Authdog ships two MCP server SDKs. They solve different problems and are not interchangeable, so pick by what your MCP server needs to enforce.

| | Token verifier SDKs | MCP runtime guard |
|---|---|---|
| Source | [authdog/mcp-sdk](https://github.com/authdog/mcp-sdk) | `packages/mcp-sdk` in the Authdog monorepo |
| Languages | Node.js, Python, Go, Rust, C#, Java, Kotlin, Swift, Dart | TypeScript (Workers or Node) |
| Checks | Is this bearer token valid, and who is the user | Token against JWKS, trust store, per-tool AuthZEN decision, audit telemetry |
| Calls | `GET /v1/userinfo` | JWKS, trust store, AuthZEN, and `POST /v1/mcp/events` |
| Availability | Source-available; registry publication unconfirmed | Private; install from source |

## Token verifier SDKs

An MCP client obtains an Authdog access token, for example through [MCP authentication](/docs/mcp-authentication), and sends it as a bearer token. `AuthdogVerifier` calls the environment's `GET /v1/userinfo` with that token and returns an `AuthInfo`:

- `subject`, `username`, and `email` for the authenticated user
- `expiresAt`, derived from the remaining session lifetime
- `scopes`, currently always empty because userinfo does not return scopes yet
- `token` and the full `user` object

A `401` from Authdog raises an authentication error your transport should turn into an HTTP 401. Any other failure raises a separate API error, so you can tell a rejected token from an unreachable Authdog.

Pick your language:

| Language | Guide | Package |
|----------|-------|---------|
| Node.js / TypeScript | [Node.js](/docs/mcp-sdk/node) | `@authdog/mcp-sdk` |
| Python | [Python](/docs/mcp-sdk/python) | `authdog-mcp` |
| Go | [Go](/docs/mcp-sdk/go) | `github.com/authdog/mcp-sdk/go` |
| Rust | [Rust](/docs/mcp-sdk/rust) | `authdog-mcp` |
| C# | [C#](/docs/mcp-sdk/csharp) | `Authdog.Mcp.Sdk` |
| Java | [Java](/docs/mcp-sdk/java) | `com.authdog:authdog-mcp-sdk` |
| Kotlin | [Kotlin](/docs/mcp-sdk/kotlin) | `com.authdog:authdog-mcp-sdk` |
| Swift | [Swift](/docs/mcp-sdk/swift) | `AuthdogMCP` |
| Dart | [Dart](/docs/mcp-sdk/dart) | `authdog_mcp` |

> **Note**
>
> These packages are source-available in [authdog/mcp-sdk](https://github.com/authdog/mcp-sdk). Registry publication is not confirmed: `@authdog/mcp-sdk` returns 404 on npm. Each guide has a from-source install.

## MCP runtime guard

The TypeScript runtime SDK runs inside your MCP worker and layers four independent controls over each tool call. Adopt them one at a time:

1. **Authenticate**: verify the caller's access token against your environment's JWKS, with RFC 9728 protected-resource metadata.
2. **Trust store**: require the calling identity to be a verified non-human identity within its allowed scopes.
3. **Authorize**: ask the AuthZEN decision point whether this identity may invoke this specific tool.
4. **Telemetry**: emit invoked, denied, and failed events for [audit and SIEM](/docs/mcp-authentication).

Trust store and authorization default to non-breaking modes (`off` and `monitor`). Move each to `enforce` after you have watched the decisions in the console. The package is private today, so install it from a clone of the monorepo.

```ts
import {
  authenticateRequest,
  checkTrustStore,
  createAuthdogTelemetry,
  withAuthdogToolGuard,
} from "@authdog/mcp-sdk"

const auth = await authenticateRequest(request, env)
if (!auth.ok) return new Response(auth.message, { status: auth.status })

const trust = await checkTrustStore(auth.claims, env)
if (!trust.ok) return new Response(trust.message, { status: trust.status })

const telemetry = createAuthdogTelemetry(env)
const readFile = withAuthdogToolGuard("my-server", "read_file", env, handler, {
  telemetry,
})
```

Configure it with these variables on your worker:

| Variable | Purpose |
|----------|---------|
| `AUTHDOG_OIDC_ISSUER` | Environment OIDC issuer; JWKS is derived from it |
| `AUTHDOG_OIDC_AUDIENCE` | Audience your tokens are minted for (your MCP server URL) |
| `MCP_REQUIRED_SCOPES` | Space-separated scopes required on every call |
| `AUTHDOG_API_BASE_URL` | Public API base, used by trust store, authorize, and telemetry |
| `AUTHDOG_ENV_API_SECRET` | Environment API secret (`adenv_...`) |
| `MCP_TRUST_STORE_MODE` | `off` (default), `monitor`, or `enforce` |
| `MCP_AUTHZ_MODE` | `off`, `monitor` (default), or `enforce` |
| `MCP_TELEMETRY` | `true` to emit tool-call events |

`AUTHDOG_DEV_MODE=true` allows `http://localhost` issuers for local development. Never set it in production.

To detect a server changing its tools after registration, report a tool manifest hash with `computeToolManifestHash` and pin it on the trust-store entry.

## Related

- [MCP authentication](/docs/mcp-authentication)
- [MCP OAuth vs platform](/docs/mcp-oauth-vs-platform)
- [Console MCP module](/docs/console/mcp)
- [Machine identity](/docs/machine-identity)