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 Chrome 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
MCP server that gives AI access to your real Chrome tabs via a bridge extension
Quickstart
# 1 — run it from where its publisher ships it
npx -y mcp-real-chrome
# 2 — ask your agent something
> MCP server that gives AI access to your real Chrome tabs via a bridge extension
Real Chrome is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
DEAll 1 server
DeepakSilaych1 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 Chrome 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-chrome-mcp -- npx -y mcp-real-chromeReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
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
27 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.
Attach debugger and start recording console log entries for a tab
Takes no parameters.
Example callreturns →
Stop console recording for the tab
Takes no parameters.
Example callreturns →
Return captured console entries for a tab
Takes no parameters.
Example callreturns →
Read content from a tab. Formats:
Takes no parameters.
Example callreturns →
Get the current text selection in a tab
Takes no parameters.
Example callreturns →
List cookies for a URL
Takes no parameters.
Example callreturns →
Read localStorage for a tab origin
Takes no parameters.
Example callreturns →
Click the first element matching a CSS selector
Takes no parameters.
Example callreturns →
Type into an input element matched by selector
Takes no parameters.
Example callreturns →
Fill multiple form fields by selector. Supports input, textarea, select (dropdown), checkbox (value=true/false), radio, and contentEditable. Set submit=true to submit the form after filling.
Takes no parameters.
Example callreturns →
Click an element and wait for a result. Use waitForNavigation=true when the click triggers a page navigation. Use waitFor=selector to wait for a specific element to appear (e.g. a modal or result). Saves an extra round-trip vs click_element + polling.
Takes no parameters.
Example callreturns →
Scroll the page by direction
Takes no parameters.
Example callreturns →
Navigate a tab to a URL
Takes no parameters.
Example callreturns →
History back for a tab
Takes no parameters.
Example callreturns →
History forward for a tab
Takes no parameters.
Example callreturns →
Reload a tab
Takes no parameters.
Example callreturns →
Navigate to a URL and wait for the page to fully load. Optionally wait for a specific CSS selector to appear after load. Faster than navigate_to + polling for content.
Takes no parameters.
Example callreturns →
Attach debugger and start recording network requests for a tab
Takes no parameters.
Example callreturns →
Stop network recording and detach debugger for that capture on the tab
Takes no parameters.
Example callreturns →
Return captured HTTP requests for a tab
Takes no parameters.
Example callreturns →
Capture the visible area of a tab as PNG base64 data URL
Takes no parameters.
Example callreturns →
Get a full page snapshot in one call: visual screenshot + interactive elements (inputs, buttons, links with selectors) + headings + URL. Use this instead of separate screenshot + get_page_content calls to save round-trips.
Takes no parameters.
Example callreturns →
List open tabs in the user Chrome profile
Takes no parameters.
Example callreturns →
Get the active tab in the current window
Takes no parameters.
Example callreturns →
Focus a tab by id
Takes no parameters.
Example callreturns →
Close a tab by id
Takes no parameters.
Example callreturns →
Open a new tab with optional URL
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Real Chrome costs nothing to install and nothing to call, 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
BTrust score 87 / 100
Release 0.0.1-security · 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 score100
Client score87
Findings2 threat · 0 capability
Capabilityminimal
Coveragemetadata
Verificationnone
Surface digestda77d9a4b61f3a901b546d0df71c6ec1169625f892ddb5ec94fc8b8147410c72
Score vectorthreat 100 → client 87
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | none | publisher verification (unlocatable) — no provenance and no public repository to inspect | −5 |
| coverage-honesty | metadata | inspection depth (metadata) — how much of the target the scan could see | −8 |
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 sourcenot available
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 digestda77d9a4b61f3a90
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 0.0.1-security — 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.
0.0.1-security
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 Chrome 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.