Feedthrough vs Public Browser
A side-by-side look at the Feedthrough and Public Browser MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Feedthrough for browser automation work as a local process; choose Public Browser for browser automation as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Feedthrough when
- You need dedicated capabilities in the Browser Automation domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
FEEDTHROUGH_PORT. - You want tools like
get_instructions, connection_status, get_console_logs.
Choose Public Browser when
- You need dedicated capabilities in the Browser Automation domain.
- You prefer a local stdio subprocess transport.
- You want tools like
virtual_desk, view_page, click.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Browser Automation | Browser Automation |
| Quality signal | 61/100 · Good | 64/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | FEEDTHROUGH_PORT | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 4 | 19 |
| Directory activity | 3 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 16 | 25 |
| Full listing | View Feedthrough | View Public Browser |
Tools & capabilities
Feedthrough tools 16
get_instructionsReturns the Feedthrough usage guide as a Markdown text document, with sections for the recommended workflow, tool-ordering tips, and selector advice. Read-only and takes no arguments; it does not touch the page or require a connected browser. Call it at the start of a debugging session if you are unfamiliar with Feedthrough or want a quick refresher.connection_statusCheck whether a browser with the Feedthrough bridge is currently connected. Returns connected flag and a list of open tabs (id, url, which is active). Call this first — every tool except get_instructions requires a connected browser.get_console_logsReturn console output captured since the bridge connected. Covers every console method — log/warn/error/info/debug plus dir, table, assert, trace, count, countReset, time/timeEnd/timeLog, group/groupCollapsed/groupEnd, and clear. Each entry has a 'level' (the closest of the five standard levels); rich methods also carry a 'method' field, and console.trace() plus failing console.assert() entries include a 'stack'. Uncaught exceptions and unhandled promise rejections are also captured (level 'error', method 'uncaught' / 'unhandledrejection') even though the app never logged them. When the app is noisy with framework or deprecation warnings, pass levels: ['error'] (or ['error', 'warn']) so the real errors aren't buried, and use 'match' to narrow by content. Pass 'since' (a ms timestamp from an earlier entry's 'ts', or Date.now() before an action) to see only what happened after that point. Read-only: it returns a passively captured buffer and neither clears the console nor changes the page. Always check this early — app errors and debug output often identify the root cause immediately.get_network_requestsReturn all fetch and XHR requests captured since the bridge connected, including URL, method, HTTP status, duration, request and response headers, and request and response bodies (bodies capped at 10 KB each — anything longer is truncated with a marker; binary responses are summarised). Use this to find failed requests (4xx/5xx), wrong URLs, slow calls, or to inspect what the app actually sent or received. Use 'filter' to narrow by URL/method and 'since' (a ms timestamp) to see only requests that fired after an action. Read-only: it returns a passively captured log and does not issue or modify any requests.query_domQuery the page with a CSS selector and return a summary of every matching element (tag, id, classes, text content). Good for counting list items, checking what's rendered, or finding the right selector before calling inspect_element or click. Read-only: it only reads the DOM and never changes the page. Returns an empty list (not an error) when nothing matches, so it is also a safe existence check.inspect_elementReturn full details about a single element: tag, id, classes, all attributes, text content, bounding rect (top/right/bottom/left/width/height + page scroll and an inViewport flag), a compact ancestor 'path' (e.g. 'body > main > div#app > button.cta'), a curated set of computed styles (layout, box model, typography, positioning, flex/grid), an 'overflow' block when content is clipped/overflowing (scroll vs client size + per-axis x/y flags), a 'clipped' block when an ancestor's overflow cuts the element off (the clipping ancestor + which edges), an effective-visibility check ('visible' boolean, with a 'hiddenReason' such as 'ancestor div#modal display:none' or 'opacity:0' when not visible, accounting for ancestors), an occlusion check ('hittable' boolean from a center-point hit-test, with 'occludedBy' naming the element actually on top when something covers it), an 'a11y' block (resolved role, best-effort accessible name, and key states like expanded/checked/selected/disabled/hidden/tabindex), a 'pseudo' block with ::before/::after content when set (icon fonts, generated text), and live form state where applicable (an input's current value, checked, disabled, etc.). Pass 'properties' to additionally read any specific computed CSS properties by name — they come back under 'requested'. Use this to understand why an element looks wrong or isn't behaving as expected. Read-only: it only reads element state and never changes the page, and it returns an error if the selector matches nothing. Note: addEventListener-registered event handlers cannot be read from the page; only inline on* handler attributes appear (in 'attributes').clickClick an element by calling its native click(), which fires a click event and runs the default activation: following a link, toggling a checkbox or radio, submitting a form. Prefer an id selector (#submit-btn) for reliable targeting. Note it does NOT synthesize the preceding pointer/mouse sequence (pointerdown / mousedown / mouseup) or move focus, so a handler wired specifically to those events rather than to click won't fire; for keyboard-driven activation use press_key instead. Behavior: if the selector matches nothing the call returns an error; it does not scroll the element into view, and it does not wait for any resulting navigation, network, or re-render to settle, returning as soon as the click is dispatched. Observe the effect with a follow-up get_console_logs / get_network_requests / query_dom. Returns the tag and id of the clicked element.fillSet the value of an input, textarea, or select element. Focuses the element, assigns the value through the element's native value setter (so React/Vue controlled inputs