Manage identity, credentials, and permissions for AI agents through a centralized auth service. Developers can verify tokens, check delegations, and enforce permission policies without building auth infrastructure from scratch.
io.github.raditotev/agent-auth
Local install
STDIO
1 required env var
How models use it and what it is built for.
Manage identity, credentials, and permissions for AI agents through a centralized auth service. Developers can verify tokens, check delegations, and enforce permission policies without building auth infrastructure from scratch.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Base URL of the AgentAuth service (e.g. https://agentauth.radi.pro or http://localhost:8000 for self-hosted)
Default API key for the authenticate tool. Optional — can also be passed per call.
Where to find authoritative docs and source for AgentAuth.
Paste any of these into Agent Studio after connecting AgentAuth.
Common questions about connecting and running AgentAuth.
What is AgentAuth MCP and what does it do?
AgentAuth MCP is a Model Context Protocol server that provides identity and authorization services for AI agents. It handles credential verification, token validation, delegation chains, and permission checks through a centralized service.
How do I set up AgentAuth MCP?
Install via `uvx agentauth-mcp-server@0.1.1`, then set the required `AGENTAUTH_URL` environment variable to your AgentAuth service endpoint (e.g., https://agentauth.radi.pro or http://localhost:8000). Optionally set `AGENTAUTH_API_KEY` for default authentication.
Can I use AgentAuth MCP without an API key?
The `AGENTAUTH_API_KEY` environment variable is optional—you can pass credentials per call instead. However, setting a default key simplifies configuration if your agents share the same authentication context.
Does AgentAuth MCP support self-hosted deployment?
Yes. Set `AGENTAUTH_URL` to your self-hosted instance (e.g., http://localhost:8000) instead of the public service. This allows you to run auth infrastructure on your own infrastructure.
What permission models does AgentAuth MCP support?
The server supports credential verification, token validation, delegation chains, and permission checks. Refer to your AgentAuth service documentation for specific policy engines and permission models available.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams