Agent Auth MCP Server

Identity and authentication service for AI agents. Issues verifiable credentials, manages API key lifecycles, and provides OAuth-like flows for

Remote serverstreamable-httpPython

What is the Agent Auth MCP server?

If you already use Agent Auth, the agent auth mcp server is the piece that lets your assistant work with it directly. Identity and authentication service for AI agents. Issues verifiable credentials, manages API key lifecycles, and provides OAuth-like flows for machine-to-machine interactions.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • discover — Returns supported grant types, available scopes, token lifetimes, and all endpoint URLs. Call this first to understand what the service offers
  • quickstart — Register a new root agent and get credentials in one call. The fastest way to get started
  • authenticate — Exchange an API key for an access token (client_credentials grant)
  • refresh_token — Exchange a refresh token for a new access + refresh token pair
  • introspect_token — Check whether a token is valid and inspect its claims (RFC 7662)
  • revoke_token — The token is added to the blocklist and invalidated. Idempotent — revoking an already-revoked token succeeds
  • create_credential — The raw_key is returned once — save it immediately. Subsequent reads only show the key prefix
  • rotate_credential — Revoke an existing API key and issue a replacement in one atomic operation
  • revoke_credential — The revoke_credential tool exposed by this server
  • create_delegation — The delegate can only receive scopes the delegator already holds. Delegations can be chained up to max_chain_depth times
  • check_permission — Dry-run policy evaluation — checks whether an agent is allowed to perform an action without actually enforcing it. Useful for pre-flight checks
  • list_agents — The list_agents tool exposed by this server

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Credentials and setup notes

Configuration is passed through the environment: AGENTAUTH_URL, AGENTAUTH_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agent Auth's toolset — discover, quickstart, authenticate and 10 more — is a fair guide to whether it matches your workflow. It is maintained by raditotev; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agent Auth.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
discoverReturns supported grant types, available scopes, token lifetimes, and all endpoint URLs. Call this first to understand what the service offers.
quickstartRegister a new root agent and get credentials in one call. The fastest way to get started.
authenticateExchange an API key for an access token (client_credentials grant).
refresh_tokenExchange a refresh token for a new access + refresh token pair.
introspect_tokenCheck whether a token is valid and inspect its claims (RFC 7662).
revoke_tokenThe token is added to the blocklist and invalidated. Idempotent — revoking an already-revoked token succeeds.
create_credentialThe raw_key is returned **once** — save it immediately. Subsequent reads only show the key prefix.
rotate_credentialRevoke an existing API key and issue a replacement in one atomic operation.
revoke_credentialThe revoke_credential tool exposed by this server.
create_delegationThe delegate can only receive scopes the delegator already holds. Delegations can be chained up to max_chain_depth times.
check_permissionDry-run policy evaluation — checks whether an agent is allowed to perform an action without actually enforcing it. Useful for pre-flight checks.
list_agentsThe list_agents tool exposed by this server.
get_agentReturns agent fields (id, name, agent_type, trust_level, status) merged with metadata (is_root, is_active).

How to install the Agent Auth MCP server

{
  "mcpServers": {
    "agentauth": {
      "url": "https://agentauth.radi.pro/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
AGENTAUTH_URLEndpoint or connection string the server talks to.Yes
AGENTAUTH_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Agent Auth to discover.
  • Use Agent Auth to quickstart.
  • Use Agent Auth to authenticate.

Frequently asked questions

It connects Agent Auth to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (discover, quickstart, authenticate, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agent Auth directly.