Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
AgentGo 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.
91/100
trust score
12
tools declared
local
runs on your machine
35
downloads
What it does
Real Chromium browser for AI agents: compact outlines, diff-only replies, real input, you approve.
Quickstart
Install it the way its author documents:
1. Download agentgo-mcp-0.1.5.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 8868bc26e8519b414b29e346eef0fb01e1b3e054b60311e74a6b2a295c537f63
The full guide: https://github.com/Moha2005269/agentgo-mcp/releases/download/v0.1.5/agentgo-mcp-0.1.5.mcpb
Publishernot claimed
MOAll 2 servers
Moha20052692 servers
2 categories
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 AgentGo 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 agentgo-mcp-0.1.5.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 8868bc26e8519b414b29e346eef0fb01e1b3e054b60311e74a6b2a295c537f63
The full guide: https://github.com/Moha2005269/agentgo-mcp/releases/download/v0.1.5/agentgo-mcp-0.1.5.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.
GoMini, the local model, is on: hand it a routine run of steps and it takes them itself (fill the values you supply, click, check, select, scroll, wait, retry) without you reading every page: opening tabs, folders or sections until something shows, a set of boxes, a long form. Not worth it for one…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| subgoal | string | yes | — |
| values | object | no | — |
| completion | string | no | — |
| constraints | array | no | — |
| maxSteps | integer | no | 1-12, default 8 |
| tabId | string | no | — |
Go to a URL (or search Google with plain words), wait for the load, and return the page as a compact outline: headings plus interactive elements as [ref] role "name". Use the refs with browser_act.
No parameter schema on file.
Read the current page. view: page (outline with refs, default), text (readable content, text boxes and code included), links, forms, tables, meta. filter keeps matching lines; offset and max count lines.
No parameter schema on file.
Act on an element by ref with real input, wait for the page to settle, and get back only what changed. action: click, fill (text), press (key), check, uncheck, select (value, or values for a multiple list), hover, scroll (to: top|bottom, or ref; until: a text to scroll to, in the page or ref's…
No parameter schema on file.
Run several browser_act steps in order in one call (e.g. fill a whole form and click Save; {action:"wait", ms} pauses). Stops at the first failure. Returns the final change set.
No parameter schema on file.
Wait until text appears, a selector is visible, a selector or text is gone, the URL contains a string, or ref enabled is usable; returns what changed. ms: just pause. No condition: waits for load.
No parameter schema on file.
Manage your tabs. op: list, new (url), switch (tabId), close (tabId), back, forward, reload.
No parameter schema on file.
Screenshot the page (or one element by ref) and return the image. Costs many tokens: prefer browser_read unless you need to see layout, images or a canvas.
No parameter schema on file.
Wait for the human operator: pass approvalId after approval.required, or nothing after handoff.required (CAPTCHA, login). Never try to solve a CAPTCHA yourself.
No parameter schema on file.
How to use this browser, when you are unsure. topic=start: the loop, rules that save turns, errors (short). topic=skill: the full guide. topic=commands: find commands: pass query (words, e.g. "selector click") for the matching ones, or group for one section (open, read, act, batch, accounts,…
No parameter schema on file.
Use the accounts the person linked for you in the Account Center. op=accounts lists them (linked or not); op=apis lists the APIs you can call; op=call sends one API request as the account (connector, method, path, body) without you ever holding a token; op=sign_in has the browser type the saved…
No parameter schema on file.
Call any other AgentGo protocol method directly (cookies, downloads, PDF, dialogs, network log, workflow.collect ...). browser_call {method:"browser.capabilities"} lists them.
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 AgentGo 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 91 / 100
Release 0.1.5 · scanned 28 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 score91
Findings1 threat · 0 capability
Capabilityminimal
Coveragemetadata
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 91
| 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 | 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>".
The implementation source was not read — the published package was fetched but contains no source files the scanner reads.
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
Scanned2026-10-28
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 0.1.5.
0.1.5
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 AgentGo 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.