register the change), then fires bubbling input and change events. The value is set in one shot, not typed character by character, so per-keystroke handlers (keydown / keypress / keyup / beforeinput) do NOT fire; to send Enter to submit or trigger a key shortcut, follow with press_key. Prefer an id selector (#search-input). If the selector matches nothing the call returns an error; it returns as soon as the events are dispatched and does not wait for downstream validation or re-renders. Returns the tag and the value that was set.hoverHover over an element by dispatching synthetic, bubbling mouseover and mouseenter events from inside the page. This triggers JavaScript hover handlers (onMouseEnter / onMouseOver), so hover-only UI that mounts on hover (tooltips, popovers, dropdown and submenus) appears in the DOM; follow up with query_dom, get_html, or inspect_element to read what was revealed. Three limits to know: it does NOT activate the CSS :hover pseudo-class (that is driven by the real cursor, not synthetic events), so styles or content shown purely via :hover in CSS will not change; no mouseout / mouseleave is sent, so the hovered state stays until the app tears it down or you interact elsewhere; and the events are dispatched whether or not the element is visible or in the viewport (it is not scrolled into view), so a successful call does not by itself confirm anything rendered. If the selector matches nothing the call returns an error. Returns the tag of the hovered element.press_keyDispatch a key press (keydown/keypress/keyup) on an element — e.g. Enter to submit a search, Escape to close a modal, Tab to move focus, or ArrowUp/ArrowDown in a list. Use named keys (Enter, Escape, Tab, Backspace, Delete, ArrowUp/Down/Left/Right) or a single character. Note: this fires key handlers but does NOT insert text into inputs — use 'fill' to set an input's value, then press_key for the submit/shortcut. If the selector matches nothing the call returns an error; it dispatches the key events and returns without waiting for any resulting navigation or re-render.get_htmlReturn the outerHTML of an element (capped at 50 KB). Use this when the summarised query_dom output isn't enough and you need to see the actual markup/structure of a region. Read-only: it only reads the DOM and makes no changes, and it returns an error if the selector matches nothing.get_page_infoReturn basic page context: current URL, document title, readyState, viewport size, scroll position, and user agent. Read-only and non-destructive: it only reads page state and makes no changes. Useful to orient at the start of a session or confirm a navigation happened.- +4 more on the listing page
Public Browser tools 25
virtual_deskList all open tabs with IDs, URLs and state. Call it first in every session, after a reconnect, or when unsure; reuse a listed tab ID instead of opening duplicates. Cheap, call liberally.view_pageSee what is on the page: text plus stable element refs for click/type/fill_form. Default filter 'interactive' lists actionable elements; for paragraphs or table cells call view_page(ref, filter: 'all'). Collapsed containers show as [eXX role, N items] — expand with view_page(ref: 'eXX', filter: 'all').clickClick an element by ref, CSS selector, visible text, or viewport x/y (canvas, pixel-precise targets). Dispatches real CDP mouse events. A click that opens a new tab is reported in the response. The DOM diff (NEW/REMOVED/CHANGED) arrives with the next page action, or here with wait_for_diff: true.typeType text into an input identified by ref or CSS selector. For 2+ fields use fill_form; for special keys (Enter, Escape, Tab, arrows) or shortcuts (Ctrl+K) use press_key.fill_formFill a whole form in one call: text inputs, <select> (by value or visible label), checkboxes (boolean) and radio buttons. One round-trip; partial errors do not abort and each field reports its own status. On per-field errors call view_page and retry the failing fields.press_keyPress a key or shortcut (Enter, Escape, Tab, arrows, Ctrl+K). Optionally focus an element first via ref or selector.scrollScroll the page, a container, or an element into view. Reports the position and content growth (scrollHeight delta — detects lazy-loaded content) and handles settle timing. Use container_ref/container_selector plus direction to scroll inside a container.dragDrag a source onto a target: HTML5 drag-and-drop (draggable lists, SortableJS, React DnD) and mouse drags (sliders, canvas, resize handles). Scrolls the source into view; says when no page reaction was detected. Source: from_ref/from_selector or from_x+from_y; target: to_ref/to_selector or to_x+to_y.navigateNavigate the active tab to a URL, or action 'back' / 'reload' (all refs become stale after reload). Waits for settle. Overwrites the user's active tab — check virtual_desk first; the first call per session is redirected to virtual_desk.switch_tabOpen a new tab, switch to a tab by ID (from virtual_desk), or close one. Prefer 'open' over navigate when the user's active tab must stay untouched. Refs from the previous tab are invalid afterwards — call view_page before acting.tab_statusActive tab's cached URL, title, ready state and errors — a cheap mid-workflow sanity check ('did my click navigate?'). Not for tab discovery or page content.wait_forWait until a condition holds: element visible, page text present, URL match, network idle, or a JS expression true. Prefer condition 'text' over a JS expression for 'has the page said X yet'. assert: true checks once and fails instead of waiting.- +13 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Feedthrough
{
"mcpServers": {
"feedthrough-feedthrough": {
"command": "npx",
"args": [
"-y",
"@feedthrough/mcp"
],
"env": {
"FEEDTHROUGH_PORT": "YOUR_FEEDTHROUGH_PORT_HERE"
}
}
}
}
Public Browser
{
"mcpServers": {
"public-browser": {
"command": "npx",
"args": [
"-y",
"public-browser@latest"
]
}
}
}
Frequently asked questions
Feedthrough is categorized under Browser Automation and uses a local stdio subprocess. Public Browser belongs to Browser Automation and uses a local stdio subprocess. Pick Feedthrough for browser automation work and Public Browser for browser automation.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Feedthrough is listed as free. Auth: no auth required. Public Browser has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add feedthrough-feedthrough and public-browser as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Feedthrough has a quality signal of 61/100 (Good) with 3 views, 0 installs and 4 GitHub stars. Public Browser has 64/100 (Good) with 1 views, 0 installs and 19 GitHub stars.