--- title: "AgentReady: a WebMCP readiness benchmark | Manas Nikam" canonical: https://manasnikam.dev/case-studies/agentready-webmcp-benchmark/ updated: 2026-09-23 --- # AgentReady: scoring whether the web is ready for agents By Manas Nikam, 3 to 10 September 2026. Hackathon build (The WebMCP Challenge, 3 to 10 September 2026); outcome not recorded. For The WebMCP Challenge I built AgentReady, a benchmark that scores a site 0 to 100 on whether agents can complete tasks; it registers 13 WebMCP tools, runs real audits through headless Chrome on Cloudflare, and reports every score with a 95% confidence interval over N runs. ## Context WebMCP lets a site register tools that an agent can call instead of driving the UI. The challenge asked for something built on it. I wanted a number, not a demo: a way to say how ready a given site is, with error bars, and a way to see what an agent fails at when it is not ready. Constraint: eight days, a serverless budget, and audits that must never bypass a login or a CAPTCHA; a failure has to be recorded as a failure. > Scoping artifact. The rubric was written before the runner: `readiness = 100 x (0.70 x best_success_rate + 0.15 x has_webmcp + 0.15 x efficiency)`. Success rate carries most of the weight because a site an agent cannot finish tasks on is not ready whatever else it has; WebMCP presence and efficiency are bonuses. The 8-category failure taxonomy was fixed at the same time so failures would be comparable across runs. ## Problem Site owners and agent builders had no shared measure of agent readiness; claims came from single demos with no repetition and no confidence interval. ## What I built I built a readiness dashboard that registers 8 WebMCP tools, a demo store with 5 tools and a shared human-and-agent cart, live agent-call analytics, and an instrumentation SDK that wraps `registerTool` so any site can report tool calls. The audit runner drives Playwright and an LLM agent against a site N times in UI mode and N times in WebMCP mode, computes success rates with 95% confidence intervals, classifies each failure into one of 8 categories, and publishes the rubric with the score. `queue_live_audit` triggers a real serverless audit: Cloudflare Queues to Browser Rendering (headless Chrome on the edge over CDP) to a Workers AI agent (Llama 3.3 70B) to D1. Synthetic sample rows are labelled as synthetic; CAPTCHAs and logins are recorded as failures, never bypassed. ## Architecture vinext (Cloudflare’s Vite-based Next.js API reimplementation) on Cloudflare Workers; D1 for results; Workers AI for the agent; Browser Rendering for headless Chrome; Queues for audit jobs; R2 pre-wired. Security: same-origin audit restriction, a daily run budget, payload caps, prompt-injection awareness. MIT licensed. 1. Dashboard or WebMCP tool call: queue_live_audit 2. Cloudflare Queue, daily run budget and payload caps enforced 3. Browser Rendering: headless Chrome over CDP, same-origin only 4. Workers AI agent (Llama 3.3 70B) attempts the task N times, UI mode and WebMCP mode 5. D1: per-run outcome, failure category, 95% confidence interval, readiness score Audit path: a tool call enqueues a job; the worker opens the target in headless Chrome, lets the agent attempt the task repeatedly in both modes, and stores each outcome so the score carries a confidence interval. Stack: TypeScript, Cloudflare Workers, vinext, D1, Workers AI, Browser Rendering, Cloudflare Queues, Playwright, WebMCP. ## Results 13 WebMCP tools live, a published rubric, and scores that come with 95% confidence intervals over N runs and an 8-category failure taxonomy; the whole thing is live at agentready.prescalesystems.workers.dev with the source on GitHub. Built and submitted in 18 commits between 3 and 10 September 2026; outcome not recorded. AgentReady, what the benchmark measures | Element | Value | | --- | --- | | WebMCP tools registered | 13 (8 on the dashboard, 5 in the demo store) | | Runs per site per mode | N, configurable | | Confidence interval on success rate | 95% | | Failure categories | 8 | | Readiness score | 100 x (0.70 x best success rate + 0.15 x has WebMCP + 0.15 x efficiency) | | Build window | 3 to 10 September 2026, 18 commits | Hackathon build; the sample rows shown on the dashboard are labelled synthetic where they are. ## What I'd do differently I published the rubric but not a metric table of real audits. Next time I would run N=10 audits on five public sites in both modes before submitting and commit the JSONL with the README table, because a benchmark without its own baseline results asks the reader to take the method on faith. ## Links - [agentready.prescalesystems.workers.dev](https://agentready.prescalesystems.workers.dev): hackathon build, live as of September 2026 - [github.com/manasnikam/agentready](https://github.com/manasnikam/agentready): source, MIT - [webmcp.devpost.com](https://webmcp.devpost.com): the challenge