Software for agents

The design workspace
your agents can use.

Most design tools are built for hands and eyes. Clearly is built so an AI agent can generate editable art, see a shared canvas, and act on it — the same generate-see-act loop a designer runs, exposed as tools and billed to one plan.

Fox mascot
Mountain landscape
Rocket launch
Botanical bloom
Geometric badge
Wave pattern

Your agent hand-rolls editable paths like these — it can post-process, diff, or hand them to a human.

MCP · CLIHeadless generationAgents can see the canvasOne metered AI pool

What is a design tool for AI agents?

It is a design workspace an agent operates directly — not a human app with an API bolted on. In Clearly, an AI agent can generate editable vector or raster art over MCP or the CLI, perceive a live canvas (nodes, selection, even the Skia-drawn chrome), and drive it — place, restyle, export — then hand the same editable file to a person to finish. Agent work and human work draw the same metered plan.

Generate · Perceive · Drive

A designer's loop, given to an agent

A human designer makes a mark, looks at the result, and adjusts. Clearly gives an agent all three verbs — not just the first one an image API stops at.

01

Generate

Make editable vector & raster art from a prompt — headless, no browser.

clearly_canvas_act over MCP — hand-rolled SVG + paths onto a real canvas. Or one beehaven CLI call.

02

Perceive

See the canvas — nodes, selection, viewport, even the Skia-drawn chrome.

canvas-perceive returns a structured CompositionRoom (or a live PNG).

03

Drive

Act on the canvas — place, paste, restyle, export — like a hand on the mouse.

canvas-invoke dispatches registered editor actions to a live tab.

Perceive + drive are what make Clearly a workspace for agents, not just a generator. The agent isn’t blind to the document it’s editing.

Why agent-native

An image API returns a picture. This runs the design loop.

The gap between a generation endpoint and a workspace an agent can actually operate.

FeatureClearly (agent-native)Generic image APIHuman-only design tool
Generate art from a prompt
Output stays editable (vectors)
Agent can see the canvas
Agent can act on the canvas
Human can refine the same file
One metered plan for agents + people
Four front doors, one engine

Connect however your agent already runs

The same generation + canvas engine behind the Clearly studio, reachable four ways. Pick the one that fits your stack — nothing to deploy.

What teams build with it

From one icon to a standing asset pipeline

Anywhere an agent needs to make or edit a picture instead of describing one.

Consistent design systems

Pin one style across a fleet of calls so 200 generated icons all match — editable SVG that drops into your component library.

Build-time asset pipelines

An agent reads a manifest in CI and emits the missing illustrations, OG images, and spot icons — no designer in the critical path.

On-brand at scale

Ground every agent in Company Brain so a thousand marketplace thumbnails or product badges come out in your palette and voice.

Agent drafts, human finishes

The agent generates onto a canvas via a compositionId; a teammate drags nodes and recolors paths. The un-copyable round trip.

Bots that return real art

A Slack, Discord, or support bot that answers with an actual sticker or diagram — generated on the fly, posted back as a URL.

Creative coding agents

Give a coding agent a drawing primitive: it reasons about a layout, calls the tool, inspects the returned paths, and iterates — a real loop, not prompt roulette.

Connect in a minute

Token, point, call

Step
01

Sign in

OAuth in the browser the first time your client connects — nothing to copy or rotate. Headless job that can’t open a browser? Mint an agent-bound token in the Agents modal.

Step
02

Point your client

Add the hosted MCP endpoint or install the beehaven CLI — nothing to deploy. Claude Code and Cursor are one line each.

Step
03

Generate, perceive, drive

Your agent now has design tools in its loop — make art, read a canvas, act on it — all billed to your AI pool.

FAQ

Software for agents, answered

01What is a design tool for AI agents?+
It is a design workspace an agent can operate directly — not a human app with an API bolted on. Clearly lets an AI agent generate editable vector or raster art (over MCP or the beehaven CLI), see what is on a canvas (canvas-perceive), and act on it (canvas-invoke) — the same generate-see-act loop a human designer runs, exposed as tools. It is billed to your Clearly plan, so agent work and human work draw the same metered pool.
02What is an MCP design server?+
An MCP (Model Context Protocol) server that exposes design capabilities as tools an agent discovers and calls. Clearly’s hosted MCP server offers clearly_canvas_perceive / clearly_canvas_act / clearly_canvas_catalog, so Claude, Cursor, or any MCP client can see a canvas and build editable SVG or raster art mid-task — headless, with the exact cost returned on every call. Connect at relay.clearly.sh/mcp with a token.
03Which agents and clients does it work with?+
Any MCP client — we test Claude Code, Cursor, and Claude Desktop — plus any code that speaks the MCP JSON-RPC directly against the hosted endpoint. The CLI (beehaven) drives the same surface from a terminal or a CI job. Because it is protocol-standard, an agent gains a design tool the moment it connects; there is no SDK to adopt or rewrite.
04How is this different from an image-generation API?+
An image API only does step one — it returns a picture. Agent-native Clearly also lets the agent see a shared canvas and act on it, keeps vector output editable (not a flattened PNG), and lets a human refine the same file afterward. The agent drafts on the canvas; a teammate finishes. That closed loop — generate, perceive, drive, hand off to a person — is the difference.
05How is agent usage billed?+
Agents spend the same metered AI pool your team does — there is no separate per-seat charge for an agent. Every generation returns its costUsd so spend is auditable per call, per user, per job, and top-ups cover any overflow. One plan, one balance, whether the work is done by a person or an agent.
06Do the results stay editable for a human to finish?+
Yes for vectors — your agent hand-rolls real <svg> and path code onto the canvas (canvas.create-node { type:'svg' | 'path' }), not a screenshot of a vector. Pass a compositionId and the asset also lands on a Clearly canvas where a person can drag nodes and recolor paths. The agent-makes / human-refines round trip is the whole point of building the design tool for agents instead of behind an opaque API.
07Why build software for agents at all?+
Increasingly the user of a tool is an agent, not only a person. Giving agents first-class, billable design capabilities — generate, perceive, drive — turns Clearly into infrastructure the way an image model or a database is, and lets a team scale design work across a fleet of agents grounded in one shared brand. It is the same reason APIs and MCP servers exist: meet the agent where it already runs.

Give your agents a design tool

Mint a token, point your client at the hosted server, and let your agents generate, perceive, and drive — metered against one AI pool for your whole team.