cursor-talk-to-figma-mcp
mcp0.3.5TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
By grab | 48 findings | Scanned 6/15/2026 | tooltrust-scanner/v0.3.17 | 6.8k
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (48)
create_frame:input schema exposes 20 properties (threshold: 10)
Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
No metadata.dependencies or repo_url were exposed by this MCP server, and no local project manifest could be inferred from the launch command.
get_document_infoget_selectionread_my_designget_node_infoget_nodes_infocreate_rectanglecreate_framecreate_textset_fill_colorset_stroke_colormove_nodeclone_noderesize_nodedelete_nodedelete_multiple_nodesexport_node_as_imageset_text_contentget_stylesget_local_componentsget_annotationsset_annotationset_multiple_annotationscreate_component_instanceget_instance_overridesset_instance_overridesset_corner_radiusscan_text_nodesscan_nodes_by_typesset_multiple_text_contentsset_layout_modeset_paddingset_axis_alignset_layout_sizingset_item_spacingget_reactionsset_default_connectorcreate_connectionsset_focusset_selectionsjoin_channelFix: Review and remediate the identified issue.
declared capabilities: filesystem access
create_rectanglecreate_framecreate_textdelete_nodedelete_multiple_nodescreate_component_instancecreate_connectionsFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y cursor-talk-to-figma-mcp"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)