microsoft / microsoft/markitdown
MCP has no option to write the markdown to a file
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 186k
- Forks
- 13.7k
- Avg merge
- 1d 4h
- Merged PRs (30d)
- 49
Description
If the PDF is too large, using the MCP exceeds the maximum tokens. But there is no option to use the MCP to output to a file.
Claude Code
I'll help you convert that PDF to markdown and update the memory/claude.md with the PDF reading tip.
⏺ markitdown - convert_to_markdown (MCP)(uri: "file:///Volumes/Dev/Work/Gondola_Dev/Illustrations/Lincoln/Lincoln FL.pdf")
⎿ Error: MCP tool "convert_to_markdown" response (51164 tokens) exceeds maximum allowed tokens (25000). Please use pagination, filtering, or limit parameters to reduce the response size.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the MCP convert_to_markdown entry point and inspect how its markdown response is returned. Add an output-to-file option that avoids exceeding the MCP token limit, then verify it with a large PDF like the reported Lincoln FL.pdf example.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- tooling
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100