affinity-mcp
AGENTS.md2 starsChanged 27 days agoMITView on GitHub
Instructions for any AI coding agent (Codex, Cursor, Claude Code, Gemini CLI, Copilot, ...) working with Affinity by Canva. The skill lives in skills/affinity/SKILL.md. Read it before calling Affinity's MCP tools, and load the files in skills/affinity/references/ that it points you to. Connection details are in skills/affinity/references/setup.md: the server is http://localhost:6767/sse (SSE), and stdio-only clients run node scripts/affinity-sse-bridge.mjs. The non-negotiables, explained in references/safety.md: work on a copy of the user's document, ask before Canva AI calls that use credits, never…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Keep skills/affinity/SKILL.md under 500 lines.
- Distinctive: line 17
No personal data in examples.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
Instructions for any AI coding agent (Codex, Cursor, Claude Code, Gemini CLI, Copilot, ...) working with Affinity by Canva.
If you are here to use Affinity
The skill lives in skills/affinity/SKILL.md. Read it before calling Affinity's MCP tools, and load the files in skills/affinity/references/ that it points you to. Connection details are in skills/affinity/references/setup.md: the server is http://localhost:6767/sse (SSE), and stdio-only clients run node scripts/affinity-sse-bridge.mjs.
The non-negotiables, explained in references/safety.md: work on a copy of the user's document, ask before Canva AI calls that use credits, never save, close or overwrite documents you did not create, and verify every visible change with render_spread.
If you are here to change this repository
- Skill content is English, imperative, and evidence-based. Do not document an API you have not run or found in the official SDK docs, and mark docs-only claims
(docs). - Keep
skills/affinity/SKILL.mdunder 500 lines. Detail belongs inreferences/. - Plugin manifests:
.claude-plugin/(plugin and marketplace),.cursor-plugin/plugin.json+mcp.json,.codex-plugin/plugin.json+.codex-plugin/mcp.json, and.mcp.jsonfor Claude. Keep versions in sync withCHANGELOG.md. scripts/affinity-sse-bridge.mjsmust stay dependency-free and loopback-only.- No personal data in examples.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.