Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
FileForge Browser DevTools is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
823
downloads a day
local
runs on your machine
153
tools declared
What it does
Browser DevTools for agents in your signed-in Chrome: cross-tab watching, route sweeps, bug reports.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user fileforge-browser-devtools-mcp '--' npx -y fileforge-mcp-server
# 2 — ask your agent for something these tools do
# fileforge_app_detect_framework, fileforge_app_get_next_data, fileforge_app_get_route_info and 150 more
FileForge Browser DevTools costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts FileForge Browser DevTools as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user fileforge-browser-devtools-mcp '--' npx -y fileforge-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
153 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Detect the frontend framework used by the page (React, Vue, Next.js, etc.).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| includeStateHints | boolean | no | — |
Extract Next.js __NEXT_DATA__ and server-side props.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Get current route information from the SPA router.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Get localStorage, sessionStorage, and accessible cookies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Detect feature flags exposed in the page (LaunchDarkly, GrowthBook, etc.).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Get a React component tree hint from the page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Inspect a web app in an open tab: detect its framework, and read routes, Next.js data, client storage, feature flags and React tree hints. Use this to understand how an app is built. Use fileforge_coding_action for a full bundle. Read-only, but get_client_storage returns raw localStorage and…
No parameter schema on file.
Unified GraphQL-feel DevTools query. Select modules (console, jsErrors, network, apiResponses, graphql, performance, webSockets, coverage, storageSummary, sourceMaps, requestChains, apiInsights, harSummary, security, thirdParties, issues, recommendations, summary) and presets in one call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| preset | string | no | — |
| query | object | no | Modules to return and their options. Takes priority over preset. Modules: …. |
| autoStartSession | boolean | no | — |
| captureForMs | number | no | — |
| stopAfterCapture | boolean | no | — |
Start an instrumented DevTools capture session for a tab.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Stop the DevTools capture session.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Clear captured DevTools session data without detaching.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Unified session lifecycle action: operation = start | stop | clear | status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| operation | string | yes | — |
Read recent console messages. Legacy action — prefer query_devtools with console module.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| levels | array | no | — |
Get JavaScript errors. Legacy action — prefer query_devtools with jsErrors module.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Inspect network requests. Legacy action — prefer query_devtools with network module.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| store | boolean | no | — |
| includeBodies | boolean | no | — |
| filter | object | no | — |
Extract API response bodies. Legacy action — prefer query_devtools with apiResponses module.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| store | boolean | no | — |
| includeBodies | boolean | no | — |
Get performance timing metrics. Legacy action — prefer query_devtools with performance module.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| store | boolean | no | — |
Inspect WebSocket frames. Legacy action — prefer query_devtools with webSockets module.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| store | boolean | no | — |
Run JS in page context via DevTools. Guarded: dryRun supported, dangerous patterns blocked unless allowDangerous=true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| expression | string | yes | — |
| dryRun | boolean | no | — |
| allowDangerous | boolean | no | — |
Replay a captured network request. Guarded: dryRun supported, non-idempotent methods and risky endpoints blocked unless allowUnsafeMethods=true.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| requestId | string | yes | — |
| overrides | object | no | — |
| dryRun | boolean | no | — |
