Files
Flash5/flash-extensions/flash-ext-mcp/docs/security.md
T

48 lines
2.5 KiB
Markdown

# Security
The MCP endpoint is secured by [`flash-ext-security-core`](../../flash-ext-security-core/docs/README.md):
whatever mechanisms the application registers — OAuth2 bearer tokens, API keys, custom ones —
authenticate `/mcp` exactly as they authenticate every other route.
| `McpConfig.security(...)` | |
|---|---|
| `REQUIRED` (default) | every call must be authenticated; boot fails without a `SecurityExtension` |
| `NONE` | a public endpoint; a tool carrying security annotations fails the boot |
## OAuth2 protected resource
When a registered mechanism publishes an OAuth2 issuer — `flash-ext-security-oidc` does — the endpoint
behaves as the MCP authorization spec requires, with nothing to configure:
- `GET /.well-known/oauth-protected-resource/mcp` serves RFC 9728 metadata: the `resource` (derived per
request from `X-Forwarded-Proto`/`-Host` or `Host`), every issuer as `authorization_servers`, and
`scopes_supported` when `McpConfig.scopesSupported(...)` is set;
- an anonymous call gets `401` with `WWW-Authenticate: Bearer resource_metadata="…"`;
- a token whose `aud` does not include the resource is `403` (RFC 8707) and logged at `WARN`. Credentials
that are not audience-bound, such as API keys, are unaffected.
For Keycloak, the audience comes from an *Audience* protocol mapper whose included custom audience is
the resource URL, attached to a client scope every MCP client receives (the built-in `basic` scope is the
one that needs no client cooperation). Clients that register dynamically need Keycloak's anonymous
client registration policies relaxed for the trusted hosts.
`McpConfig.requireTokenAudience(false)` drops that last check for an authorization server that cannot
mint a resource audience at all — Keycloak ignores RFC 8707's `resource` parameter, so a deployment that
cannot add the mapper has no other way in. Every token a registered issuer signs is then accepted on the
endpoint, and the boot logs say so.
## Tool policies
The core annotations work on tools as on handlers, checked per `tools/call` against the caller the route
authenticated:
```java
@Tool(name = "approve", description = "Approves a pending proposal")
@RolesAllowed(value = "REVIEWER", on = {"project", "locale"}) // read from the tool's arguments
public class ApproveTool extends McpTool { }
```
A denial is a tool result with `isError: true` — the call reached the server, the tool did not run.
`McpConfig.middleware(...)` runs after authentication, for rate limiting, auditing or tracing.