rm-mcp

Overview Schema Source Related Servers Discussions Admin

remarkable_image

Read-onlyIdempotent

Render a specific page from a reMarkable document as a PNG or SVG image to view hand-drawn diagrams, sketches, or mockups that text extraction misses.

Instructions

Get an image of a specific page from a reMarkable document. Renders a notebook or document page as an image (PNG or SVG). This is useful for:

Viewing hand-drawn diagrams, sketches, or UI mockups
Getting visual context that text extraction might miss
Implementing designs based on hand-drawn wireframes
SVG format for scalable vector graphics that can be edited

Response Formats

By default, images are returned inline:

PNG: Returned as ImageContent with base64-encoded data
SVG: Returned as EmbeddedResource with TextResourceContents containing SVG markup

If your client doesn't support embedded resources in tool responses, set compatibility=True to receive a JSON response with just the resource URI. The client can then fetch the resource separately.

Optionally, enable include_ocr=True to extract text from the image using OCR. When REMARKABLE_OCR_BACKEND=sampling is set and the client supports sampling, the client's own LLM will be used for OCR (no API keys needed).

Note: This works best with notebooks and handwritten content. For PDFs/EPUBs, the annotations layer is rendered (not the underlying PDF content).

document: Document name or path (use remarkable_browse to find documents)
page: Page number (default: 1, 1-indexed)
background: Background color as hex code. Supports RGB (#RRGGBB) or RGBA (#RRGGBBAA). Default is "#FBFBFB" (reMarkable paper color), or set REMARKABLE_BACKGROUND_COLOR env var to override. Use "#00000000" for transparent.
output_format: Output format - "png" (default) or "svg" for vector graphics
compatibility: If True, return resource URI in JSON instead of embedded resource. Use this if your client doesn't support embedded resources in tool responses.
include_ocr: Enable OCR text extraction from the image (default: False). When REMARKABLE_OCR_BACKEND=sampling, uses the client's LLM via MCP sampling.

Input Schema

TableJSON Schema

Name	Required	Default
`page`	No
`document`	Yes
`background`	No
`include_ocr`	No
`compatibility`	No
`output_format`	No	png
`compact_output`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.0Sep 7, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description adds rich context beyond them: exact response formats (PNG as ImageContent, SVG as EmbeddedResource), the compatibility flag for clients without embedded-resource support, OCR behavior and the REMARKABLE_OCR_BACKEND=sampling path, and PDF/EPUB annotation-layer rendering. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with usecase/instructions/parameters/examples tags, front-loaded with the purpose, and examples add real value. Slightly long, but the dense instructions are organized in scannable subsections (Response Formats, OCR, PDF behavior) so every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and 0% schema coverage, the description carries a heavy burden and mostly delivers: it explains return formats, defaults, OCR, PDF caveats, and includes 7 illustrative examples. The sole completeness gap is the undocumented compact_output parameter, which an agent could not know how to use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate — and it does thoroughly: document (with browse pointer), page (1-indexed default), background (hex format, default, env override, transparent), output_format, compatibility, and include_ocr all get meaningful semantics. However, the input schema's compact_output parameter is not mentioned anywhere in the description, leaving one of seven parameters undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The usecase tag states a specific verb+resource ('Get an image of a specific page from a reMarkable document') that clearly distinguishes it from siblings like remarkable_read (text extraction) and remarkable_browse (document tree). The instruction that it provides 'visual context that text extraction might miss' further disambiguates it from remarkable_read.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lists concrete use cases (viewing diagrams, sketches, mockups, wireframes) and a clear when-not: 'works best with notebooks... For PDFs/EPUBs, the annotations layer is rendered (not the underlying PDF content)'. It also routes to remarkable_browse for finding documents. However, it never explicitly names remarkable_read as the alternative for text-only extraction, leaving that exclusion implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server