cnvs.app

Add Image

add_image

Destructive

Place a raster or SVG image on the board at (x, y) with explicit width/height in board pixels. data_url MUST be a data:image/(png|jpeg|gif|webp|svg+xml);base64,... string ≤ ~900 kB; hosted URLs are not accepted. The bytes are header-checked (the leading bytes must be PNG/JPEG/GIF/WebP/SVG; not a full decode); SVG content must be declared image/svg+xml, raster content must not be. Strongly recommended: also pass a tiny thumb_data_url (≤8 kB JPEG/PNG/WebP, ~64 px on the long edge) — it is embedded into the SVG preview so OTHER AI viewers (and you, on later get_preview calls) can actually see the image instead of a placeholder box.

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>",
      "x": "<x>",
      "y": "<y>",
      "width": "<width>",
      "height": "<height>",
      "data_url": "<data_url>"
    },
    "name": "add_image"
  }
}

Input Schema

Name	Required	Description
`x`	Yes
`y`	Yes
`id`	No
`width`	Yes
`author`	No
`height`	Yes
`board_id`	Yes
`data_url`	Yes
`access_key`	No	8-character lowercase alphanumeric board access key when the board is locked (legacy 6-character lowercase alphanumeric keys are also accepted). Equivalent to setting the `X-Board-Key` HTTP header on the JSON-RPC POST. Omit for unlocked boards. Obtain via POST /api/boards/<id>/lock.
`thumb_data_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 20, 2026

changedInput schema / properties / access_key / description

Previous value: -"6-char board access key (a-z, 0-9) when the board is locked. Equivalent to setting the `X-Board-Key` HTTP header on the JSON-RPC POST. Omit for unlocked boards. Obtain via POST /api/boards/<id>/lock."New value: +"8-character lowercase alphanumeric board access key when the board is locked (legacy 6-character lowercase alphanumeric keys are also accepted). Equivalent to setting the `X-Board-Key` HTTP header on the JSON-RPC POST. Omit for unlocked boards. Obtain via POST /api/boards/<id>/lock."

Changed1 schema field changedMay 14, 2026

addedInput schema / properties / access_key

Added value: +{
+  "description": "6-char board access key (a-z, 0-9) when the board is locked. Equivalent to setting the `X-Board-Key` HTTP header on the JSON-RPC POST. Omit for unlocked boards. Obtain via POST /api/boards/<id>/lock.",
+  "type": "string"
+}

First observedApr 20, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Discloses behavior beyond the annotations: leading-byte header validation without a full decode, the ~900 kB ceiling, the exact media/type pairing rules for SVG vs raster, and the consequence of omitting a thumbnail (placeholder box for other AI viewers and future get_preview calls). That is precisely the kind of operational detail annotations cannot convey.

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-loaded with placement and geometry before the encoding rules, and no sentence is filler. The final sentence is long and parenthesis-heavy, but every clause (size, aspect, embedding behavior) carries information the agent needs.

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?

Covers input contract, validation, and the thumbnail workflow for a mutation tool with no output schema and only partial annotation coverage. Return value (e.g., whether a created element id comes back) is never stated, and id/author remain opaque, but the essential call-correctness information is present.

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 only 10%, so the description carries the burden and mostly does: data_url and thumb_data_url are fully specified (format, size, edge length), and x/y/width/height gain units ('board pixels'). The id and author properties still receive no explanation in either place, which keeps this just below a 5.

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 ('Place a raster or SVG image on the board') plus the placement/sizing contract in board pixels, which cleanly separates it from add_text, add_link, and draw_stroke. An agent can tell what it does 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 clear constraints on acceptable input (data URL only, hosted URLs rejected, size ceiling, SVG media type rules) and a strong recommendation to pass thumb_data_url with the reason why. It stops short of explicitly naming sibling alternatives for other content types, but the conditions for correct use are unambiguous.

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

All cnvs.app 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.