MCP server that scans web pages for WCAG accessibility issues with axe-core, so AI agents can audit and fix accessibility. By
Free
Nothing to run from here
Real Browser 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
Real-browser automation based on Patchright with ad blocking.
Quickstart
# 1 — run it from where its publisher ships it
npx -y real-browser-mcp-server
# 2 — the plan is chosen at checkout, in the browser
# 3 — ask your agent something
> Real-browser automation based on Patchright with ad blocking.
Publishernot claimed
REAll 1 server
real-browser-mcp-server1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Real Browser 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add real-browser-mcp -- npx -y real-browser-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
This is a paid listing, so the CLI has to be signed in and the licence has to be on your account — how the login works. Until then the install stops with the price rather than half-writing a config entry.
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
26 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.
Initialize a browser session with configurable options: headless mode, proxy, viewport, video recording, and resource filtering. Automatically recovers stale sessions.
Takes no parameters.
Example callreturns →
Navigate to a URL with configurable wait conditions, timeout, and automatic retry on failure.
Takes no parameters.
Example callreturns →
Get page content in multiple formats: html, text, markdown, rawHttp, or elements. Extracts text, attributes, or bounding box coordinates. Can save directly to a file.
Takes no parameters.
Example callreturns →
Wait for a selector, navigation event, networkidle state, or a fixed timeout before continuing.
Takes no parameters.
Example callreturns →
Click a page element by CSS selector or annotation ID. Supports iframe context, hover before click, video player API, and automatic retry with fallback selectors.
Takes no parameters.
Example callreturns →
Close the browser session and release all browser resources.
Takes no parameters.
Example callreturns →
Automate form completion and interactive widget verification on web pages. Supports JavaScript-based challenge widgets, image text transcription, and intelligent form field mapping for QA and automated browsing workflows.
Takes no parameters.
Example callreturns →
Scroll the page with configurable direction, amount, and automatic lazy-load triggering.
Takes no parameters.
Example callreturns →
Trace the complete redirect chain of a URL. Tracks HTTP 301/302, JavaScript navigation (window.location, setTimeout), and meta refresh tags. Returns the full path with status codes and headers.
Takes no parameters.
Example callreturns →
Extract structured data from the current page in multiple modes: regex, json, meta, structured, auto, apiDiscovery, parse (string conversion), transform (data format conversion), or links (all links including nested iframes).
Takes no parameters.
Example callreturns →
Press keyboard keys with configurable modifier keys, repeat count, and keystroke delay.
Takes no parameters.
Example callreturns →
Track multi-step task progress with estimated time remaining.
Takes no parameters.
Example callreturns →
Inspect the current page in depth: DOM structure, scripts, stylesheets, accessibility, performance metrics, SEO tags, response headers, loaded technologies, and content-loading strategy recommendations.
Takes no parameters.
Example callreturns →
Record and inspect all network activity. Supports 11 actions: start, stop, get, clear, get_media, get_navigations, get_api_calls, get_intercepted_apis, get_websockets, get_graphql, export_har.
Takes no parameters.
Example callreturns →
Execute custom JavaScript in the page context with async support, return value capture, and iframe targeting.
Takes no parameters.
Example callreturns →
Inspect client-side storage: IndexedDB databases and registered Service Workers on the current page.
Takes no parameters.
Example callreturns →
Re-send a network request inside the page context, reusing the current session headers.
Takes no parameters.
Example callreturns →
Generate JSON schemas from API responses, diff two JSON objects, or create SDK boilerplate code in Python or TypeScript.
Takes no parameters.
Example callreturns →
Browser lifecycle management
Takes no parameters.
Example callreturns →
Page navigation
Takes no parameters.
Example callreturns →
User interactions
Takes no parameters.
Example callreturns →
Content extraction and reading
Takes no parameters.
Example callreturns →
Network operations
Takes no parameters.
Example callreturns →
Page analysis
Takes no parameters.
Example callreturns →
Page snapshot and visual inspection
Takes no parameters.
Example callreturns →
Utility tools
Takes no parameters.
Example callreturns →
Startermost installed
$12 / month
- 10,000 calls a month, included
- 120 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Team
$39 / month
- 50,000 calls a month, included
- 600 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Scale
$89 / month
- 250,000 calls a month, included
- 3,000 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
No call is billed on its own, and this plan carries no monthly call limit. $12 a month covers every tool 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: $8.42
$16.58 left
ATrust score 97 / 100
Release 3.2.8 · scanned 25 Aug 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 score99
Client score97
Findings2 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationnone
Surface digest930992f18d45361b13cf4b3f0f9c437ee119dd8e6095668343d6018847d6c837
Score vectorthreat 99 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| −1.2 | |||
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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. minimal 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. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digest930992f18d45361b
Scanned2026-08-25
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
Pinned to 3.2.8 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
3.2.8
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Real Browser in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.