
go-docs-mcp
Lets your AI read PDF, Office files, EPUB, HTML, Jupyter and images, with OCR, search and paging.
- GitHub stars
- 12
- tools
- 13
- auth
- Required
- transport
- STDIO
- env vars
- 3
- last updated
- Nov 9, 2026
Tools
13 toolsPublic tool metadata for what this MCP can expose to an agent.
list_documentsList all documents with metadata (format, pages, size)
List all documents with metadata (format, pages, size)
No parameter schema in public metadata yet.
list_formatsList supported formats and dependency status
List supported formats and dependency status
No parameter schema in public metadata yet.
read_documentFull text, specific page, or page ranges from any format
Full text, specific page, or page ranges from any format
No parameter schema in public metadata yet.
read_urlDownload from URL and extract text (50MB max)
Download from URL and extract text (50MB max)
No parameter schema in public metadata yet.
get_document_summaryFirst 3 pages as a quick overview
First 3 pages as a quick overview
No parameter schema in public metadata yet.
search_documentCase-insensitive full-text search with context
Case-insensitive full-text search with context
No parameter schema in public metadata yet.
get_document_metadataTitle, author, dates, version, page count
Title, author, dates, version, page count
No parameter schema in public metadata yet.
get_document_outlineHeading structure deduced from the text
Heading structure deduced from the text
No parameter schema in public metadata yet.
extract_tablesTables as structured data
Tables as structured data
No parameter schema in public metadata yet.
extract_imagesImages as PNG image content, scaled to fit (max 10 per call, 8 MB budget)
Images as PNG image content, scaled to fit (max 10 per call, 8 MB budget)
No parameter schema in public metadata yet.
ocr_documentForce OCR on scanned/image-based PDFs
Force OCR on scanned/image-based PDFs
No parameter schema in public metadata yet.
read_imageExtract text from PNG, JPG, WebP, TIFF, BMP via OCR
Extract text from PNG, JPG, WebP, TIFF, BMP via OCR
No parameter schema in public metadata yet.
convert_to_markdownConvert any document to clean Markdown
Convert any document to clean Markdown
No parameter schema in public metadata yet.
Sponsors
Configuration
DOCS_MCP_DIR*Folder with the documents to serve.
DOCS_MCP_OCR_LANGdefault: engTesseract language for OCR, for example spa or eng+spa.
DOCS_MCP_DISABLE_URLdefault: falsetrue removes the read_url tool.
Readme
Go-Docs MCP
Go-Docs MCP
Install and Go. One command, single binary. Your AI reads any document: PDF, text, Markdown, Office files, EPUB, HTML, notebooks, images.
MCP server for multi-format document access: read, search, extract images, OCR, and fetch documents from URLs via the Model Context Protocol. 13 tools, 14 formats, zero configuration.
Details
- Repository
- github.com/drolosoft/go-docs-mcp
- Website
- drolosoft.com/go-docs-mcp.html
- Categories
- Documents & Knowledge, Search & Web Crawling, Data & Analytics, Productivity & Office
- Package
https://github.com/drolosoft/go-docs-mcp/releases/download/v1.5.0/go-docs-mcp_1.5.0.mcpb- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active