# deputy-mcp Deputy's MCP bridge: Claude Code, Codex, Cursor and any MCP client use the pages in your browser as typed tools. Needs the Deputy Chrome extension and a Deputy Pro license. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 0.1.1 - **Author:** Unknown - **License:** PolyForm-Shield-1.0.0 - **npm:** deputy-mcp - **Source:** https://razin.ai/deputy/ - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 0 days ## Security scan - **Status:** clean - **Scanned:** 2026-10-16T11:16:04.574Z - **Version scanned:** 0.1.1 - **CVEs:** none found by OSV at scan time ## Tools 27 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `browser_capabilities` — The full contract of every open tab: each form as a typed tool with its JSON Schema (types, allowed values, min/max, required fields), what those fields current - `browser_invoke` — Call one of the tools browser_capabilities listed, with arguments matching its inputSchema. This acts in the real logged-in browser: it fills and submits the ac - `browser_fill` — Set a single field to a value, addressed by the ref browser_capabilities gave it. Use this - `browser_click` — Click something browser_capabilities listed under "actions", by its ref. - `browser_read` — Return the page as plain text for you to read yourself. Use browser_ask instead when you only need one fact: with a model (Deputy Pro or OPENROUTER_API_KEY) Dep - `browser_navigate` — Point a tab at a URL and wait for it to load, or move through its history with action "back" / "forward", or "reload" it. Deputy re-reads what the new page can - `browser_tabs` — Work with browser tabs. "list" shows every tab; "open" opens a URL in a new tab and makes it active; "select" makes a tab active (other tools act on the active - `browser_wait` — Wait until text appears, text disappears, or an element becomes visible — for pages that - `browser_screenshot` — Take a screenshot and return the image to you. An image costs you roughly 1,000-1,600 tokens, so use it when you need to SEE something: visual or frontend work, - `browser_find` — Find elements by visible text, role (button, link, textbox, checkbox, combobox, option, heading, tab, menuitem, dialog, img, row, cell) or CSS selector. Returns - `browser_act` — Do one thing to an element: click, double_click, right_click, hover, focus, type (value; replaces unless append), press (keys like "Enter", "Tab", "Escape", "Ar - `browser_scroll` — Scroll the page (or an element) down/up, by pixels, or to top/bottom. untilStable keeps scrolling to the bottom while an infinite feed keeps loading, and report - `browser_drag` — Drag one element onto another (HTML5 drag-and-drop, or pointer-driven libraries such as kanban boards). - `browser_upload` — Attach local files (absolute paths, 25 MB total) to a file input, or drop them onto a drop zone. - `browser_inspect` — With a ref or selector: the element's box model, position, computed CSS (or the properties you name), flex/grid layout, visibility, text contrast, overflow, and - `browser_extract` — Turn a table, or a repeated list (search results, product cards, feed items), into JSON rows; or list the links. kind "auto" picks the biggest table, else the b - `browser_console` — Console messages and page errors: uncaught exceptions with stacks, unhandled rejections, failed resources, and console output from when an agent started driving - `browser_network` — Requests the page made: method, URL, status, time, type, size, for fetch/XHR and every resource (documents, scripts, styles, images). failedOnly shows 4xx/5xx a - `browser_dialog` — Decide how alert/confirm/prompt dialogs are answered on a tab you are driving. By default they are dismissed (a confirm returns false) and reported in the actio - `browser_resize` — Set the page viewport to a width and height in CSS pixels, e.g. 375×812 to check a mobile layout. - `browser_eval` — Run JavaScript in the page and return its JSON-serialisable result. An expression returns its value; for statements, use return. Promises are awaited. Runs in t - `browser_downloads` — Files the browser downloaded. "list" shows recent downloads; "wait" waits for the one just started (by a click) to finish; "read" returns a finished download by - `browser_look` — A vision model looks at the page and answers in text: describe it, or answer your question about what is visible (layout, images, charts, whether something look - `browser_ask` — Ask a question about what is on a browser tab. Deputy reads the page itself and returns a - `delegate_goal` — Hand the browser agent a goal in plain language and let it work. It knows the page, the session you are signed into, and what each form accepts. Prefer this ove - `task_status` — Poll a task by id. Use when a delegation is still running or was interrupted. - `answer_task` — Resume a task that stopped because it needed a human — a confirmation, or a sign-in that ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"deputy\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"deputy-mcp\"\n ]\n }\n }\n}" ``` ## Blast radius Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs commands; runs on your machine. - Floor 43, ceiling 71 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/deputy-mcp - Install plan: https://forgeregistry.com/api/v1/packages/deputy-mcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/deputy-mcp - HTML page: https://forgeregistry.com/registry/deputy-mcp - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.