webmcpify (Agent Skill)

Browser AI agents (Gemini in Chrome, extensions, assistive tech) are learning to call structured page tools instead of scraping the DOM. WebMCP is the emerging standard for that, co-authored by Google and Microsoft engineers, in origin trial since Chrome 149. Making an app agent-ready by hand means reading a spec that is still moving (the API surface changed twice during the trial), learning tool-design conventions, and building a verification setup — webmcpify packages all of that into one command for your coding agent.

/plugin marketplace add TueJon/webmcpify /plugin install webmcpify@webmcpify

The skill directory is self-contained — pipeline, phase guides, vendorable runtime, and the verification template all ship inside it.

Open your agent in the target repo and pick your scope:

/webmcpify # full pipeline /webmcpify inventory # just investigate + propose the tool manifest (zero code changes) /webmcpify integrate # integrate the approved manifest /webmcpify verify # verify + heal what's integrated /webmcpify status # where are we? what's next?

(or in plain words:"webmcpify this app","map what tools this app could expose")

The pipeline hasone main checkpoint— you approve the tool manifest (and, for apps under git, choose whether integration batches are committed). Beyond that it only comes back for things it genuinely can't resolve: an app that won't start, or a tool that still fails after capped heal attempts. All state persists in.webmcpify/manifest.json, so runs areresumableacross sessions, context windows, and even different agents.

Every phase is aloop over persistent state, not a one-shot pass:

- Inventorymaps the codebase into areas (routes/views/modules) first, then deep-reads one area per iteration — a 500-file SaaS is processed area by area, never in one context-busting sweep. Sub-agent fan-out writes per-area shard files; a single coordinator merges them (no write races).
- Tool budgetskeep SaaS toolsets usable: priority waves, an overlap rule (no two tools matching the same request), and role/tenant coverage tracking.
- Integrateworks in small batches (one area or ≤5 tools), each independently built and typechecked — committed per batch only if you opted in.
- Verify/Healiterate per tool with attempt caps and honest escalation instead of infinite loops; mutating tools get cleanup steps between retries.
- Interrupt at any point; the next run resumes from the manifest.

- Unrelated logic and UI stay untouched— every diff hunk traces to a manifest entry; a final audit against the recorded baseline commit enforces it, and files that were already dirty when the run started are never modified or reverted.
- Read-only first— mutating tools require your explicit per-tool approval; destructive/payment actions are never exposed.
- Server stays the trust boundary— tools only call code paths your UI already uses; no new endpoints, no bypasses.
- Spec-shaped, zero dependencies— a small MIT runtime is vendored into your repo (no npm dependency), everything feature-detected: your app isbehaviorally unchangedin browsers without WebMCP.
- Exercised, not assumed— every tool is enumerated and executed in real Chrome, asserting on both the tool result and the resulting UI state, from examples recorded in the manifest. That includes mutating declarative forms, where Chrome pauses the execution until a real submit interaction — the harness performs that submit click mid-execution instead of faking the pass.
- Spec over scoreboard— WebMCP checkers and inspector extensions grade pages against a mix of spec features, conventions, and invented checks. webmcpify classifies their findings instead of chasing them: it never emits non-existent attributes or adds markup an app doesn't need to raise a score. Optional off-page discovery (a/.well-known/webmcpmanifest,rel="webmcp"links) is a separately approved layer, because it publishes tool metadata publicly — never part of a default integration.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

Interact with Odoo instances using the XML-RPC API. Requires configuration via environment variables or config files.

D2C eCommerce fulfillment platform: manage orders, inventory, shipments, campaigns, and billing via AI agents

MCP Server For Apache Doris, an MPP-based real-time data warehouse.

Oracle Fusion Cloud integration using OAuth2. Write operations disabled by default per integration. 1000+ tools covering Financials, Procurement, Inventory, Suppliers, Tax, and Workforce.

Connect SAP Business One (SQL Server) to Claude AI Desktop via MCP. Query financials, inventory, sales, and purchasing with natural language.

A read-only MCP server by CData for querying live Zoho Inventory data.

Official remote MCP server for Foundry IMS: manage an inventory and product catalog — products, variants, brands, categories, images, custom fields, bundles, and assemblies/BOMs.

Browse GPU inventory, launch and manage VMs, and audit billing on Massed Compute from any AI agent.