
MCP server for AgentGo, the browser your AI agent drives: compact page outlines, diff-only replies
MCP server for AgentGo, the browser your AI agent drives: compact page outlines, diff-only replies, real input, human approval. MIT.
·
This is AgentGo's MCP server. The browser lives in the main repo.
⭐ Star AgentGo ·
⬇ Download for Windows 11 ·
Benchmark
The MCP server for AgentGo, the browser your AI agent drives. MIT licensed.
AgentGo is a real Chromium browser for Windows 11, built for agents. This repository is the part your agent talks to: the MCP server, the local control protocol it speaks to the browser, the command registry and the policy types. The browser itself lives in the main repository.
browser_open and browser_read return a short outline: headings plus interactive elements as [ref] role "name".browser_act and browser_batch use real mouse and keyboard input, wait for the page to settle, and reply with the diff, not the whole page again.approval.required; the agent calls browser_wait_human and you approve in the browser.browser_account calls the APIs of accounts you linked, without the agent ever holding a token.browser_act {action: "scroll", until} scrolls a long or virtual list in one call, browser_wait takes named conditions (enabled, gone, text), and any action can say what must happen (expect).browser_delegate hands it routine steps.On 24 BrowserGym MiniWoB++ tasks with the same model, AgentGo solved 22, browser-use 19 and Playwright MCP 18 (method and results). With 0.1.6, on 37 tasks including 14 single-page apps and all four browsers running at the same time: AgentGo with GoMini v6 solved 37, AgentGo 37, browser-use 35 and Playwright MCP 31, with AgentGo using 95-114k input tokens per task against 227-306k (0.1.6 results).
browser_open, browser_read, browser_act, browser_batch, browser_wait, browser_tabs, browser_screenshot, browser_wait_human, browser_guide, browser_account, browser_call, plus browser_delegate when GoMini is on.
Install AgentGo from the latest release. Its installer connects Claude Code, Codex or Droid for you, using agentgo mcp.
Claude Code plugin: the server and the agent guide in one step.
/plugin install agentgo --marketplace Moha2005269/agentgo-mcpClaude Desktop: open agentgo-mcp-0.1.6.mcpb to install it as an extension.
MCP Registry: listed as io.github.Moha2005269/agentgo.
To run this server from source instead:
cargo build --release -p agentgo-mcp --bin agentgo-mcpThen point your MCP client at target/release/agentgo-mcp. It attaches to the newest running AgentGo, or starts agentgo from PATH (set AGENTGO_EXE to use another path).
{ "mcpServers": { "agentgo": { "command": "C:\\path\\to\\agentgo-mcp.exe" } } }agentgo-mcp-offline builds on any OS and answers initialize and tools/list with the real tool list, with no browser behind it. Tool calls explain where to get AgentGo. It exists so MCP directories can check the server; the Dockerfile builds it.
AgentGo is a browser, so the pages your agent opens and the forms it submits go to those websites, as they would from any browser. Nothing goes to us: no telemetry, no accounts, and your profile (history, cookies, saved sign-ins) stays on your computer. Payments and final submissions wait for your approval. See PRIVACY.md and the browser's network calls.
| Crate | What it is |
|---|---|
crates/agentgo-mcp | The stdio MCP server and the protocol client |
crates/agentgo-protocol | Message envelopes, framing, versions, typed errors |
crates/agentgo-shell-bridge | The registry of browser commands |
crates/agentgo-policy | Modes, risk levels, scopes, prompt-injection checks |
skills/agentgo | The agent guide served by browser_guide |
Tests: cargo test --workspace.
This repository mirrors the same crates in the main AgentGo repository, where they are developed.
MIT, see LICENSE. The AgentGo browser itself is under the Business Source License 1.1.
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add agentgo -- C:\path\to\agentgo-mcp.exe{
"mcpServers": {
"agentgo": {
"command": "C:\\path\\to\\agentgo-mcp.exe"
}
}
}code --add-mcp '{"name":"agentgo","command":"C:\\path\\to\\agentgo-mcp.exe"}'[mcp_servers.agentgo]
command = "C:\\path\\to\\agentgo-mcp.exe"Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/agentgo-mcp to learn what the "Agentgo Mcp" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
This server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/agentgo-mcp)Nothing comparable is listed yet.
v0.1.6agentgo-mcp 0.1.6Release notesv0.1.5agentgo-mcp 0.1.5Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "agentgo-mcp" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.