mcpField
A
Auth Your Agent

Auth Your Agent

Local
authyouragent.comBrowser Automation

About Auth Your Agent

Auth Your Agent is an open-source MCP server that lets agents operate websites through a sandboxed browser on the owner's machine, with phone-based approval and takeover. It keeps passwords and cookies from the agent and signs out sites before destroying the browser profile.

Key features

  1. 01Drive a sandboxed browser
  2. 02Request phone approval for actions
  3. 03Hand off sign-in to the owner
  4. 04Fill saved credentials without revealing them
  5. 05Sign out and destroy browser profile

Use cases

  1. 01Complete website tasks requiring owner sign-in
  2. 02Require approval before submitting sensitive actions
  3. 03Run pre-approved steps in scheduled tasks

MCP support

It exposes browser control, credential filling, approval, takeover, and scheduled-plan tools to MCP clients. The server operates a separate browser vault and disconnects the agent while the owner takes control.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"com-authyouragent": {
"command": "uvx",
"args": [
"authyouragent"
],
"env": {
"AYA_AGENT_ID": "<AYA_AGENT_ID>",
"AYA_KEY_FILE": "<AYA_KEY_FILE>",
"AYA_VAULT_URL": "<AYA_VAULT_URL>",
"AYA_VAULT_TOKEN_FILE": "<AYA_VAULT_TOKEN_FILE>"
}
}
}
}
Run commanduvx authyouragent
Environment variables to set
AYA_AGENT_IDYour agent's id (ag_...), from Agents in the Auth Your Agent app
AYA_KEY_FILESecretPath to the agent's private key (PEM), created with: authyouragent keygen
AYA_VAULT_URLBrowser vault address
AYA_VAULT_TOKEN_FILESecretPath to the vault's token file

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiauthyouragent0.3.42

Tools

23

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
urlstringYes

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

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.