| allowUnsafeMethods | boolean | no | — |
Export the captured session as a HAR archive on disk.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| filename | string | no | — |
| includeBodies | boolean | no | — |
Extract structured content from pages, tabs or a whole site: text, links, tables, metadata, assets and design tokens. Prefer query_scrape; the others are older single-purpose actions. It can't click or submit; use fileforge_page_interaction for that. crawl_site opens real tabs in your signed-in…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| tabId | string | no | — |
| tabIds | array | no | — |
| url | string | no | — |
| urls | array | no | — |
| sections | array | no | Page sections to scrape. Defaults to all of them. |
| maxPages | number | no | — |
| store | boolean | no | — |
| project | string | no | — |
| source | object | no | — |
| preset | string | no | — |
| query | object | no | Sections to return and their options. Takes priority over preset. Sections: …. |
| beforeSnapshotId | string | no | — |
| afterSnapshotId | string | no | — |
Unified GraphQL-feel audit. Select audit modules (seo, accessibility, performance, conversion, visual, technical, privacyTrust, structuredData, crawl), presets, scores, issues, roadmap, report, and snapshots in one call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | object | no | — |
| preset | string | no | — |
| query | object | no | Modules to return and their options. Takes priority over preset. Modules: …. |
| tabId | string | no | — |
Compare two audit snapshots (by ID) and report score deltas, new issues, resolved issues, and changed modules.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| beforeSnapshotId | string | yes | — |
| afterSnapshotId | string | yes | — |
Audit site routes and links for broken routes, invalid links, duplicate titles, missing canonicals, redirects, and route health.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| routes | array | no | — |
| maxPages | number | no | — |
| maxChecks | number | no | — |
| crawlRef | string | no | — |
| store | boolean | no | — |
| project | string | no | — |
Detect pricing, subscription, feature-count, product-identity, and limitation contradictions across crawled pages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| crawlRef | string | no | — |
| maxPages | number | no | — |
| store | boolean | no | — |
| project | string | no | — |
Review site/listing/manifest copy for Chrome extension policy and claim-safety risks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| listingCopy | string | no | — |
| manifest | object | no | — |
| maxPages | number | no | — |
| store | boolean | no | — |
| project | string | no | — |
Inspect client-side storage for Pro/license flags, exposed secrets, debug flags, tokens, and sensitive state with redacted evidence.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| tabId | string | no | — |
| store | boolean | no | — |
| project | string | no | — |
Reveal one exact redacted client-storage value after an explicit scoped agent request, and log the reveal.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| tabId | string | no | — |
| namespace | string | no | — |
| key | string | no | — |
| location | string | no | — |
Deduplicate and rank issues by impact, severity, confidence, project type, and affected pages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | no | — |
| issues | array | no | — |
| projectType | string | no | — |
| store | boolean | no | — |
Compare two stored audit runs for added/resolved issues and high-level performance/evidence changes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| beforeRef | string | yes | — |
| afterRef | string | yes | — |
| store | boolean | no | — |
Export a stored audit result as a ZIP package with report.md, issues.json, summary.json, and evidence/result.json.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | — |
| filename | string | no | — |
Return a stored audit result in an agent-friendly summary mode such as developer, seo, compliance, conversion, detailed, short, or json-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | — |
| summaryMode | string | no | — |
Classify whether a URL appears sensitive/private before deep authenticated-page scraping.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| title | string | no | — |
| text | string | no | — |
Audit a page or site for SEO, content, policy and client-side security issues. Prefer query_audit with a preset; compare_runs shows what changed between stored audits. Use fileforge_a11y_action, fileforge_perf_action or fileforge_responsive_action for one focused check.…
No parameter schema on file.
