From OpenChrome
Controls a real Chrome browser via CDP for navigation, clicking, reading, screenshots, crawling, and parallel automation with authenticated sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openchrome:openchromeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
OpenChrome is an MCP server that controls your real, already-logged-in Chrome
OpenChrome is an MCP server that controls your real, already-logged-in Chrome through the CDP. It wraps the browser API with a hint engine, circuit breaker, auto-recovery runtime, and token-efficient page serialization.
navigate url=<url> opens a URL in a managed tab.read_page mode=dom returns a compact, ~5–15x token-cheaper
serialization of the page. Use ref_N handles in follow-up actions.interact, fill_form, form_input, act for clicking,
typing, and high-level actions.computer returns a screenshot of the current viewport.oc_lane_create; work them
concurrently with the same Chrome session and existing cookies.oc_assert checks page state against a JSON contract
(url equals, dom_count ≥ N, dom_text contains …) and returns pass / fail /
inconclusive without guessing.oc_skill_record / oc_skill_recall store and replay procedural
memory across sessions.crawl_start / crawl_status / crawl_cancel with
cursor pagination.npm install -g openchrome-mcp
openchrome setup # Claude Code
openchrome setup --client codex # Codex CLI
Restart your MCP client. Chrome auto-launches on the first tool call.
Use this as the short routing card. The full catalogue remains in
docs/agent/capability-map.md.
| Intent | Start with | Fallback | Verify with |
|---|---|---|---|
| Open a URL | navigate | tabs_create | read_page |
| Read page facts | read_page mode=dom | inspect / query_dom | oc_assert |
| Find action targets | oc_observe | find / oc_query | inspect |
| Click or type | interact | computer | oc_assert |
| Verify success | oc_assert | validate_page | oc_evidence_bundle |
| Capture evidence | oc_evidence_bundle | page_screenshot | oc_diff |
| Debug a broken page | validate_page | console_capture | oc_evidence_bundle |
| Crawl or run background work | crawl_start | crawl_status / crawl_cancel | oc_assert |
| Repair runtime setup | openchrome doctor | oc_doctor_report | openchrome check |
Default loop: navigate → read_page / oc_observe → interact →
oc_assert → oc_evidence_bundle if the result is uncertain.
Use something else when:
| Tool | Purpose |
|---|---|
navigate | Open a URL |
read_page | Read page content (dom / markdown / screenshot) |
interact | Click / type on an element |
oc_assert | Verify page state against a contract |
oc_lane_create | Open a parallel tab lane |
oc_skill_record | Store a reusable step sequence |
oc_skill_recall | Retrieve steps for a domain |
crawl_start | Start an async crawl job |
oc_evidence_bundle | Snapshot DOM + screenshot + network + console |
oc_diff | Compare two evidence bundles |
Full catalogue: docs/agent/capability-map.md.
npx claudepluginhub shaun0927/openchromeControls local Chrome/Chromium via CDP for signed-in profiles, anonymous sessions, screenshots, console logs, network capture, form filling, uploads, downloads, and PDF export.
Controls Chrome via DevTools Protocol for navigating, clicking, typing, multi-tab management, and content extraction with auto-screenshots.
Controls a live Chrome browser via puppeteer-core for automation, testing, and performance auditing. Use for clicking, typing, screenshots, DOM/AX tree, network interception, HAR export, Lighthouse audits, and device emulation.