MCP SERVER
Interface understanding as MCP tools
memi exposes repository audits, briefs, tokens, and scaffold plans through MCP so an agent can read the interface before it writes.
REGISTRY
Public install target
Registry id
io.github.memi-design/memiPackage
@memi-design/cli@2.7.9ModeWorks code-first with
--no-figma; Figma context is optional.REMOTE
Connect over Streamable HTTP
MCP SERVER URL
https://www.memoire.cv/api/mcpmemi_capabilities- discover remote and local execution boundaries.prepare_design_agent_brief- generate a compact, executable design workflow.get_design_ci_policy- create deterministic UI quality gates.get_install_instructions- configure npm, MCP, Agent Skills, and agent kits.get_public_proof- resolve canonical package, registry, docs, and proof links.
The remote server is stateless and scoped. Repository files, approved scaffolds, local audits, and Figma context stay in the npm MCP server so Memi never pretends Vercel has access to a caller's project.
START
Run the full engine locally
TERMINAL
npm i -g @memi-design/cli@2.7.9
memi mcp start --no-figmaMCP CONFIG
{
"mcpServers": {
"memoire": {
"command": "memi",
"args": ["mcp", "start", "--no-figma"]
}
}
}TOOLS
v2.7.9 agent design tools
prepare_design_agent_brief- compact, standard, or full design-agent summaries.scaffold_agent_design_files- dry-run or approved Atomic Design spec scaffolds.run_audit- local design, UX, and craft evidence for a repo or route.design_doc- agent-ready interface summaries from a live route.get_tokens- token context without forcing Figma connection.