io.github.tathagat22/plumb-mcp
Figma → code MCP: no rate limits, no metered quotas, verification loop. Works on every Figma plan.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"plumb-mcp": {
"command": "npx",
"args": [
"-y",
"plumb-mcp"
],
"env": {
"FIGMA_TOKEN": "<your-figma_token>",
"PLUMB_SESSION_NAME": "<plumb_session_name>"
}
}
}
}{
"mcpServers": {
"plumb-mcp": {
"command": "npx",
"args": [
"-y",
"plumb-mcp"
],
"env": {
"FIGMA_TOKEN": "<your-figma_token>",
"PLUMB_SESSION_NAME": "<plumb_session_name>"
}
}
}
}npx -y plumb-mcpFIGMA_TOKENFigma personal access token (read-only). Only needed for the REST path — not required when the Plumb plugin is paired in Figma desktop. Create one at figma.com → Settings → Security → Personal access tokens.
PLUMB_SESSION_NAMEOptional label shown in the Plumb Figma plugin when multiple plumb-mcp servers are paired with the same plugin (multi-agent connect). Defaults to the basename of the current working directory.
AI-powered trading strategy development: backtesting, market data, and portfolio analysis
Feature flagging and A/B testing platform with AI-first experimentation workflows.
Query Meta Ads performance data — accounts, campaigns, ad sets, ads, metrics & settings.