Go to a URL in a tab, or in a new tab with newTab.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| preset | string | no | Preset for query_context. "snapshot" is the automation sweet spot (active tab + nav + compact tabs). "basic" is cheaper (no nav fields). |
| query | object | no | Fine-grained projection for query_context. Sections: activeTab, tabs, windows, summary, privacy. Merged on top of preset. |
| tabId | string | no | Tab ID or "active". Omit in navigate for smart URL-reuse behaviour. |
| url | string | no | URL for navigate or open_url_with_capture. |
| active | boolean | no | Focus the tab after navigate / open. |
| newTab | boolean | no | Force a new tab in navigate even if an existing tab has the same URL. |
| bypassCache | boolean | no | — |
| direction | string | no | Direction for history action. |
| until | string | no | Condition to wait for. |
| urlIncludes | string | no | URL substring — required for wait(until="url") and close_tabs_matching. |
| timeoutMs | number | no | — |
| idleMs | number | no | Quiet period before considering tab idle. |
| titleIncludes | string | no | Title substring for close_tabs_matching. |
| keepActiveTab | boolean | no | Protect active tab from close_tabs_matching. |
| dryRun | boolean | no | Simulate without closing. |
| keepOpen | boolean | no | Leave tab open after capture. |
| includeApiBodies | boolean | no | — |
| includePerformance | boolean | no | — |
| includeScreenshot | boolean | no | — |
Read and act inside one open page: get text, snapshots and forms, click, fill, scroll, assert, and debug selectors. click and fill act on the real signed-in page, so they can submit or change data. hide_elements lasts until restore_hidden_elements. Use fileforge_qa_testing for repeatable checks…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| tabId | string | no | — |
| store | boolean | no | — |
| selector | string | no | CSS selector. |
| selectors | array | no | — |
| timeoutMs | number | no | — |
| depth | number | no | Depth for DOM snapshot |
| fallback | boolean | no | — |
| maxHtmlLength | number | no | — |
| textSampleLimit | number | no | — |
| includeScreenshotFallback | boolean | no | — |
| project | string | no | — |
| includeSelectors | boolean | no | — |
| value | string | no | Value to fill |
| direction | string | no | — |
| amount | number | no | — |
| maxTextLength | number | no | — |
| assertions | array | no | List of assertions. Each has: type, value?, selector?, text?, count?. |
| checks | array | no | Specific checks to run (smoke_test or check_layout). Defaults apply if omitted. |
| includeHidden | boolean | no | Include hidden elements in find_errors / check_broken_images / check_links. |
Capture a screenshot of a tab. The tab must be the visible one in its window; otherwise the call returns TAB_NOT_VISIBLE.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| fullPage | boolean | no | — |
| format | string | no | — |
| store | boolean | no | — |
| includeBase64 | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping screenshot artifacts |
| name | string | no | Optional artifact filename stem |
| url | string | no | Optional page URL to include in metadata |
| viewport | string | no | Optional viewport label or dimensions |
Capture a stitched full-page screenshot of a tab and store it as a local artifact.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| store | boolean | no | — |
| includeBase64 | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping screenshot artifacts |
| name | string | no | Optional artifact filename stem |
| maxHeight | number | no | — |
| scrollWaitMs | number | no | — |
| hideFixedElements | boolean | no | — |
Capture a screenshot of a specific page element by selector and store it as a local artifact.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
| tabId | string | no | — |
| padding | number | no | — |
| store | boolean | no | — |
| includeBase64 | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping screenshot artifacts |
| name | string | no | Optional artifact filename stem |
Capture a rectangular viewport or page region and store it as a local artifact.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| x | number | yes | — |
| y | number | yes | — |
| width | number | yes | — |
| height | number | yes | — |
| coordinateSpace | string | no | — |
| tabId | string | no | — |
| store | boolean | no | — |
| includeBase64 | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping screenshot artifacts |
| name | string | no | Optional artifact filename stem |
Start an in-page element picker, capture the chosen element, and store it as a local artifact.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| padding | number | no | — |
| timeoutMs | number | no | — |
| store | boolean | no | — |
| includeBase64 | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping screenshot artifacts |
| name | string | no | Optional artifact filename stem |
Capture a URL across multiple viewport presets and return stored screenshot artifact refs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| viewports | array | no | — |
| fullPage | boolean | no | — |
| active | boolean | no | — |
| keepOpen | boolean | no | — |
| timeoutMs | number | no | — |
| settleMs | number | no | — |
| store | boolean | no | — |
| includeBase64 | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping matrix artifacts |
| name | string | no | Optional artifact filename stem |
Capture and store a baseline screenshot for later comparison.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| name | string | yes | Baseline name |
| viewport | string | no | — |
