Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
Optics 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.
99/100
trust score
41
tools declared
local
runs on your machine
33
downloads
What it does
Drive Android, iOS, smart TV and web apps from an agent; save the steps as CSV/YAML test suites.
Quickstart
Install it the way its author documents:
1. Download optics-framework-1.11.0.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 9db4696f332c20627ac9e90415e3b17657be114a5f1ea3f366e788cb38a03ba3
The full guide: https://github.com/mozarkai/optics-agent-plugins/releases/download/mcpb-v1.11.0/optics-framework-1.11.0.mcpb
Publishernot claimed
OFAll 1 server
optics-framework1 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 Optics 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.
Install it the way its author documents:
1. Download optics-framework-1.11.0.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 9db4696f332c20627ac9e90415e3b17657be114a5f1ea3f366e788cb38a03ba3
The full guide: https://github.com/mozarkai/optics-agent-plugins/releases/download/mcpb-v1.11.0/optics-framework-1.11.0.mcpb
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.
Start a new optics session and launch the target app.
No parameter schema on file.
Terminate a session and release its driver/resources.
No parameter schema on file.
Capture the current screen and return it as a rendered PNG image.
No parameter schema on file.
Clear text from a specified element.
No parameter schema on file.
Press an element if it appears within `timeout`; otherwise do nothing.
No parameter schema on file.
Enter a specified number into an element.
No parameter schema on file.
Enter text into a specified element.
No parameter schema on file.
Enter text using the keyboard.
No parameter schema on file.
Enter text or press a special key using the keyboard.
No parameter schema on file.
Execute JavaScript/script in the current context.
No parameter schema on file.
Get the text from a specified element.
No parameter schema on file.
Go back one screen: browser history on the web, the back button on a phone.
No parameter schema on file.
Press a specified checkbox element.
No parameter schema on file.
Press a specified element.
No parameter schema on file.
Press a device key by keycode, for system/hardware keys with no on-screen element.
No parameter schema on file.
Press a specified radio button.
No parameter schema on file.
Scroll the current view one step in a direction.
No parameter schema on file.
Perform a scroll action starting from a specified element.
No parameter schema on file.
Scroll in a specified direction until an element appears.
No parameter schema on file.
Open a dropdown and select one of its options, scrolling through the list if needed.
No parameter schema on file.
Sleep for a specified duration.
No parameter schema on file.
Swipe from a point in a specified direction.
No parameter schema on file.
Swipe from a screen position, given in percentages, in a specified direction.
No parameter schema on file.
Perform a swipe action starting from a specified element.
No parameter schema on file.
Swipe a seekbar to the right.
No parameter schema on file.
Swipe in a specified direction until an element appears.
No parameter schema on file.
Tears down the active driver session and flushes all pending events.
No parameter schema on file.
Forcefully terminates the specified application.
No parameter schema on file.
Gets the version of the application.
No parameter schema on file.
Return the current driver session id, if available.
No parameter schema on file.
Sets up the environment for the driver module.
No parameter schema on file.
Launches the specified application.
No parameter schema on file.
Starts another application.
No parameter schema on file.
Starts an Appium session.
No parameter schema on file.
Compares two values for equality.
No parameter schema on file.
Asserts the presence of elements anywhere in the page or DOM, visible or not.
No parameter schema on file.
Asserts that elements are rendered and visible on screen right now, not just present in the page or DOM.
No parameter schema on file.
Retrieves a list of interactive elements on the current screen.
No parameter schema on file.
Checks if the specified element is in a given state (e.g., Enabled/Disabled/Visible/Invisible).
No parameter schema on file.
Verifies the specified element.
No parameter schema on file.
Verifies the specified screen by checking element presence.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Optics 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 99 / 100
Release 1.11.0 · scanned 20 Oct 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 score99
Findings1 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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. 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 digest2dc22d3bf39daa39
Scanned2026-10-20
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
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 1.11.0.
1.11.0
undated
latestNo release note was published with this version.
—
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 Optics 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.