Reported issues for reMarkable MCP Server

Pod holds 20 of 30 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to reMarkable MCP Server.

Most discussed

remarkable_image fails in Claude Desktop/Web with "cairo library missing", but works in MCP Inspector

I'm seeing inconsistent behavior between MCP Inspector and Claude.

• remarkable_browse works correctly.
• remarkable_read works correctly.
• remarkable_image works correctly in MCP Inspector.
• However, Claude always reports "cairo library missing" when it tries to use remarkable_image.

Because Inspector successfully generates PNG images, it doesn't appear that Cairo is actually missing on the server.

Environment

• remarkable-mcp: 1.0.0
• Started with:

npx -y mcp-

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/137) · 2026-07-21 · closed · external user · 4 comments

### Unable to review handwritten notes

I'm unable to review my handwritten notes with Google Vision. I'm using the USB web interface. I've tried creating new notebooks for testing and I'm running the latest firmware. This is the error message in claude cowork. 

**Unfortunately, all your notebooks are in an older reMarkable format (v5) that the current integration can't extract text or render images from. This affects all 6 of your recent documents**

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/102) · 2026-06-08 · closed · external user · 2 comments

### 400 Bad Request on sync/v3 endpoint - Cloud authentication fails despite valid device token

**Environment**
- OS: Windows 11
- remarkable-mcp version: latest (uvx remarkable-mcp)
- Transport: Cloud (REMARKABLE_TOKEN via environment variable)
- reMarkable Connect subscription: active

**Problem**
Authentication always fails with 400 Bad Request on a specific sync/v3 URL.
The URL and hash are always identical regardless of token:

  400 Client Error: Bad Request for url:
  https://internal.cloud.remarkable.com/sync/v3/files/8a2469797b082cbe6ad8ff9fc5a4b8ca161cc44f59542ebc9d3ace1ce5ee32dc

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/101) · 2026-06-06 · closed · external user · 4 comments

### Can't get it to work

Man, I love the idea of this project, but I haven't been able to get it to work.  In USB mode it appears that the image generation is failing, so it can't do OCR to extract text.  Even if cloud mode is slow, I'd be willing to live with it to give it a go, but it fails with bad request, despite me copying and pasting the generated key output from the terminal.

Any suggestions are welcome!

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/94) · 2026-05-20 · closed · external user · 6 comments

