Cube
This MCP server, developed by Isaac Wasserman, interfaces with Cube.dev's REST API to enable AI agents to interact with semantic data layers. Built with Python and utilizing the Model Context Protocol SDK, it provides tools for querying and describing data available in Cube deployments. The implementation focuses on simplifying access to complex data structures, offering functionality to read data and retrieve metadata. It's particularly useful for organizations looking to leverage their existing Cube semantic layers with AI agents, enabling use cases such as automated data analysis, natural language querying of business metrics, and AI-assisted data exploration without directly dealing with Cube's API complexities.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/isaacwasserman/mcp_cube_server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Cube 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.