Milanote MCP Server and API by Cotlet

Upload image

upload_image

Destructive

Image card from a PNG, JPEG, GIF or WebP file, added to a board's Unsorted panel. Uploads one image per call, as Upload in Milanote does, and returns its card_id and size. The file goes in as a file argument (a link, an upload or base64), up to 10 MB; the extension of the name follows the real file type. The image_url opens only for people signed in to Milanote who can see the board. On the free plan an image counts toward the 100 cards limit and uploads are limited too. Nobody is notified; move the card to the trash in Milanote to undo it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "board_id": "<board_id>",
      "file": "<file>"
    },
    "name": "upload_image"
  }
}

Input Schema

Name	Required	Description	Default
`file`	Yes	PNG, JPEG, GIF or WebP image. Its name is shown on the card, e.g. location-01.jpg. Up to 10 MB, image/png, image/jpeg, image/gif, image/webp. Give exactly one of file_id (from cotlet_upload_file or POST /api/v1/files), url (a public link Cotlet downloads) or base64 (small files only).
`board_id`	Yes	Board ID from list_boards, or the board URL.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations flag destructiveHint and openWorldHint, and the description goes well beyond them: 10 MB cap, extension following the real file type, image_url visibility restricted to signed-in users who can see the board, free-plan 100-card limit and upload throttling, no notifications, and undo via trash. That is exactly the extra context annotations cannot carry.

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?

The purpose and scope are front-loaded, then constraints follow in a logical order (input, access, plan limits, undo). It is a dense paragraph with several clauses, but each sentence carries a distinct fact and nothing is filler.

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

Completeness5/5

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

With no output schema, the description correctly names the return values (card_id and size) and covers size limits, access semantics, rate limits, and reversibility. An agent has everything needed to call this correctly and to predict its side effects.

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

Parameters3/5

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

Schema coverage is 100% and every parameter, including the nested file object's one-of rule, is already documented there. The description restates the 10 MB limit and file-type rule without adding syntax or format detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource ('Image card from a PNG, JPEG, GIF or WebP file, added to a board's Unsorted panel') plus the cardinality rule ('one image per call'). This clearly separates it from file-upload siblings like cotlet_upload_file and from other card creators such as add_link or add_note.

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?

Explains the operation model (one image per call, mirroring Upload in Milanote) and the file-input options. It does not explicitly say when to prefer cotlet_upload_file + file_id over base64, but the schema's description covers that selection, leaving only a minor gap in the prose.

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

All Milanote MCP Server and API by Cotlet tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.