### remarkable_read fails in cloud mode with coroutine error

## Description

`remarkable_read()` fails in cloud mode (both 0.7.0 and 0.8.0) with the following error:

```json
{
  "_error": {
    "type": "read_failed",
    "message": "the JSON object must be str, bytes or bytearray, not coroutine",
    "suggestion": "Check remarkable_status() to verify your connection."
  }
}

Reproduction

1. Connect via cloud mode (environment variable token)
2. Verify connection works: remarkable_status() → authenticated: true, document_count: 67
3. Verify

Read the thread · 2026-03-05 · closed · external user · 3 comments

Error reading notebook with handwritten notes

The two tools are attempted for use: remarkable_read and remarkable_image for this notebook, which the Claude Code in VS Code on MacOS did find using remarkable_search. However, I get this error:

{
  "_error": {
    "type": "render_failed",
    "message": "Failed to render page to image.",
    "suggestion": "Make sure 'rmc' and 'cairosvg' are installed. Try: uv add rmc cairosvg"
  }
}

I do have the MCP setup like this:

    "remarkable": {
      "command": "uvx",
      "args

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/52) · 2026-02-01 · closed · external user · 2 comments

### Alternative to SSH or Cloud Connection

Hey, 

I was wondering if it's possible to use alternatives for the cloud connection or ssh connection, such as a fire t integration with RMAPI which can simulate a Linux desktop app to obtain the files. 

Would this be something that would be useful to this?

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/51) · 2026-02-01 · closed · external user · 3 comments

### Export in pdf, ocr via google gemini

Thanks for your incredible work!

I'm wondering why you chose google vision api, if let's say gemini flash can do the trick with pdf even simpplier and with a way better quality?

Thanks, af

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/44) · 2026-01-12 · closed · external user · 4 comments

## Most recent

### remarkable_read and remarkable_image disagree on total_pages for handwritten notebooks

One more from Claude, so the usual grain of salt applies:

For a notebook that's mostly handwriting, `remarkable_read` reports `total_pages` as the number of extracted text segments (`len(notebook_pages)`), which collapses to 1 when there's little or no typed text. `remarkable_image` reports the real document page count. So the same seven page notebook answers 1 from one tool and 7 from the other.

This affects any client that reads first and then iterates pages using the count it was given. Not

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/165) · 2026-08-14 · closed · external user · 1 comment

### render_merged is opt-in, so agents silently get inkless renders of annotated PDFs

Claude has filed this one too, but pretty sure it's right!

After #159 the merged PDF and annotation rendering works really well, but `remarkable_image` defaults to `render_merged=False`. A client that doesn't pass the flag follows the annotation-only path: a page with ink renders as bare strokes floating on the background with no PDF page beneath them, and a page without ink falls back to rasterizing the clean source PDF. Neither response mentions the missing layer. This is a bad bug for agent 

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/164) · 2026-08-14 · closed · external user · 1 comment

### default nix configuration module does not even build

git commit version: `d0f98094626bb2fb49c32b10bfb8fcc6b732966d`

error:

building the system configuration... error: … while calling the 'derivationStrict' builtin at «nix-internal»/derivation-internal.nix:37:12: 36| 37| strict = derivationStrict drvAttrs; | ^ 38|

   … while evaluating derivation 'nixos-system-nixos-26.11pre1050399.279b4a8275f0'
     whose name attribute is located at /nix/store/dy2m3gv51jdklsi

Read the thread · 2026-08-14 · closed · external user · 1 comment

Fresh installs broken: unbounded mcp dependency now resolves to the 2.0 SDK

Thanks for building this! Browsing and OCR-ing a reMarkable library over MCP is exactly what I needed, and the transport fallback design is really nice. This is going to make using my tablet so much nicer!

Claude has filed this, so please take with a grain of salt:

Fresh installs are currently broken: pyproject.toml declares mcp>=1.27.0 with no upper bound, and the MCP Python SDK has released 2.0.0, which removes the mcp.server.fastmcp module path that server.py imports. A clean instal

Read the thread · 2026-08-11 · closed · external user · 1 comment

ModuleNotFoundError: No module named 'mcp.server.fastmcp' when installed via uvx (unpinned mcp dependency)

Description

Running uvx remarkable-mcp --usb (or --ssh) fails at startup with:

Root cause (suspected)

remarkable-mcp does not appear to pin an upper bound on the mcp SDK dependency. uvx resolves the latest available mcp release at each invocation, and a recent mcp release appears to have moved or removed the mcp.server.fastmcp module, breaking the import in server.py.

Reproduction

• Worked correctly on 2026-07-28 (fresh uvx install, USB mode).
• Broke starting 2

Read the thread · 2026-08-03 · closed · external user · 0 comments

Unbounded mcp>=1.27.0 breaks on mcp 2.0.0 — server dies at import as a generic "Connection closed"

Summary

remarkable-mcp declares mcp>=1.27.0 with no upper bound. mcp 2.0.0 removed the mcp.server.fastmcp module, so any fresh resolve picks up mcp>=2 and the server dies at import.

Because uvx re-resolves on every launch, this breaks the server silently and repeatedly on a previously working install — no code changed on either side.

What the user sees

The MCP client reports:

-32000: Connection closed

That reads like an authentication or cloud-token failure, whi

Read the thread · 2026-07-30 · closed · external user · 0 comments

ModuleNotFoundError: No module named 'mcp.server.fastmcp'

Got this error today:

Traceback (most recent call last):
  File "<frozen runpy>", line 203, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "C:\Users\USER\AppData\Local\uv\cache\archive-v0\6wSz6y4hY01v5E9WgJW1w\Scripts\remarkable-mcp.exe\__main__.py", line 10, in <module>
    sys.exit(main())
             ~~~~^^
  File "C:\Users\USER\AppData\Local\uv\cache\archive-v0\6wSz6y4hY01v5E9WgJW1w\Lib\site-packages\remarkable_mcp\cli.py", line 182, in main
    from remar

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/139) · 2026-07-28 · closed · external user · 1 comment

### Text-anchored ink renders overlapping the typed text block; remarkable_read returns no typed text from the same v6 page

## Summary

Two related problems on pages that mix typed text with handwriting (native notebooks, current firmware / v6, cloud mode):

1. **Rendered images draw the ink and the typed text block on top of each other.** On the device, ink written below a typed block is *anchored* to a text character (`Group.anchor_id`) and moves with it as the text reflows. `_v6_paths_from_blocks` draws strokes at their raw stored coordinates and never consults the group's anchor, so anchored handwriting lands ins

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/135) · 2026-07-20 · closed · external user · 1 comment

### Request dependency bump to resolve v5 stroke rendering and empty text layer errors via uvx

When running the server via uvx, Claude encounters an unhandled exception during the image rendering stage on modern reMarkable notebooks using the .v5 stroke format. The background stroke parser fails to compute the layout, resulting in empty text layers and an entirely frozen file state.Could the underlying rmc or rmscene library dependencies be updated in the package setup to explicitly support v5 rendering blocks out-of-the-box?

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/124) · 2026-06-19 · closed · external user · 2 comments

### remarkable_recent crashes when any document has null modified date

## Summary

`remarkable_recent` throws a Python `TypeError` whenever the library contains any document with a null/missing `modified` timestamp — which happens for freshly-created notebooks before any edits land.

## Environment

- `remarkable-mcp` v0.9.1
- Transport: USB web interface

## Reproduction

1. Have a reMarkable library with at least one notebook that has `ModifiedClient: null` (e.g. a brand-new notebook with no strokes yet). `remarkable_browse(path="/")` shows it as `"modified": nul

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/96) · 2026-05-27 · closed · external user · 0 comments

### Notebook render fails on current firmware — fall back to USB PDF export

## Summary

Reading and rendering handwritten notebooks fails in USB mode on current reMarkable firmware. The MCP returns empty content via `remarkable_read` and a `render_failed` error via `remarkable_image`. However, the **same USB web interface that the MCP talks to already serves correctly-rendered PDFs** at `http://10.11.99.1/download/<uuid>/anything` — suggesting the MCP could fall back to that endpoint when the local stroke renderer (`rmscene` / `rmc`) can't decode the notebook format.

#

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/95) · 2026-05-27 · closed · external user · 1 comment

### Cloud mode broken: /sync/v3/files/ returns 400 — rm-filename header now required server-side

### Description

Cloud mode fails on v0.9.1 when fetching files via `/sync/v3/files/{hash}`. The endpoint returns `400 Bad Request` with the message `"unexpected 'rm-filename' http header"` — regardless of whether the header is actually sent.

Authentication and root hash retrieval work fine. The failure occurs at the file download step.

I also tested v0.8.2 and confirmed the same error — both versions use identical sync endpoints, which points to a server-side change on reMarkable's end rather

[Read the thread](https://github.com/SamMorrowDrums/remarkable-mcp/issues/92) · 2026-05-20 · closed · outside contributor · 1 comment

The remaining reports are on [the project's issue tracker](https://github.com/SamMorrowDrums/remarkable-mcp/issues).