MCP server · Productivity
Go-Docs MCP server
by drolosoft
Lets your AI read, search and pull text from your PDFs, Word files, spreadsheets and images.
Go-Docs MCP is a small helper program that lets your AI assistant open and read documents sitting in a folder on your computer. It handles PDFs, plain text, Markdown, CSV, Word files and images, and can even read scanned pages by recognizing the text in them. It is handy if you often ask your AI questions about reports, contracts or manuals you have saved locally.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. It cannot open a file on your computer unless something gives it that ability. An MCP server is a small helper program that hands your AI a new skill, and here that skill is reading and searching documents in a folder you choose. Once it is connected, you can just ask your AI about a file and it will go look it up for you.
What this MCP server does
You point the helper at one folder on your computer where your documents live. When you ask your AI something about a file, the AI sends the request to this helper, and the helper opens the file and pulls out the text. For scanned PDFs or pictures, it can read the words using a text-recognition step. The AI then answers you in the chat using what it found, and it never changes or deletes your files.
Click to zoomWhat you can do with it
- List all documents in your chosen folder with their format and size
- Read the full text of a PDF, Word file, text file, Markdown or CSV
- Read just one page or a range of pages, like pages 1 to 5
- Search inside a document for a word and see the matching lines
- Pull out the table of contents or bookmarks from a document
- Extract tables or images from a document
- Read text from a scanned PDF or an image file like a photo of a receipt
- Download a document from a web address and read its text
Try asking your AI
- “What is the summary of architecture-guide.pdf?”
- “Find every mention of microservice in the contract PDF”
- “Read pages 1 to 3 of the report I downloaded”
- “What does the receipt.png image say?”
What it gives back to you
You get back plain answers in the chat: the text of a document, a short summary of the first pages, a list of matching lines with a bit of context, a list of files, or details like the author and page count. Tables come back as structured rows, and images come back as picture data. Everything shows up as normal chat text you can read or copy.
Before you start
What you need
- A folder on your computer with the documents you want your AI to read
- Go 1.25 or newer to install the program
- poppler installed for PDF support (a free set of PDF tools)
- tesseract installed if you want to read scanned pages or images (optional)
- pandoc installed if you want to read Word documents (optional)
Good to know
It only reads files inside the folder you set, and it never changes or deletes anything, so it is safe to try.
Install it with your AI
Add Go-Docs MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Go-Docs MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Anyone who works with a lot of PDFs, reports, contracts or scanned paperwork on their own computer and wants their AI to read them without copying and pasting.
