modelcontextprotocol / modelcontextprotocol/servers
[Filesystem] - File Options
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 90.5k
- Forks
- 11.7k
- Avg merge
- 2d 2h
- Merged PRs (30d)
- 5
Description
Is your feature request related to a problem? Please describe.
I would like to get some basic information of file contents like row count, header, first n-rows, last n-rows.
It is currently trying to load/read the entire file and fails if the file is larger than certain size on claude desktop(windows 11, 32gb memory)
Describe the solution you'd like
Add methods to work on file content without reading entire content.
Either streaming/line by line/buffered or other memory efficient methods.
Describe alternatives you've considered
A python based filesystem server or alternative js packages if the current implementation/packages can only handle very small files.
Additional context
Tried with reading entire csv(method: read_file) with 10 columns and:
500 rows(failed)
100 rows(failed)
5 rows(succeeded)
Contributor guide
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 by locating the filesystem server entry point and the existing read_file method mentioned in the issue. Review how file contents are currently read, then clarify the API needed for row counts, headers, and first or last rows without loading the whole file; done should include behavior that works for files larger than the reported limit.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100