| fullPage | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping baseline artifacts |
| active | boolean | no | — |
| keepOpen | boolean | no | — |
Capture and store baseline screenshots for multiple routes and viewports.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseUrl | string | yes | — |
| routes | array | yes | — |
| viewports | array | no | — |
| namePrefix | string | no | — |
| fullPage | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping baseline artifacts |
| active | boolean | no | — |
| keepOpen | boolean | no | — |
| timeoutMs | number | no | — |
| settleMs | number | no | — |
| store | boolean | no | — |
Compare the current state of a URL against its stored baseline.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| name | string | yes | — |
| viewport | string | no | — |
| fullPage | boolean | no | — |
| ignoreSelectors | array | no | — |
| store | boolean | no | — |
| project | string | no | — |
| run | string | no | Optional run ID for grouping comparison artifacts |
| threshold | number | no | — |
Compare multiple routes against their baselines.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseUrl | string | yes | — |
| routes | array | yes | — |
| viewports | array | no | — |
| namePrefix | string | no | — |
| fullPage | boolean | no | — |
| ignoreSelectors | array | no | — |
| store | boolean | no | — |
| project | string | no | — |
| threshold | number | no | — |
Extract computed CSS for an element.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
| tabId | string | no | — |
Extract the color palette from the page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Detect fonts used on the page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
Measure the size and position of an element.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | — |
| tabId | string | no | — |
Export a visual diff bundle as a ZIP.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | — |
| filename | string | no | — |
Capture and compare how pages look: screenshots of a page, element or region, baselines, visual diffs across routes and viewports, and computed CSS, colors and fonts. Use fileforge_responsive_action to find layout bugs. Files and baselines are saved locally. capture_screenshot needs the tab to be…
No parameter schema on file.
Check one page's accessibility: run an audit, read the accessibility tree, and check keyboard navigation and color contrast. Use this for focused accessibility work, and fileforge_audit_action for a wider audit. Doesn't change the page; results can be stored locally. Needs the extension.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| tabId | string | no | — |
| standard | string | no | — |
| store | boolean | no | — |
List the API calls captured in a tab, grouped by path, method or status and by domain. Stores the result by default.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| tabId | string | no | — |
| groupBy | string | no | — |
| includeBodies | boolean | no | — |
| store | boolean | no | — |
| filename | string | no | — |
One-shot Chrome coding context for a URL or active tab: DOM, selectors, forms, framework, console, network, API, a11y, responsive, perf, and optional screenshot.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | Optional URL. If omitted, inspect the active tab. |
| tabId | string | no | — |
| reload | boolean | no | — |
| keepOpen | boolean | no | — |
| includeScreenshot | boolean | no | — |
| includeApiBodies | boolean | no | — |
| includeStorage | boolean | no | — |
| includePerformance | boolean | no | — |
| domDepth | number | no | — |
| timeoutMs | number | no | — |
| settleMs | number | no | — |
| store | boolean | no | — |
| project | string | no | — |
Fast hidden-Chrome route sweep for coding: captures load-time console, network, API failures, a11y/responsive issues, selectors, and compact summaries per route.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseUrl | string | yes | — |
| routes | array | yes | — |
| includeScreenshot | boolean | no | — |
| includeApiBodies | boolean | no | — |
| includePerformance | boolean | no | — |
| domDepth | number | no | — |
| timeoutMs | number | no | — |
| settleMs | number | no | — |
| store | boolean | no | — |
| project | string | no | — |
Capture a compact bug-fix bundle from Chrome for Codex: page context, issues, HAR-style network export, and optional screenshot/API bodies.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| title | string | no | — |
| includeScreenshot | boolean | no | — |
| includeApiBodies | boolean | no | — |
| includeStorage | boolean | no | — |
| timeoutMs | number | no | — |
| settleMs | number | no | — |
| project | string | no | — |
Extract and store an article/documentation context bundle for research debugging. Captures article text, heading outline, metadata, links, code blocks, framework info, and page route state. Ideal for docs, blogs, changelogs, README pages, and research pages that an agent needs to consume.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | Optional URL to open. If omitted, use the active tab. |
| tabId | string | no | — |
| maxTextLength | number | no | — |
| includeComparison | boolean | no | Include visible vs article comparison data |
| store | boolean | no | — |
| project | string | no | — |
Get context for fixing code in one call. inspect_page returns a page's framework, selectors, forms, console, network and performance; audit_routes sweeps many routes for errors; bug_context and article_context gather focused context. Use fileforge_qa_testing for pass/fail checks. Opens pages in…
No parameter schema on file.
