# go-docs-mcp

go-docs-mcp — an MCP server for Claude Code gives your assistant direct access to 14 file formats and OCR text extraction. Runs when searching local files or requesting document resources via docs://.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12 repo stars
- Author: drolosoft
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/drolosoft/go-docs-mcp
- Updated: 2026-11-15
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/go-docs-mcp

## What it does

The server exposes 13 tools over standard I/O to inspect, parse, and convert documents inside the folder set by `DOCS_MCP_DIR`. Text endpoints accept `offset` and `max_chars`, preventing multi-megabyte files from overflowing the context window. Files in the directory appear automatically as `docs://<filename>` resources.

Plain text, Markdown, and CSV files work out of the box with zero extra software. Processing PDF files relies on system `poppler` binaries. Converting Office documents, EPUB, RTF, and Jupyter notebooks requires `pandoc`, while image text extraction and scanned pages depend on `tesseract`.

Running the provided Docker image avoids manual setup because it bundles poppler, pandoc, and tesseract together.

## Requirements
- Needs: Docker
- Environment variables: `DOCS_MCP_DIR`, `DOCS_MCP_OCR_LANG`, `DOCS_MCP_DISABLE_URL` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env DOCS_MCP_DIR=<DOCS_MCP_DIR> --env DOCS_MCP_OCR_LANG=<DOCS_MCP_OCR_LANG> --env DOCS_MCP_DISABLE_URL=<DOCS_MCP_DISABLE_URL> --transport stdio go-docs-mcp -- docker run -i --rm -e DOCS_MCP_DIR -e DOCS_MCP_OCR_LANG -e DOCS_MCP_DISABLE_URL ghcr.io/drolosoft/go-docs-mcp:1.5.0
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add go-docs-mcp --env DOCS_MCP_DIR=<DOCS_MCP_DIR> --env DOCS_MCP_OCR_LANG=<DOCS_MCP_OCR_LANG> --env DOCS_MCP_DISABLE_URL=<DOCS_MCP_DISABLE_URL> -- docker run -i --rm -e DOCS_MCP_DIR -e DOCS_MCP_OCR_LANG -e DOCS_MCP_DISABLE_URL ghcr.io/drolosoft/go-docs-mcp:1.5.0
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "go-docs-mcp": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "DOCS_MCP_DIR",
                "-e",
                "DOCS_MCP_OCR_LANG",
                "-e",
                "DOCS_MCP_DISABLE_URL",
                "ghcr.io/drolosoft/go-docs-mcp:1.5.0"
            ],
            "env": {
                "DOCS_MCP_DIR": "<DOCS_MCP_DIR>",
                "DOCS_MCP_OCR_LANG": "<DOCS_MCP_OCR_LANG>",
                "DOCS_MCP_DISABLE_URL": "<DOCS_MCP_DISABLE_URL>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "go-docs-mcp": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "DOCS_MCP_DIR",
                "-e",
                "DOCS_MCP_OCR_LANG",
                "-e",
                "DOCS_MCP_DISABLE_URL",
                "ghcr.io/drolosoft/go-docs-mcp:1.5.0"
            ],
            "env": {
                "DOCS_MCP_DIR": "<DOCS_MCP_DIR>",
                "DOCS_MCP_OCR_LANG": "<DOCS_MCP_OCR_LANG>",
                "DOCS_MCP_DISABLE_URL": "<DOCS_MCP_DISABLE_URL>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e DOCS_MCP_DIR=<DOCS_MCP_DIR> -e DOCS_MCP_OCR_LANG=<DOCS_MCP_OCR_LANG> -e DOCS_MCP_DISABLE_URL=<DOCS_MCP_DISABLE_URL> go-docs-mcp docker run -i --rm -e DOCS_MCP_DIR -e DOCS_MCP_OCR_LANG -e DOCS_MCP_DISABLE_URL ghcr.io/drolosoft/go-docs-mcp:1.5.0
```
Replace <…> with your own values

## When to use it
- extract text and tables from `DOCX` and `XLSX` files
- recognize text in image files and scanned pages using OCR
- fetch specific page ranges from heavy PDF reports
- search across files in the document folder for matching phrases

## Example prompts
- Search my document folder for the Q3 report and show the budget table
- Run OCR on the scan in `invoice.png` and extract all text
- Extract the heading outline from `spec.docx` and convert it into Markdown

## Similar
- [pdf-processing-pro](https://affpapa.org/en/nevibecode/skills/pdf-processing-pro.md) — skill · 5869 installs
- [liteparse](https://affpapa.org/en/nevibecode/skills/k-dense-ai-liteparse.md) — skill · 1700 installs
- [pdf-to-structured](https://affpapa.org/en/nevibecode/skills/pdf-to-structured.md) — skill · 149 installs
- [pdf](https://affpapa.org/en/nevibecode/skills/shareai-lab-pdf.md) — skill · ★ 80707 repo stars
- [whitepaper](https://affpapa.org/en/nevibecode/skills/whitepaper.md) — skill · 1600 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
