Review new or changed SAP Datasphere MCP tools for adherence to the project's 4-layer pattern and invariants (row caps, URL prefix fallback, mockmode, error shape, matching example + test). Use after adding or modifying a datasphere tool.
Security audit of the SAP Datasphere MCP server's auth and credential-handling surface — OAuth token flow, TLS toggle, secret handling, and error messages that might leak secrets. Use before releases or after touching auth.py, config.py, or client.py.
Scaffold a new SAP Datasphere MCP tool across all four required layers (client method, business-logic function, @server.tool wrapper, example + test) following project conventions. Use when adding a new datasphere tool.
Cut a new version of the SAP Datasphere MCP server — bump the version in pyproject.toml, sync CHANGELOG.md and README, and prepare the release commit. Use when asked to release, cut a version, or bump the version.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Claude Code instructions for rahulsethi/SAPDatasphereMCP, covering claude.md — sap datasphere mcp server, what this is, layout, conventions and commands.
Model Context Protocol (MCP) server for SAP Business Data Cloud (BDC): contract-first, safe-by-default tooling for AI agents. Runs locally from the sap-bdc-mcp Python package.