PDF document using tesseract. Useful for scanned/image-based PDFs or when pdftotext returns garbled text. Requires tesseract and pdftoppm.

number

string

string

Extracts text from an image file using OCR. Supports PNG, JPG, and TIFF. Requires tesseract.

read_url

Downloads a document from a URL and extracts its text content. Maximum file size: 50MB.

search_document

Searches within a document for lines matching a query. Returns matches with 2 lines of context and approximate page numbers.

url

string