flatmark MCP server
Commit Nov 11, 2026Converts PDF, Word, PowerPoint, Excel, and HTML documents into Markdown using OCR and table detection.
Also known as flatmark-dev/flatmark-integrations
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 11, 2026
- License
- MIT
What is flatmark MCP?
flatmark converts PDF, Word, PowerPoint, Excel, and HTML documents into Markdown using OCR and table detection.
Summary generated from the project's README
About flatmark MCP server
Converting complex documents like PDF, Word, PowerPoint, Excel, and HTML into Markdown is the primary function of this server. It serves developers who need to transform various file formats into clean text for AI processing or RAG vector stores. Users can perform quick conversions for files up to 8 MB using MarkItDown in a single call. For larger files up to 25 MB or documents reaching 200 pages, the server utilizes a queue running Docling to provide OCR and table detection.
To use this service, you must provide an API key via the X-API-Key header. The server is hosted in Germany and offers a free plan that includes 100 credits per month without requiring a credit card. Developers can manage their workflow using specific operations such as convert_document for immediate tasks or submit_conversion_job to handle larger files through a queue that supports polling or signed webhooks.
What you can do with it
- 1Process large scanned documentsSubmit a large PDF to the OCR queue to extract text and tables from scanned pages.
- 2Quickly convert small filesTransform a standard Word or Excel document into Markdown using a single API call.
- 3Monitor document processing statusCheck the progress of queued conversion jobs using their unique identifiers.
- 4Manage API usage limitsCheck how many monthly credits remain on your current subscription plan.
Written from the project's README. Every use case is checked against a quote from it.
README
View on GitHubflatmark integrations
Document to Markdown API and MCP server for PDF, Word, PowerPoint, Excel and HTML. OCR queue for large files. Hosted in Germany.
flatmark converts PDF, Word, PowerPoint, Excel and HTML to Markdown over a REST API and an MCP server. Files up to 8 MB convert in one call with MarkItDown. Files up to 25 MB and 200 pages go through a queue that runs Docling with OCR and table detection. The queue returns Markdown and a JSON structure file, by polling or a signed webhook. The servers are in Germany. The free plan has 100 credits a month and needs no card.
Official integrations for the flatmark API, generated from its OpenAPI document and published from this repository.
Get an API key
Create a key and send it in the X-API-Key header.
Integrations
- Dify —
podshalocef/flatmarkon the Dify Marketplace - Python SDK —
pip install flatmark· PyPI - GitHub Action —
flatmark-dev/flatmark-actionon the GitHub Marketplace - LangChain document loader (
FlatmarkLoader) —pip install langchain-flatmark· PyPI
Templates
Ready-made automations on the API: the walkthrough on the site, the files in this repository.
| Template | Platform | Walkthrough | Files |
|---|---|---|---|
| Documents to a RAG vector store | Code | flatmark.dev/templates/documents-to-rag-vector-store | templates/documents-to-rag-vector-store |
| Large scanned PDFs through the OCR queue | Code | flatmark.dev/templates/large-scanned-pdfs-ocr-queue | templates/large-scanned-pdfs-ocr-queue |
| Folder of PDFs to Markdown notes with n8n | n8n | flatmark.dev/templates/folder-to-markdown-notes | templates/folder-to-markdown-notes |
Operations
| Operation | Endpoint | What it does |
|---|---|---|
get_me |
GET /v1/me |
Your plan, remaining requests, and remaining credits |
get_job |
GET /v1/jobs/{job_id} |
Get one queued job by ID |
list_jobs |
GET /v1/jobs |
List your queued jobs, newest first |
convert_document |
POST /v1/convert |
Convert a document to Markdown in one call |
submit_conversion_job |
POST /v1/convert/jobs |
Queue a document for conversion with OCR and tables |
get_conversion_result |
GET /v1/convert/jobs/{job_id}/result |
Download a queued job's Markdown or JSON |
API reference: https://flatmark.dev/docs · Base URL: https://api.flatmark.dev
Support
Every file listed in .generated is rebuilt from the live API; changes to them are overwritten.
flatmark MCP questions
What file formats does flatmark support?
The service supports PDF, Word, PowerPoint, Excel, and HTML.
How much does the free plan cost?
The free plan provides 100 credits per month and does not require a credit card.
How are large files processed?
Files up to 25 MB and 200 pages are processed through an OCR queue that uses Docling for OCR and table detection.
Where are the servers located?
The servers are hosted in Germany.