# io.github.feedthrough/feedthrough (npm · @feedthrough/mcp) Debug bridge inside your web app: an agent reads the DOM, console and network. Any browser. - Trust score: 78/100 (medium) - Change this week: +35 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-08-03 ## Components - npm · `@feedthrough/mcp`: 78/100 (this document), [markdown](https://verifymcp.io/servers/feedthrough-feedthrough/feedthrough-mcp.md), [page](https://verifymcp.io/servers/feedthrough-feedthrough/feedthrough-mcp) ## Channel facts - Registry: `npm` - Package: `@feedthrough/mcp` - Version: `0.3.2` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-08-03. - **Supply Chain Security**: 87/100 - No malware found by supply-chain analysis. - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. - No install/post-install scripts declared. - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. - **Provenance & Transparency**: 97/100 - Source repository is publicly reachable at the declared URL. - Cryptographically verified build provenance (signed, bound to feedthrough/feedthrough). - Clear OSI-approved license (MIT). - Actively maintained (last published 47 days ago). - Disclosure check failed: no security disclosure policy was found in the source repository. - **Schema Quality & AI Usability**: 68/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 3110 tokens (~194/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 27/100 - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### Claude ```bash claude mcp add feedthrough-feedthrough -- npx -y @feedthrough/mcp ``` ### Codex ```bash codex mcp add feedthrough-feedthrough -- npx -y @feedthrough/mcp ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "feedthrough-feedthrough": { "type": "local", "command": [ "npx", "-y", "@feedthrough/mcp" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add feedthrough-feedthrough --command npx --arg -y --arg @feedthrough/mcp ``` ### Hermes ```yaml mcp_servers: feedthrough-feedthrough: command: "npx" args: ["-y", "@feedthrough/mcp"] ``` ### Other ```json { "mcpServers": { "feedthrough-feedthrough": { "command": "npx", "args": [ "-y", "@feedthrough/mcp" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-08-03 (score 78, +4) - [functional improvement] Stability: unverified → 0.27 ### 2026-08-02 (score 74, +54) - [security improvement] Provenance: unverified → pass - [security improvement] Install scripts: unverified → pass - [security improvement] Known CVEs: unverified → partial - [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). - [security] The attested source repository moved: feedthrough/feedthrough - [functional regression] Security disclosure: fail → unverified - [functional improvement] Schema quality: unverified → excellent - [functional improvement] License: unverified → pass - [functional improvement] Dependency health: unverified → partial - [functional improvement] Maintenance: unverified → pass - [functional improvement] MCP protocol: unverified → pass - [functional improvement] Tool coverage: unverified → 100 - [functional] Licence: MIT ### 2026-08-01 (score 20, +2) - [security improvement] Malware scan: unverified → pass - [functional regression] Tool coverage: 100 → unverified - [functional] First check of Schema quality: unverified ### 2026-07-31 (score 18, −7) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-07-30 (score 25, −18) - [security regression] Malware scan: pass → unverified ### 2026-07-27 (score 43) First indexed and scored. ## MCP tools (16) ### `get_instructions` (~79 tokens) Returns 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_status` (~54 tokens) Check 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_logs` (~367 tokens) Return 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. Input parameters: - `levels` (array): Restrict to these levels, e.g. ['error'] to skip noisy warn/info/debug, or ['error', 'warn'] for both. Omit for all levels. - `limit` (integer): Cap the result to the N most-recent entries, e.g. 50. Omit to return everything captured since the bridge connected. - `match` (string): Case-insensitive substring filter on the serialized message content - `since` (number): Only entries with ts >= this (ms epoch). Scope to 'what happened after I did X'. ### `get_network_requests` (~194 tokens) Return 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. Input parameters: - `filter` (string): Filter by URL substring or HTTP method, e.g. 'api' or 'POST' - `since` (number): Only requests with ts >= this (ms epoch). Scope to 'what fired after I did X'. ### `query_dom` (~137 tokens) Query 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. Input parameters: - `selector` (string, required): A CSS selector matched against the whole document, e.g. '.todo-item', '#search-input', or 'nav a'. Returns every match, so it also works as a count or existence check. ### `inspect_element` (~470 tokens) Return 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'). Input parameters: - `properties` (array): Extra computed CSS properties to read by name (kebab-case), e.g. ['transform', 'z-index', 'margin-top']. They come back under a 'requested' object, in addition to the curated default set. - `selector` (string, required): A CSS selector that should resolve to one element, e.g. '#submit-btn' or 'main .card:first-child'. If several match, the first in document order is inspected. ### `click` (~223 tokens) Click 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. Input parameters: - `selector` (string, required): A CSS selector for the element to click, e.g. '#submit-btn' or 'button[type=submit]'. If several match, the first in document order is clicked. ### `fill` (~227 tokens) Set 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. Input parameters: - `selector` (string, required): A CSS selector for the input, textarea, or select to fill, e.g. '#email' or 'input[name=q]'. - `value` (string, required): The full value to set. It replaces the field's current contents (it is not appended); for a