Read, create, and modify Figma designs programmatically via MCP, empowering AI to execute Figma changes safer, cleaner, and faster.
- capability exposureinferred+22
- trust mitigatorsmixed−3
inferredmixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 11m ago · see ecosystem CVEs →
- A · 7 → B · 19
- A · 9 → A · 7
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit dad009e · analyzer v17 · 15h ago
skills & prompt files 7
- agent-rulesneozhehan-figma-edit-mcp-dad009e/.cursorrules
- agent-rulesneozhehan-figma-edit-mcp-dad009e/.github/copilot-instructions.md
- agent-rulesneozhehan-figma-edit-mcp-dad009e/AGENTS.md
- agent-rulesneozhehan-figma-edit-mcp-dad009e/CLAUDE.md
- prompt-fileneozhehan-figma-edit-mcp-dad009e/documentation/completed/v2.0.0/drafts/prompts/reaction_to_connector_strategy.draft.md
- prompt-fileneozhehan-figma-edit-mcp-dad009e/documentation/completed/v2.0.0/drafts/prompts/swap_overrides_instances.draft.md
- skillneozhehan-figma-edit-mcp-dad009e/skills/figma-edit/SKILL.md
[](https://mcpobservatory.com/servers/github:neozhehan/figma-edit-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of neozhehan.