What formats does Go Docs Mcp support?
PDF, TXT, MD, CSV, DOCX, and images (PNG, JPG, TIFF). TXT, MD, and CSV have zero dependencies; PDF requires poppler; DOCX requires pandoc; images require tesseract.
Go Docs MCP Server
@drolosoft
Basic information
About Go Docs MCP Server
Multi-format document MCP server — read, search, OCR, and extract from PDF, TXT, MD, DOCX, CSV, and images. Single Go binary, 12 tools, smart caching.
Go Docs MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"docs": {
"command": "go-docs-mcp",
"env": {
"DOCS_MCP_DIR": "/path/to/your/documents"
}
}
}
}Go Docs MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Go Docs Mcp?
Go Docs Mcp is a Go-based MCP server that provides multi-format document access — reading, searching, extracting images, OCR, and fetching documents from URLs — for AI assistants via the Model Context Protocol.
How to use Go Docs Mcp?
Install with go install github.com/drolosoft/go-docs-mcp@latest. Configure the document directory via the DOCS_MCP_DIR environment variable (default ~/.docs-mcp/documents/). The server communicates over stdio and can be added to Claude Code or Claude Desktop settings, or used directly with any MCP client.
Key features of Go Docs Mcp
- Multi-format support (PDF, TXT, MD, CSV, DOCX, images)
- Full-text search with context and page hints
- OCR for scanned documents and images
- Image extraction from documents as base64
- Directory-locked, read-only access for security
- Single binary, no runtime dependencies
Use cases of Go Docs Mcp
- An AI assistant reading a PDF report and answering questions about its content.
- Searching for keywords across a collection of local documents.
- Extracting tables from a DOCX file as structured data.
- OCR-ing a scanned contract to extract text from images.
- Fetching a document from a URL and reading its content directly.
Frequently asked questions
What dependencies are required?
Go 1.25+ for building, poppler for PDF support, and optionally tesseract for OCR and pandoc for DOCX. TXT, MD, and CSV work out of the box.
How does Go Docs Mcp compare to other document MCP servers?
Unlike single-format servers, Go Docs Mcp handles six formats in one binary and offers OCR, image extraction, table extraction, and URL fetching — all with a single `go install` command.
Where are documents stored and how is access controlled?
Documents are read from a directory configured via `DOCS_MCP_DIR` (default `~/.docs-mcp/documents/`). The server enforces directory-locked, read-only access with path traversal prevention.
What transport and authentication does Go Docs Mcp use?
It uses stdio transport with JSON-RPC 2.0. No authentication is mentioned; security is handled via directory-locked access and read-only operations.
More Memory & Knowledge MCP servers
M1K3
Round-TowerLocal AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.
7
Leviathan Systems Public Content MCP
Leviathan SystemsSearch published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.
Agimem
Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
Takibi Base
Deian IsacAsk your Takibi Base collections anything; get answers with cited passages and a support score.
ctxfile
ctxfileLocal-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
2
Comments