Export a stored result ref to a file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | — |
| format | string | no | — |
| filename | string | no | — |
Run a SQL query and export results to a file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| format | string | no | — |
| filename | string | no | — |
Write stored results or SQL query output to a file in formats such as CSV, JSON, Markdown, HAR or ZIP. Use this to hand data to another tool. Use fileforge_result_action or fileforge_sql_action to read data without creating a file. Writes only to FileForge's exports folder, and a filename you…
No parameter schema on file.
Inspect the loaded FileForge extension manifest and declared runtime surfaces.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| store | boolean | no | — |
| project | string | no | — |
Inspect extension chrome.storage areas with redacted values and reveal metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| area | string | no | — |
| store | boolean | no | — |
| project | string | no | — |
Inspect the extension service-worker status and runtime identity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| store | boolean | no | — |
| project | string | no | — |
Reveal one exact redacted extension storage value after an explicit scoped agent request, and log the reveal.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| area | string | no | — |
| key | string | yes | — |
Inspect content-script/page injection evidence on a tab, including selectors and FileForge DOM nodes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| selectors | array | no | — |
| store | boolean | no | — |
| project | string | no | — |
Inspect declared extension permissions, host permissions, and content-script matches.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| store | boolean | no | — |
| project | string | no | — |
Collect recent extension/MCP bridge failures with structured failure details.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| store | boolean | no | — |
| project | string | no | — |
Run a composable extension QA check: manifest, permissions, storage, service worker, injection, and errors.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| selectors | array | no | — |
| store | boolean | no | — |
| project | string | no | — |
Inspect a Chrome extension: manifest, permissions, storage, service worker, content-script injection and errors. Use this to debug an extension you're building, and fileforge_audit_action for store policy checks. reveal_storage_value needs FILEFORGE_ALLOW_SECRET_REVEAL=1. Needs the extension.
No parameter schema on file.
Convert a file to another format.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL, or a local path in an allowed folder. |
| from | string | no | Source format |
| to | string | yes | Target format |
Extract plain text from a file (PDF, DOCX, etc.).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Parse and decode a Data URI.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataUri | string | yes | — |
| textPreviewLimit | number | no | — |
Inspect a Data URI: MIME, encoding, decoded size, preview-safe text, image dimensions, and warnings.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataUri | string | yes | — |
| includeTextPreview | boolean | no | — |
| textPreviewLimit | number | no | — |
Decode a Data URI into a local artifact and return compact metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataUri | string | yes | — |
| project | string | no | — |
| run | string | no | — |
| name | string | no | — |
| includeTextPreview | boolean | no | — |
Find Data URIs embedded in the active page DOM, styles, links, images, media, and scripts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| store | boolean | no | — |
| project | string | no | — |
| limit | number | no | — |
Convert an image Data URI to PNG, JPEG, or WebP using the browser canvas and store it as an artifact.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataUri | string | yes | — |
| format | string | no | — |
| quality | number | no | — |
| tabId | string | no | — |
| project | string | no | — |
| run | string | no | — |
| name | string | no | — |
Fetch a resource URL and save it locally.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| store | boolean | no | — |
Fetch and parse a resource (JSON, CSV, XML, etc.).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| format | string | no | — |
| store | boolean | no | — |
Fetch, parse and convert files, extract text, and decode data URIs, including those in a page. Use this for documents and embedded assets, and fileforge_scrape_action for HTML pages. Fetches public URLs without your browser session; private addresses need FILEFORGE_ALLOWED_FETCH_HOSTS. Local paths…
No parameter schema on file.
