Heptabase
This MCP server provides AI assistants with access to Heptabase backup data through a comprehensive toolkit for searching, analyzing, and exporting knowledge graphs from the visual note-taking platform. Built by Stanley using TypeScript and the Model Context Protocol SDK, the implementation automatically extracts and processes Heptabase backup ZIP files to enable querying of whiteboards, cards, connections, and their relationships through tools for backup management, content search with date/tag filtering, whiteboard analysis, and export capabilities supporting multiple formats including Markdown, JSON, and HTML. The server includes advanced features like file watching for automatic backup detection, graph analysis with centrality and clustering metrics, backup comparison tools, and content parsing that converts Heptabase's rich text format to readable Markdown, serving researchers and knowledge workers who want conversational access to their Heptabase data for analysis, content discovery, and knowledge management workflows without manually navigating the visual interface.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- monitoring
- Source
- PulseMCP
- Repository
- github.com/larrystanley/heptabase-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Heptabase 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.