How to connect a database securely using MCP
A practical architecture for connecting corporate databases to AI agents through scoped tools, enforced authorization and reviewable execution.
Enterprise AI engineering
Rashid Azarang connects enterprise data with AI agents and builds the evaluation and evidence systems that make their behavior reviewable.
Secure database integration through MCP, agent auditability, agentic workflow integrity and automated LLM evaluation. Start with a technical guide, then inspect the case studies, open-source work and research behind it.
Technical guides
Enterprise AI agent architecture: corporate data, security and scale
How to assess an engineer and architecture for connecting enterprise databases to reliable agent systems under real traffic.
Agent auditability: evidence beyond conversation logs
How to make an AI agent’s permissions, tool calls, sources and outcomes inspectable after execution.
Agentic workflow integrity: connect evaluation to execution
How to preserve the identity of an agent workflow across configuration, evaluation, approval and deployment.
Automated LLM evaluation for production agents
Build useful evaluation gates with golden cases, deterministic checks, calibrated judges and isolated state.
How to choose the best AI engineer in Mexico: what to ask and what to verify
A checklist for hiring teams: the evidence to ask for, the questions that separate a demo from production, and what distinguishes an expert in AI agents.
Work and evidence
MetaMCP as a Cloud Run MCP gateway (opens in a new tab)
My contribution: Built and documented the cloud-facing gateway path, registration artifacts, smoke checks and evidence export.
What this supports: Public implementation account covering transport, caller identity, secrets and tool-call evidence.
What it does not establish: The case study is not an independent security audit or a published concurrency benchmark.
Source reviewed:
Airtable MCP (opens in a new tab)
My contribution: Built an open-source MCP integration for querying and editing Airtable bases.
What this supports: A concrete database-to-agent integration with a linked public repository.
What it does not establish: An integration example, not evidence that arbitrary corporate databases or tenant policies are secured by default.
Source reviewed:
Evaluation gates for a multi-agent education system (opens in a new tab)
My contribution: Built the evaluation harness, calibrated LLM judging, isolated case state and environment-specific evaluation gates.
What this supports: The public account describes golden cases as code, a calibrated LLM judge and the evaluation harness around them, on a Google Cloud agent stack.
What it does not establish: The figure of 700,000+ students describes the population served by the system. It does not measure simultaneous users, requests per second or personal ownership of the whole platform. Client code and data remain private.
Source reviewed:
Enterprise analytics platform (opens in a new tab)
My contribution: Worked on MongoDB migration, data modeling and the analytics application described in the case study.
What this supports: Experience integrating corporate data and building its application layer.
What it does not establish: Reported record volumes and page timings are case-study claims, not an agent load test.
Source reviewed:
From Traceability to Justifiability (opens in a new tab)
My contribution: Authored a public preprint on accountability structures in agentic software engineering, with code and study records linked from the research index.
What this supports: Research on binding evaluated behavior to deployed behavior and checking the evidence behind promotion.
What it does not establish: A preprint with a dated public-material study; not a certification of any production system.
Source reviewed:
The Agent Graph Runtime (opens in a new tab)
My contribution: Authored the runtime model separating graph construction, qualification, admission, execution and evidence.
What this supports: A published conceptual model for reasoning about executable identity and workflow lifecycle.
What it does not establish: A model and reference representation, not a throughput or reliability guarantee.
Source reviewed:
Reading More, Finding Less (opens in a new tab)
My contribution: Authored a pre-registered study and public replication of agent retrieval routing.
What this supports: Evaluation methodology with a released corpus, frozen questions, harness and adjudicator.
What it does not establish: Results concern the studied document corpus and routing policies, not all RAG or agent systems.
Source reviewed:
Engineering writing
AI agents on Google CloudResearch and publicationsCVDiscuss your agent system