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
Chromedebug 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
ChromeDebug MCP - MCP server that provides full control over a Chrome browser instance for debugging and automation with AI assistants like Claude Code
Quickstart
# 1 — run it from where its publisher ships it
npx -y @dynamicu/chromedebug-mcp
# 2 — ask your agent something
> ChromeDebug MCP - MCP server that provides full control over a Chrome browser instance for debugging and automation with AI assistants like
Chromedebug is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
DYAll 1 server
@dynamicu1 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 Chromedebug 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 chromedebug-mcp -- npx -y @dynamicu/chromedebug-mcpReconnect, 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
37 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.
Launch a Chrome browser instance for this MCP server
Takes no parameters.
Example callreturns →
Connect to an existing Chrome instance with debugging enabled
Takes no parameters.
Example callreturns →
Navigate to a URL
Takes no parameters.
Example callreturns →
Pause Chrome execution
Takes no parameters.
Example callreturns →
Resume Chrome execution
Takes no parameters.
Example callreturns →
Step over in Chrome debugger
Takes no parameters.
Example callreturns →
Evaluate a JavaScript expression in Chrome
Takes no parameters.
Example callreturns →
Get scope variables from the top call frame
Takes no parameters.
Example callreturns →
Set a breakpoint at a specific URL and line
Takes no parameters.
Example callreturns →
Get recent console logs
Takes no parameters.
Example callreturns →
Check if Chrome is connected
Takes no parameters.
Example callreturns →
Force reset Chrome by killing all processes and clearing state
Takes no parameters.
Example callreturns →
Take a screenshot optimized for AI processing
Takes no parameters.
Example callreturns →
Get the content of the current page including text, HTML, and DOM structure. Useful for checking if specific content exists without taking a screenshot.
Takes no parameters.
Example callreturns →
Get information about the currently selected element from Chrome extension
Takes no parameters.
Example callreturns →
Apply CSS styles to the currently selected element
Takes no parameters.
Example callreturns →
Execute JavaScript code on the currently selected element
Takes no parameters.
Example callreturns →
Clear the currently selected element
Takes no parameters.
Example callreturns →
Get WebSocket server information for Chrome extension
Takes no parameters.
Example callreturns →
Get a complete workflow recording including actions and optional logs
Takes no parameters.
Example callreturns →
List all workflow recordings stored in the database
Takes no parameters.
Example callreturns →
Get only function execution traces from a workflow recording
Takes no parameters.
Example callreturns →
Get only error logs and error-related actions from a workflow
Takes no parameters.
Example callreturns →
Get a concise summary of a workflow recording
Takes no parameters.
Example callreturns →
Get filtered workflow actions by type or time range
Takes no parameters.
Example callreturns →
Save a restore point for the current browser state including DOM, form values, storage, and cookies
Takes no parameters.
Example callreturns →
Restore the browser to a previously saved restore point
Takes no parameters.
Example callreturns →
List all restore points for a workflow
Takes no parameters.
Example callreturns →
Display frame recording information in a compact format optimized for MCP tools. Shows frame metadata, console logs, and timestamps without including large image data.
Takes no parameters.
Example callreturns →
Get information about a frame capture session including total frames and timestamps
Takes no parameters.
Example callreturns →
Get all user interactions (clicks, inputs, keypresses, scrolls) recorded during a screen recording session
Takes no parameters.
Example callreturns →
Get a specific frame from a frame capture session
Takes no parameters.
Example callreturns →
Search for specific logs across all frames in a recording session
Takes no parameters.
Example callreturns →
Get logs for a specific frame with pagination to handle large log volumes
Takes no parameters.
Example callreturns →
Get the screenshot image data for a specific frame as base64 encoded string. This allows viewing of the actual screenshots captured during frame recordings.
Takes no parameters.
Example callreturns →
Play a workflow recording by executing all recorded actions
Takes no parameters.
Example callreturns →
Play a workflow recording by its name
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. Chromedebug 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
CTrust score 79 / 100
Release 2.7.7 · 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 score87
Client score79
Findings8 threat · 10 capability
Capabilityhigh
Coveragesource
Verificationnone
Surface digest099bd325d8e5d18bfc6a99575cd53070d94e0ac73b540748acb6f26c9fb8facb
Score vectorthreat 87 → client 79
| Term | Level | What it prices | Points |
|---|---|---|---|
| −1.2 | |||
| −0.6 | |||
| −0.3 | |||
| −0.12 | |||
| −6.3 | |||
| −3.15 | |||
| −1.2 | |||
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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. 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 digest099bd325d8e5d18b
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 2.7.7 — 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.
2.7.7
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 Chromedebug 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.