io.github.tathagat22/plumb-mcp

It requires FIGMA_TOKEN and PLUMB_SESSION_NAME; FIGMA_TOKEN is a sensitive credential and could allow access to associated Figma resources if exposed. No explicit credential-abuse pattern is shown in the materials, but the token should be handled as a high-sensitivity secret.

No remote host is declared, but the tool is positioned as 'Figma → code' and requires a FIGMA_TOKEN, which typically implies interaction with Figma services and transmission of design data. The materials do not show exfiltration to unknown or unrelated endpoints, so there is no concrete red flag for a high-risk rating.

The system flags it as executes-code, indicating it can run code locally or start related processes. This is a common MCP/tool capability, and the materials do not show requests for system privileges clearly beyond its stated purpose.

Based on the description, the tool likely accesses Figma design data and generates code, so it may handle user project content. The current materials do not specify any broader local file read/write scope, and no obvious over-privileging is shown, but it should be assumed to access provided design inputs and generated outputs.

It comes from the official Registry, is open-source, and has been updated within the last year; these are positive signals that materially reduce risk. However, the README is absent, the license is undeclared, and community adoption is very low (0 stars), so available auditability remains limited and a caution rating is more appropriate than safe.