About AgentGo
AgentGo's MCP server connects AI agents to its real Chromium browser on Windows 11. It returns compact page outlines and change-only results, while requiring human approval for payments and final submissions.
Key features
- 01Compact page outlines
- 02Diff-only action replies
- 03Real mouse and keyboard input
- 04Human approval for submissions
- 05Linked account API access
- 06Single-page app controls
Use cases
- 01Navigate pages with an AI agent
- 02Automate browser actions while reviewing changes
- 03Require approval before payments or final submissions
- 04Operate long or virtualized lists
MCP support
The MCP server exposes browser controls such as opening and reading pages, acting, waiting, taking screenshots, and requesting human approval. It attaches to a running AgentGo browser or starts one from PATH.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README
This is AgentGo's MCP server. The browser lives in the main repo.
⭐ Star AgentGo ·
⬇ Download for Windows 11 ·
Benchmark
agentgo-mcp
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.
- Compact pages.
browser_openandbrowser_readreturn a short outline: headings plus interactive elements as[ref] role "name". - Only what changed.
browser_actandbrowser_batchuse real mouse and keyboard input, wait for the page to settle, and reply with the diff, not the whole page again. - The human stays in charge. Payments and final submissions come back as
approval.required; the agent callsbrowser_wait_humanand you approve in the browser. - Accounts without tokens.
browser_accountcalls the APIs of accounts you linked, without the agent ever holding a token. - Built for single-page apps. Repeated buttons say which row they belong to, a reference that a re-render moved to another item heals or fails loudly instead of clicking the wrong row,
browser_act {action: "scroll", until}scrolls a long or virtual list in one call,browser_waittakes named conditions (enabled,gone,text), and any action can say what must happen (expect). - GoMini. When the on-device model is on,
browser_delegatehands 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).
Tools
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.
Use it
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-mcp
Claude 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-mcp
Then 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" } } }
Offline mode
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.
Data
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.
Layout
| 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.
License
MIT, see LICENSE. The AgentGo browser itself is under the Business Source License 1.1.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.