From rule-based expert systems to the Model Context Protocol — click any card to expand
Expert systems like MYCIN and DENDRAL used hand-coded rule engines as their "tools." Each rule was a conditional action: IF symptom_X AND symptom_Y THEN prescribe_Z. The tools were domain-specific, brittle, and required manual updates for every new case. There was no general-purpose tool interface — each system was its own closed world.
IBM's Deep Blue defeated Garry Kasparov by deeply integrating hardware-accelerated chess evaluation as a "tool" for its search algorithm. The system called its evaluation function millions of times per second. The lesson: tight integration between a reasoning system and specialized tools can achieve superhuman performance in bounded domains. The boundary was the key word.
OpenAI Gym standardized the environment interface for reinforcement learning: env.step(action) returns (observation, reward, done, info). This created a common API across hundreds of environments — the same agent code could train on Atari, MuJoCo, or a custom environment. It was the first widely-adopted standard for "agent takes action, environment returns observation."
Yao et al. published "ReAct: Synergizing Reasoning and Acting in Language Models" (arXiv:2210.03629). The paper formalized the THOUGHT/ACTION/OBSERVATION loop and showed empirically that interleaving reasoning with tool use dramatically outperformed either alone on HotpotQA (35.1% vs 25.7% for action-only) and AlfWorld (71% vs 45%). This was the moment the academic community had a rigorous framework for what practitioners were already doing ad-hoc.
OpenAI launched the ChatGPT Plugins beta — the first mainstream product that let end users connect LLMs to external tools via a standardized API spec. Plugins used OpenAPI schemas to describe tool capabilities, which ChatGPT would read and use for tool selection. Within weeks, hundreds of third-party tools (Wolfram, Zapier, Expedia) had plugin integrations.
OpenAI released the function calling API for GPT-4, providing a structured way to define tools via JSON schema and receive structured JSON back from the model when it wanted to call a tool. This replaced ad-hoc prompting tricks ("output JSON like this...") with a first-class protocol. The model was explicitly fine-tuned to produce valid function calls, not just text that looks like function calls.
Shi et al. (2023) released ToolBench: a benchmark of 16,464 real-world APIs from RapidAPI, covering 49 categories. The paper showed that GPT-4 achieved only 49% success on complex multi-tool tasks out-of-the-box, and that description quality was the single biggest predictor of tool selection accuracy. Fine-tuning on ToolBench raised open-source model performance by 28 percentage points.
Zhuang et al. (2024) published Gorilla, a model fine-tuned specifically on API documentation. The key finding: LLMs hallucinate tool arguments significantly — especially when APIs change after the training cutoff. Gorilla introduced retrieval-augmented tool use: fetch the current API doc at inference time, not from training data. This reduced hallucination rates by 47% compared to GPT-4 on the same benchmark.
Anthropic open-sourced the Model Context Protocol: a JSON-RPC 2.0-based standard for connecting LLMs to tools, resources, and prompts. MCP defines three primitives: Tools (executable functions with schemas), Resources (files and data the model can read), and Prompts (reusable templates). Transport layer supports stdio (local) and HTTP/SSE (remote). The spec was immediately open-sourced at modelcontextprotocol.io.
By mid-2025, MCP had been adopted by VS Code (GitHub Copilot), Claude Desktop, Cursor, Windsurf, Zed, and JetBrains IDEs. Enterprise adopters surpassed 340 companies. The MCP registry had 2,400+ community-built servers covering databases, cloud APIs, dev tools, and SaaS platforms. OpenAI announced MCP support in the ChatGPT API, effectively making it the industry standard.