D2 Diagramming
This D2MCP server by Yasushi Itoh provides AI assistants with direct access to D2 diagram creation and rendering capabilities, integrating with Terrastruct's D2 declarative diagramming language to generate SVG, PNG, and PDF outputs. The implementation supports 20+ built-in themes, programmatic diagram creation with in-memory storage, and file-based operations for persistent diagram management, using external tools like rsvg-convert or ImageMagick for non-SVG format conversion. Built with clean architecture patterns and comprehensive error handling, it enables natural language diagram generation workflows where users can create technical diagrams, flowcharts, and architectural visualizations through conversational interfaces without directly writing D2 syntax.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/i2y/d2mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve D2 Diagramming from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.