AI / A CONCEPT NOTE
MCP & Function Calling
how models talk to your systems
Overview · mechanism
pitfall · examples
01 / THE SHORT VERSION
The idea in a few sentences.
Function calling lets models output structured JSON actions representing function arguments. Model Context Protocol (MCP) standardizes how models connect to local file systems.
02 / FOLLOW THE MECHANISM
How an API interaction flows
User Prompt
asks: 'Check the disk space in my server'.
JSON decision
model outputs: { 'name': 'check_disk', 'arguments': {} } instead of text.
Local Execute
application parses arguments, runs local script, and returns result to model.
Final answer
model reads script output and answers user: 'Your server has 14GB free'.
04 / COMMAND NOTES
Read the command, then the result.
Inspect the flags and arguments before trying an example. Snippets can need local setup, replacement values, or resources in your own environment.
launch an MCP database server node
npx -y @modelcontextprotocol/server-sqlite05 / CHECK YOURSELF
Could you explain MCP & Function Calling to a teammate?
Try it out loud in two sentences: what it is, and the one detail that changes the picture. If you stall, the gap is the part to reread.
Up next in AI engineeringEvalstesting something non-deterministic