Server data from the Official MCP Registry
Act for a person on websites: sandboxed browser, phone approvals, take over at sign-in walls.
About
Act for a person on websites: sandboxed browser, phone approvals, take over at sign-in walls.
Security Report
Auth Your Agent is a well-architected MCP server for delegated browser automation with strong security controls. The codebase demonstrates thoughtful permission scoping, secure credential handling, and proper use of sandboxing. However, there are moderate concerns around Web Bot Auth key management, token storage practices, and some areas where input validation could be more robust. These issues are not critical given the system's architecture, but warrant attention. Supply chain analysis found 10 known vulnerabilities in dependencies (0 critical, 5 high severity). Package verification found 1 issue.
4 files analyzed · 19 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
What You'll Need
Set these up before or after installing:
Environment variable: AYA_AGENT_ID
Environment variable: AYA_KEY_FILE
Environment variable: AYA_VAULT_URL
Environment variable: AYA_VAULT_TOKEN_FILE
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"com-authyouragent-mcp": {
"env": {
"AYA_AGENT_ID": "your-aya-agent-id-here",
"AYA_KEY_FILE": "your-aya-key-file-here",
"AYA_VAULT_URL": "your-aya-vault-url-here",
"AYA_VAULT_TOKEN_FILE": "your-aya-vault-token-file-here"
},
"args": [
"-y",
"authyouragent"
],
"command": "npx"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
Auth Your Agent
An open-source MCP server that lets an AI agent act for a person on websites, with the person's approval on their phone.
The agent drives a sandboxed browser (the vault) that runs on the person's own machine. When a site asks for a password, a CAPTCHA or a 2FA code, the person takes over that browser from their phone, signs in, and hands it back. The agent never sees the password and never holds the cookies. When the task is done, the vault signs out of every site it used, then destroys the browser profile.
Website: authyouragent.com · License: MIT
What is in this repository
The MCP server, the browser vault and the SDKs:
| Path | What it is |
|---|---|
sdk/authyouragent/mcp_server.py | The MCP server (stdio, 20 tools). Entry point authyouragent-mcp. |
vault/ | The browser vault: broker.py (HTTP API the MCP server calls; drives Chromium, detects sign-in, signs out), egress.py (public-internet-only proxy), screen.py (phone screen stream), seccomp.json, chromium-policy.json, Dockerfile. Details: vault/README.md. |
sdk/authyouragent/vault_cli.py | authyouragent vault up/down/status/env: runs the vault with every protection on. |
sdk/authyouragent/ | Python SDK: agent side (agent.py), website side (site.py), take-over helper for your own Playwright browser (takeover.py). |
sdk-js/ | JavaScript SDK, and npm-wrapper/ so Node clients can start the MCP server with npx authyouragent-mcp. |
Dockerfile | Container for the MCP server alone. |
The phone app and the approval service run at authyouragent.com. The agent signs its requests with its own key pair; the service never receives the person's passwords.
MCP tools
| Tool | What it does |
|---|---|
navigate, click, type_text, read_page | Drive the vault's browser. Only public websites open. Clicks that submit a form, or whose button says create, send, save, delete, pay and the like, ask the owner's phone first. |
list_secrets, fill_secret | Fill a username, password or authenticator code from the owner's Bitwarden or Vaultwarden into the page. The agent never sees the value; it fills only on the item's own site and only the right kind of field. |
check_login_wall | Is the page blocked by a password, CAPTCHA, one-time code or sign-in approval? Reads the page's fields and text, so the model needs no vision. |
request_takeover | Ask the owner to take over the browser from their phone. Returns done, cancelled, expired, incomplete, or waiting. |
wait_for_takeover | Keep waiting after waiting. |
request_approval | Ask the owner to approve an action. approved, denied or expired. |
notify_owner | A one-way note to the owner's phone: done, stuck, or what failed. Nothing to approve. |
end_session | Sign out of every site used, then destroy the browser profile. Reports per site whether sign-out was confirmed. The vault then sends the owner its own summary of the session. |
check_agent_status | active or revoked. |
report_site | Report a site where take over did not work. |
Run it
From PyPI:
pip install "authyouragent[mcp]"
authyouragent vault up --agent-id ag_... --key /path/to/agent-key.pem
From this repository:
git clone https://github.com/kjames2001/authyouragent && cd authyouragent
pip install "./sdk[mcp]"
docker build -f vault/Dockerfile -t authyouragent/vault:local .
authyouragent vault up --agent-id ag_... --key /path/to/agent-key.pem --image authyouragent/vault:local --no-pull
The vault needs Docker. vault up prints the MCP settings to add to your client. (If you skip vault up, the MCP server starts the vault itself the first time the agent needs the browser; AYA_VAULT_AUTOSTART=0 turns that off.)
{
"mcpServers": {
"authyouragent": {
"command": "authyouragent-mcp",
"env": {
"AYA_AGENT_ID": "ag_...",
"AYA_KEY_FILE": "/path/to/agent-key.pem",
"AYA_VAULT_URL": "http://127.0.0.1:7801",
"AYA_VAULT_TOKEN_FILE": "~/.authyouragent/vault/token"
}
}
}
}
Node clients can use npx authyouragent-mcp as the command. The agent ID and key come from adding the agent in the phone app (Agents > Add an agent). Without them the server still starts and lists its tools; each tool then says what is missing.
Security
- Chromium's own sandbox is on (custom seccomp profile, all container capabilities dropped); gVisor is used automatically when Docker has the
runscruntime. - The browser can reach only the public internet: loopback, private networks, cloud metadata addresses and the vault's own ports are refused, checked on the resolved address.
- The agent is disconnected while the owner is in control, and cannot read the browser's cookies.
- Sign out first, wipe second: at the end of a session, when the agent stops sending heartbeats, or when it is revoked. Sites the vault could not sign out of are reported to the owner, also after a crash.
Known limits are listed in vault/README.md.
Scope: what Auth Your Agent does, and does not do
Auth Your Agent answers one question for a website: who is acting, for whom, with what permission, and can it be withdrawn. A feature belongs here if it grants, limits, proves or withdraws an agent's authority on a site. That covers approvals, sign-in for agents, step-ups in the site's own words, take over at a sign-in wall, signing out, and the vault's own record of what was done with the owner's authority.
It does not do:
- Conversation with the agent. No multiple-choice or free-text questions, chat or task updates beyond a short note. A card from Auth Your Agent is always about permission, so the owner never learns to tap through it like a chat prompt. Use a tool built for talking to agents (for example Paseo) alongside it.
- Running or orchestrating agents. It works with whichever agent you use; it does not start, schedule or supervise them.
- Judging intent with AI. Approval rules are fixed rules the owner can read. No model decides what is safe.
- Getting past sites' defences. No CAPTCHA solving or bot-detection evasion; the owner takes over instead.
- Turning websites into tools. Learning a site's API calls as MCP tools is a separate project built on top of the vault.
New features are checked against this list first.
Documentation
- For AI agents
- Take over developer guide
- Developer quickstart
- How it works
- Changelog: what each release added or fixed
Android app
Download from authyouragent.com/download/android.
License
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Fetch
Freeby Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
Worldmonitor
Freeby Koala73 · Developer Tools
Live markets, conflicts, country risk, chokepoints, energy, and China decision signals. 86 tools.
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
