Secretless private vector search for Foundry Agents via MCP and Cosmos DB
adnan_hashmi · x · 2026-11-04
A walkthrough for wiring secretless, private vector search into Azure Foundry Agents: the agent sends natural-language questions through a remote MCP Toolkit, Foundry Models generate query embeddings, and Azure Cosmos DB's diskANN index serves results. Security comes from managed identity and private endpoints throughout — no API keys anywhere in the data path.
More from coding & agent
- Karpathy's viral take: engineers' biggest regret is unsaved AI conversations — bfrench · 2026-11-04
- Apple lets apps bundle Siri skill files, devs mock the sloppy docs — msg · 2026-11-04
- YC-backed Simantic adds a simulation layer so AI agents can test firmware at software speed — ycombinator · 2026-11-04
- Bittensor Subnet 33 Launches Skill Store: Tested Skills Aim to Make Open Models Do Frontier Work — markjeffrey · 2026-11-04
- Building a 24-hour AI newsroom on Microsoft Copilot Harness: workflow beats prompts — WirelessLife · 2026-11-04
- Polyphonic to give AI agents their own Mac via open-source terminal-mac — RileyRalmuto · 2026-11-04