How one big city is letting AI agents in

"The next wave of AI will be defined by agentic systems that can take actions: query databases, navigate portals, retrieve records, and increasingly interact with public digital infrastructure at scale. That shift is already showing up as traffic hitting government sites and services is becoming machine traffic. Some of it is benign (search and discovery). Some of it is ambiguous (scraping and automated browsing). And some of it could become actively harmful if agents can reserve scarce services, submit fraudulent requests, or generate volume that overwhelms public systems."

"The problem is that the government's current interfaces were not designed for agent-to-government interactions, and the default state of the world has become improvisation: agents 'figure it out' by scraping pages and guessing based on previous learning. Rather than treating agents as something to block wholesale, or something to embrace without guardrails, Boston is experimenting with a middle path: build a governed, secure, and reliable layer that mediates how AI agent systems interact with government resources."

"MCP stands for Model Context Protocol, and it's relatively recent. Anthropic, the company behind Claude, launched MCP servers about a year ago. Why it matters is that it provides a way for large language models to interface with the kinds of resources we have in government. Concretely, it's a way to connect LLMs to APIs and other programmatic systems."

AI agentic systems are generating increasing machine traffic to government websites and services, ranging from benign search activities to potentially harmful actions like fraudulent requests or system overload. Government interfaces were not designed for agent interactions, leading to improvised solutions where agents scrape pages and guess based on learning. Boston is pioneering a middle approach by building a governed, secure layer using Model Context Protocol (MCP) to mediate AI agent interactions with government resources. MCP, launched by Anthropic about a year ago, provides a standardized way for large language models to interface with government systems through APIs and programmatic connections. Starting with open data as a low-risk proving ground, Boston is developing replicable digital public infrastructure that other cities could deploy.

Read at Fast Company