back_office_ops · workflow
Agoda builds API Agent: a universal MCP server enabling natural language queries across any internal API via SQL post-processing
Agoda operates hundreds of internal services, each requiring its own custom MCP server integration to connect to AI tools — a bottleneck that meant any new API connection required bespoke code, and any ad hoc query required knowing the schema or asking an engineer to write a script.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Natural language question received
A user asks a question in natural language via the MCP client.
Tools used
FastMCPOpenAI Agents SDKDuckDBOpenTelemetryJaegerZipkinGrafana TempoArize Phoenix
Outcome
A single API Agent deployment serves any number of target APIs simultaneously; repeated query patterns are parameterized as recipes and replayed at a fraction of the latency without full LLM reasoning.
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
agentic workflowai agentdata extractionknowledge basebuilder submittednamed customerproduction runtime claimedsource backedtools describedworkflow describedtravelemployee productivitytime savedtechnical build writeupback office opsagentic task execution