go-docs-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PDF_MCP_DIR | No | Backward-compatible alias for DOCS_MCP_DIR | |
| DOCS_MCP_DIR | No | Directory containing documents to serve | ~/.docs-mcp/documents/ |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Start with list_documents to see which files exist, then call get_document_outline to learn how a document is organised before reading it. Use search_document to find the pages that answer the question, and read_document with page or pages to read only those instead of the whole file. For long text without pages, read_document takes offset and max_chars to read it in slices. Every document is also a docs://{filename} resource with the same text.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| convert_to_markdownA | Convert a document to clean Markdown format. Use this when you need structured, readable output from any document; for PDFs headings are detected and formatted, for TXT/CSV content is wrapped in code blocks, and MD files are returned as-is. Long output comes in pages of max_chars characters, like read_document. Read-only. |
| extract_imagesA | Extract the embedded images of a PDF as PNG image content, scaled to at most 1600 px on the longer side, 10 per call by default and 8 MB in total. Soft masks are not returned as images. Use this when you need to see figures, charts, or photos embedded in a PDF document. Read-only. |
| extract_tablesA | Extract table-like structures from a document, detecting pipe-delimited, tab-delimited, and multi-space-delimited columns. Use this when you need structured tabular data from a PDF, CSV, or text file. Read-only. |
| get_document_metadataA | Get document metadata including title, author, dates, page count, and file size. Use this when you need document properties without reading its content; returns full PDF-specific fields (subject, creator, producer, version) for PDF files. Read-only. |
| get_document_outlineA | Extract the heading structure and table of contents from a document. Use this to understand document organization before reading specific sections; detects numbered sections, ALL-CAPS headings, and markdown # headings. Read-only. |
| get_document_summaryA | Get a quick summary by extracting the first 3 pages or ~100 lines of a document. Use this to preview document content before deciding to read it in full. Read-only. |
| list_documentsA | List all documents in the configured directory with format detection and metadata (filename, pages, size). Use this to discover available documents before reading or searching. Read-only. |
| list_formatsA | Show all supported document formats and their dependency installation status. Use this to check which formats are available and diagnose missing dependencies. Read-only. |
| ocr_documentA | Force OCR text extraction on a PDF, bypassing normal text extraction. Use this when read_document returns garbled or empty text from a scanned PDF; requires tesseract and pdftoppm. Read-only. |
| read_documentA | Read text content from a document with optional page selection. Use this when you need the raw text of a PDF, TXT, MD, CSV, DOCX, XLSX, PPTX, ODT, EPUB, HTML, RTF or IPYNB file; TXT/MD/CSV are returned verbatim, the Office, EPUB, HTML, RTF and notebook formats via pandoc; PDFs support page ranges (e.g. "1-5", "1-3,7,10-12") and auto-OCR fallback for scanned pages. Long texts come in pages of max_chars characters; a truncated result ends with the offset to ask for next. Read-only. |
| read_imageA | Extract text from a standalone image file (PNG, JPG, WebP, TIFF, BMP) using OCR. Use this when you need to read text from an image rather than a document; supports multiple languages via tesseract. Read-only. |
| read_urlA | Download a document from a URL and extract its text content (max 50MB). Use this when the document is hosted online rather than in the local directory; supports PDF and plain text URLs. Read-only, downloads to a temporary file. |
| search_documentA | Search for text within a document and return matching lines with context and approximate page numbers. Use this when you need to find specific content without reading the entire document. Read-only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Each tool targets a distinct operation: discovery (list_documents, list_formats), inspection (metadata, outline, summary), extraction (read_document, extract_images, extract_tables), and search/OCR. There is mild overlap between get_document_summary and read_document, and between ocr_document and read_document's built-in auto-OCR fallback, but descriptions clearly steer usage.
All 13 tools follow a consistent snake_case verb_noun pattern (get_document_metadata, extract_tables, list_documents, read_url, search_document). Verb choices are semantically meaningful rather than arbitrary, and there is no mixing of conventions.
13 tools is well within the ideal 3-15 range for a document-reading server. Each tool covers a distinct capability (format discovery, dependency check, per-content-type extraction) without redundant entries.
The read-only surface is thorough: listing, metadata, outline, summary, full text, search, format conversion, image/table extraction, standalone image OCR, and URL ingestion. Minor gaps exist around saving/exporting converted output or batch-reading multiple local documents, but agents can work around these.