Save the text of a tab's page to local memory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| tabId | string | no | — |
| project | string | no | — |
| query | string | no | — |
| question | string | no | — |
| url | string | no | — |
| limit | number | no | — |
| ref | string | no | — |
| offset | number | no | — |
| store | boolean | no | — |
Create a local note.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | — |
| body | string | yes | — |
| tags | array | no | — |
| url | string | no | Associated URL, if any |
List saved notes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tag | string | no | — |
| limit | number | no | — |
| offset | number | no | — |
Search notes by text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | number | no | — |
Keep local notes: create, list and search them. Use this to save findings across sessions. Use fileforge_memory_action to save page content and fileforge_report_action for shareable evidence. Notes stay in ~/.fileforge, and there's no update or delete action.
No parameter schema on file.
Run a performance audit on a URL across viewports and return Core Web Vitals. Use this for a performance check of one page. Use fileforge_devtools_action for raw session data and fileforge_audit_action for SEO, content and security. Loads the URL in its own tab, closes it afterward, and stores the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| url | string | yes | — |
| viewports | array | no | — |
| includeScreenshot | boolean | no | — |
| timeoutMs | number | no | — |
| settleMs | number | no | — |
| networkIdleMs | number | no | — |
| networkIdleTimeoutMs | number | no | — |
| store | boolean | no | — |
| project | string | no | — |
Load a page, plus any routes, and list issues on each. Fails on high or critical issues. Stores the result by default.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| url | string | no | — |
| baseUrl | string | no | — |
| routes | array | no | — |
| store | boolean | no | — |
| tabId | string | no | — |
| selector | string | no | — |
| watchId | string | no | — |
| timeoutMs | number | no | — |
| project | string | no | — |
Generate a bug report bundle from the active tab.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| title | string | yes | — |
| include | array | no | — |
| format | string | no | — |
Generate a PR evidence bundle (screenshots, QA results, diff).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | — |
| urls | array | no | — |
| include | array | no | — |
Create a debug bundle with full diagnostics.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tabId | string | no | — |
| title | string | yes | — |
Generate evidence bundles from the active tab: a bug report, PR evidence with screenshots and QA results, or a full debug bundle. Use this when you need something to share or attach. Use fileforge_coding_action for context while working. Bundles are saved locally and can contain page data, so…
No parameter schema on file.
Find layout bugs across screen widths: scan a URL, and locate overflow and overlapping elements. capture_matrix takes a screenshot at each viewport. Use fileforge_visual_action to compare screenshots against baselines. Loads the page in your session and can store results; it doesn't change the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | — |
| url | string | no | — |
| widths | array | no | Viewport widths to test |
| checks | array | no | — |
| tabId | string | no | — |
| store | boolean | no | — |
Retrieve a stored result by its ref.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | The result ref (e.g. scrape_page_20260509_abc123) |
List stored results, newest first. Optionally filter by project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project | string | no | Filter by project name. |
| limit | number | no | — |
| offset | number | no | — |
Search stored results by keyword across URL, tool name, and data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| project | string | no | — |
| limit | number | no | — |
Get a paginated slice of a stored result.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | — |
| offset | number | no | — |
| limit | number | no | — |
Read results other tools stored in ~/.fileforge: fetch one by ref, list them, search them, or slice a large one. Use this when a tool returns a ref instead of full data. Use fileforge_sql_action to query across results and fileforge_export_action to write one to a file. Works without the extension.
No parameter schema on file.
