AgentAuth runs on your own machine — the client starts it, so there is no endpoint to ping. 148 installs a week from pypi.
Identity and auth for AI agents: credentials, tokens, delegations, and permission checks.
The linked repository no longer exists on GitHub — it was deleted or made private.
This one has been quiet for a while
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agent-auth -e 'AGENTAUTH_URL=<AGENTAUTH_URL>' -- uvx agentauth-mcp-server{
"mcpServers": {
"agent-auth": {
"command": "uvx",
"args": [
"agentauth-mcp-server"
],
"env": {
"AGENTAUTH_URL": "<AGENTAUTH_URL>"
}
}
}
}[mcp_servers.agent-auth]
command = "uvx"
args = ["agentauth-mcp-server"]
env = { AGENTAUTH_URL = "<AGENTAUTH_URL>" }{
"mcpServers": {
"agent-auth": {
"command": "uvx",
"args": [
"agentauth-mcp-server"
],
"env": {
"AGENTAUTH_URL": "<AGENTAUTH_URL>"
}
}
}
}{
"servers": {
"agent-auth": {
"type": "stdio",
"command": "uvx",
"args": [
"agentauth-mcp-server"
],
"env": {
"AGENTAUTH_URL": "<AGENTAUTH_URL>"
}
}
}
}Put your own value in place of
<AGENTAUTH_URL> (Base URL of the AgentAuth service (e.g. https://agentauth.radi.pro or http://localhost:8000 for self-hosted)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
AGENTAUTH_API_KEY (Default API key for the authenticate tool. Optional — can also be passed per call).
Alternatives to AgentAuth
same job, measured the same wayOAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.
Read-only checks for DIDs, credentials, MCP servers, A2A cards and agent delegation.
Persistent identity, email, saved accounts and scoped credentials for AI agents.
ERC-7303 token-controlled roles for AI agents: grant, check, and revoke permissions on-chain
AI agent identity, signed credentials, delegated authority and governance evidence.
AI agents get on-chain identity, credentials, reputation, escrow, and persistent memory on XRPL.
Open Identity Standard for AI Agents — DID, Agent Cards, delegation, reputation, payment & escrow
Sanctions screening and PEP checks via OpenSanctions API for AI agents
AgentAuth — questions
Answers built from our own checks of this server.