1. Install
pip install anthropic httpx
That's it. The Anthropic SDK and an HTTP client.
Tool-use spec for the Anthropic SDK. Works with Claude Desktop, Claude Code, the Anthropic API directly, AWS Bedrock, and Google Vertex. Setup time: about five minutes.
pip install anthropic httpx
That's it. The Anthropic SDK and an HTTP client.
export ANTHROPIC_API_KEY=sk-ant-...
export AEGISAI_BASE_URL=https://api.aegisai.store
export AEGISAI_USER_TOKEN=<user JWT>
python example.py "Show me vendor 100247's open invoices"
Claude reasons, emits a tool_use block, the dispatch loop hits AegisAI, the masked response goes back to Claude.
samples/connectors/anthropic-claude/.| File | Purpose |
|---|---|
README.md | Setup walkthrough plus the two-token identity model explainer. |
tool_spec.json | The tool definition you pass to the Anthropic SDK (or Bedrock/Vertex equivalent). |
example.py | Working ~80-line example with the full dispatch loop. |
Two tokens, never confused: the Anthropic API key proves your application is allowed to call Claude. The end user's JWT proves the user is allowed to access the SAP/cloud data. Your application is the bridge — Claude generates a tool_use block, your dispatch loop attaches the user's JWT in the request body, AegisAI extracts sub, and the audit row records the human.
If you collapse these into one token (e.g. mint a fake user identity from the Anthropic key), the audit chain shows "the bot" for every action and identity propagation collapses. Don't.