Create a routine (prompt or steps input).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| description | string | no | — |
| inputType | string | no | — |
| prompt | string | no | — |
| steps | array | no | — |
| propsSchema | object | no | — |
| defaultProps | object | no | — |
| permissions | object | no | — |
| triggerType | string | no | — |
| cronExpression | string | no | — |
| enabled | boolean | no | — |
| concurrencyPolicy | string | no | — |
| retryPolicy | object | no | — |
| timeoutConfig | object | no | — |
| retentionPolicy | object | no | — |
| exportConfig | object | no | — |
| storageConfig | object | no | — |
| notificationConfig | object | no | — |
| metadata | object | no | — |
| createdBy | string | no | — |
Update a routine (snapshots a new version).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
| patch | object | yes | — |
| reason | string | no | — |
| updatedBy | string | no | — |
Fetch a routine (optionally a specific version).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
| version | number | no | — |
Duplicate an existing routine.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
| name | string | no | — |
Enable a routine.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
Disable a routine.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
Validate a routine or an arbitrary step array against the tool catalog.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | no | — |
| steps | array | no | — |
| propsSchema | object | no | — |
| defaultProps | object | no | — |
| permissions | object | no | — |
Produce a dry-run report for a routine without executing anything.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
| propOverrides | object | no | — |
| simulateMissing | boolean | no | — |
Enqueue a routine for execution.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
| propOverrides | object | no | — |
| idempotencyKey | string | no | — |
| priority | number | no | — |
| trigger | string | no | — |
| retryOfRunId | string | no | — |
| parentRunId | string | no | — |
Stop / cancel a running or queued run.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| runId | string | yes | — |
| reason | string | no | — |
List runs for a routine.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | yes | — |
| status | string | no | — |
| limit | number | no | — |
| offset | number | no | — |
Get full details of a run (steps + events + artifacts).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| runId | string | yes | — |
| includeStepResults | boolean | no | — |
| includeEvents | boolean | no | — |
Export a run as JSON or CSV.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| runId | string | yes | — |
| format | string | no | — |
| includeRaw | boolean | no | — |
| includeLogs | boolean | no | — |
| includeSummary | boolean | no | — |
Return the FileForge tool capability catalog.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filterPermissions | object | no | Only return actions whose required permissions are all granted in this map. |
Return planning context (registry slice + schema + planning prompt) for an LLM to use when converting a prompt into an executable step array.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | — |
| propsSchema | object | no | — |
| permissions | object | no | — |
| hints | array | no | — |
Validate an LLM-produced step array and save it as a routine (new or updated).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| routineId | string | no | — |
| plannedSteps | array | yes | — |
| propsSchema | object | no | — |
| defaultProps | object | no | — |
| permissions | object | no | — |
| name | string | no | — |
| description | string | no | — |
| reason | string | no | — |
Check that the MCP server is alive.
No parameter schema on file.
Get the current status of the MCP bridge and extension connection.
No parameter schema on file.
List all registered tools and their availability.
No parameter schema on file.
Get recent RPC request log entries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max entries to return |
| failuresOnly | boolean | no | — |
| includeDetails | boolean | no | — |
Check FileForge itself: whether the server and extension are connected, their versions, which tools are available, and recent requests. Use status when other tools report a bridge or connection error. It doesn't touch page content.
No parameter schema on file.
Search across pages, notes, history, and bookmarks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | number | no | — |
Search within the text of a specific page result.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| ref | string | no | — |
Search saved notes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | number | no | — |
Search browser history.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | number | no | — |
Search browser bookmarks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| limit | number | no | — |
Search local data by text: saved pages, stored results, notes, browser history and bookmarks. Use all to search everything, or narrow it to one source. Use fileforge_memory_action to compare page visits and fileforge_scrape_action to read a live page. History and bookmarks need the extension.
No parameter schema on file.
List all available SQL tables.
No parameter schema on file.
Describe the columns and schema of a table.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| table | string | yes | — |
Run a SQL SELECT query against stored data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | SQL SELECT statement |
| ref | string | no | Optional result ref to scope the query |
| limit | number | no | — |
| offset | number | no | — |
Run a SQL query and export the results to a file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| format | string | no | — |
| filename | string | no | — |
Query FileForge's stored results with SELECT-only SQL. Use list_tables and describe_table to see the schema, query to read rows, and export_query to write rows to a file. Covers saved results and scraped pages, links and tables, not the live browser. Use fileforge_result_action to fetch a single…
No parameter schema on file.
