Milanote MCP Server and API by Cotlet

Add notes

add_notes

Destructive

Up to 15 note cards in one call, into Unsorted or a column, in the order given. Creates one note card per text, in the order given, on top of the board's Unsorted panel or of a column, and returns each card_id. The text is plain: line breaks become paragraphs, Markdown is not converted, any script (Chinese, Arabic, emoji) is kept. Each note counts toward the free plan's 100 cards limit; get_usage shows what is left. If Milanote stops partway, the answer is an error and the notes made before it stay on the board. Editors of the board see them, nobody is notified.

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>",
      "notes": "<notes>"
    },
    "name": "add_notes"
  }
}

Input Schema

Name	Required	Description
`notes`	Yes	1 to 15 note texts, in order. Each line of a text becomes a paragraph.
`board_id`	Yes	Board ID from list_boards, or the board URL.
`column_id`	No	Column on the board (from get_board) to put the notes in, at the top. Default: the board's Unsorted panel.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses partial-failure semantics (error returned, notes already created remain), quota consumption against the free-plan 100-card limit, return of card_id per note, text fidelity rules (line breaks become paragraphs, Markdown not converted, unicode preserved), and visibility/no-notification behavior. The destructiveHint=true and idempotentHint=false annotations are consistent with non-atomic, repeatable creation.

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?

Front-loads capacity, destination, and ordering, then layers failure mode and quota. Minor waste from repetition — 'in the order given' and the Unsorted-or-column placement are each stated twice across the first two sentences.

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?

For a 3-parameter mutation tool with no output schema, the description covers everything an agent needs: what gets created, where, how many, how text is interpreted, what is returned, what happens on failure, and side effects on quota and collaborators.

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 coverage is 100%, so baseline is 3; the description earns an extra point by adding semantics the schema does not fully carry, such as Markdown not being converted, scripts/emoji being preserved, and ordering guarantee for the resulting cards. It does partially restate the schema's own notes about order, top placement, and the 1–15 range.

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 (add), resource (note cards), batch scope (up to 15 in one call) and placement rules, which cleanly separates it from add_note (single) and add_column in the sibling list. An agent can identify the operation without opening the schema.

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?

Gives concrete routing context: batch up to 15, default destination is Unsorted, column_id targets a column, and points to get_usage for remaining quota. It stops short of explicitly naming add_note as the alternative for single-note cases, so the when-not guidance is inferred rather than stated.

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.