Illustrated: Function Calling vs MCP in LLMs
Roger_M_Taylor · x · 2026-07-20
This thread clearly compares the differences and connections between LLM Function Calling and MCP (Model Context Protocol). - **Function Calling**: The model itself does not execute any code. Based on the prompt and available function definitions, it simply outputs a tool call request in its response. The developer's backend service then parses this request, executes the actual function, and returns the result to the model. - **MCP**: Before MCP, every tool integration required custom connection code. MCP standardizes this integration layer, though the underlying model invocation logic still relies on the exact same function calling mechanism.
More from coding & agent
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21
- X post asks whether Cursor Composer, built on Kimi models, would also be banned — max_paperclips · 2026-07-21
- A developer’s Codex usage is draining pooled enterprise credits at a small company — Distinct_Relation_62 · 2026-07-21