Start an asynchronous task made of structured FileForge tool invocations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | no | Saved task id to run. |
| title | string | no | Optional label for an inline action task. |
| actions | array | no | Ordered FileForge tool invocations: [{ tool, params, name?, required? }]. |
| task | string | no | Legacy label alias. Do not use as a prompt. |
| description | string | no | Legacy label alias. Do not use as a prompt. |
| url | string | no | Optional starting URL |
| mode | string | no | — |
| maxMinutes | number | no | — |
| capture | array | no | — |
| recipeName | string | no | Saved workflow recipe to run asynchronously. |
| recipe | object | no | Inline workflow recipe to save and run asynchronously. |
| pollIntervalMs | number | no | — |
| timeoutMs | number | no | — |
| store | boolean | no | — |
Add a saved task made of structured FileForge tool invocations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | no | Optional explicit task id. |
| title | string | no | Task label. |
| task | string | no | Legacy label alias. Do not use as a prompt. |
| description | string | no | Legacy label alias. Do not use as a prompt. |
| actions | array | yes | Ordered FileForge tool invocations: [{ tool, params, name?, required? }]. |
| mode | string | no | — |
| status | string | no | — |
| result | object | no | — |
Edit a saved task record.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
| title | string | no | Task label. |
| task | string | no | Legacy label alias. Do not use as a prompt. |
| description | string | no | Legacy label alias. Do not use as a prompt. |
| actions | array | no | Ordered FileForge tool invocations: [{ tool, params, name?, required? }]. |
| mode | string | no | — |
| status | string | no | — |
| result | object | no | — |
Get the current status of a running task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
Get progress events for a task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
| since | string | no | ISO timestamp to get events after |
Pause a running task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
Resume a paused task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
Cancel a running task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
List all tasks (running, paused, completed).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
Delete a task and its event history.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
Export task results and artifacts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| taskId | string | yes | — |
| format | string | no | — |
Monitor a page for changes over time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| intervalMinutes | number | no | — |
| maxMinutes | number | no | — |
| watch | array | no | Selectors or data types to watch |
| store | boolean | no | — |
Collect rows from a paginated table into a local dataset.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| selector | string | no | CSS selector for the table |
| maxPages | number | no | — |
| store | boolean | no | — |
Run a search on a website and collect all results into a dataset.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| query | string | yes | — |
| maxPages | number | no | — |
| store | boolean | no | — |
Run multi-step work two ways. Tasks (start, add, status, monitor_page) track one job. Routines (create, validate, dry_run, run, plan_from_prompt) are saved and can be scheduled, but cron only fires while this server runs. For a single step, call the tool directly. Runs act in your browser, pausing…
No parameter schema on file.
Start recording a browser workflow (clicks, typing, navigation).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Recipe name to save as |
| tabId | string | no | — |
| steps | array | no | Optional explicit recipe steps to save immediately. |
| assertions | array | no | Optional assertions saved with the recipe. |
Stop the current workflow recording and save the recipe.
No parameter schema on file.
List all saved workflow recipes.
No parameter schema on file.
Replay a saved workflow recipe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| inputs | object | no | Variable substitutions for the recipe |
| capture | array | no | — |
| assertions | array | no | — |
| store | boolean | no | — |
Export a workflow recipe to a file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| format | string | no | — |
Delete a saved workflow recipe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
Record browser actions as a reusable recipe, then list, replay, export or delete recipes. Use this to repeat a sequence you did by hand. Use fileforge_task_action for scheduled or multi-step routines. Replaying really clicks and types in your signed-in browser, and delete_recipe is permanent.…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install FileForge Browser DevTools or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.3.0 · scanned 6 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digeste002a686de77de8776a2603c90d8ba5af6dd5de9c4d14889da040402c6e4a07e
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digeste002a686de77de87
Scanned2026-11-06
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.0. Pin a release below and the command asks for exactly that one.
0.3.0
5 Nov 2026
latestNo release note was published with this version.
0.2.2
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish FileForge Browser DevTools can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.