fix(mcp): open MCP OAuth in same browser as gateway (#951)

* fix(mcp): use gateway callback for MCP OAuth so auth opens in same browser

When MCP OAuth is triggered from the web gateway, the auth URL was being
opened via `open::that()` which launches the OS default browser instead
of the browser already running the gateway UI. This changes the MCP OAuth
flow to use the same gateway callback pattern as WASM extensions: in
gateway mode, the auth URL is returned to the frontend via SSE and opened
with `window.open()`, keeping the user in the same browser.

Also adds RFC 8707 `resource` parameter support to the gateway token
exchange path, scoping issued tokens to the correct MCP server.

Closes #299

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* style: cargo fmt

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(mcp): persist DCR client_id in gateway OAuth callback for token refresh

The gateway callback handler stored access and refresh tokens but not
the DCR client_id. When the token expired, refresh failed with "No
client ID found" because get_client_id() could not find it in secrets.

Adds client_id_secret_name to PendingOAuthFlow so the gateway callback
handler persists the client_id alongside the tokens, matching the
behavior of the CLI flow in authorize_mcp_server().

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(mcp): return AuthRequired on 401 so activate triggers OAuth flow

activate_mcp() returned ActivationFailed for all errors including 401
auth responses, so the activate handler never triggered the OAuth flow.
Now 401/auth errors return AuthRequired, which the handler detects and
redirects to the OAuth flow — matching the WASM extension pattern.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix(mcp): fix gateway OAuth flow, approval cards, and auto-activation

- Add explicit gateway_mode flag on ExtensionManager (set at startup by
  web gateway) so MCP OAuth returns auth URLs to the frontend instead of
  calling open::that() on the server machine.
- Auto-activate extensions after successful OAuth callback so the UI
  transitions from "Activate" to "Active" without a second click.
- Send ApprovalNeeded status (not generic "Awaiting approval") from
  thread_ops.rs for all three NeedApproval paths so the web UI shows
  approval cards for deferred tool calls.
- Remove duplicate ApprovalNeeded send from agent_loop.rs (thread_ops.rs
  is now the canonical sender).
- Skip approval for tool_auth in gateway mode since it only returns a URL.
- Revert fragile active-server detection heuristic from system prompt.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address PR review findings

- Use Release/Acquire ordering for gateway_mode AtomicBool instead of
  Relaxed to ensure visibility across threads.
- Report activation failure as error in OAuth callback SSE event instead
  of silently falling back to the success message.
- Fix EnvGuard::drop to remove env var when original was unset.
- Replace hardcoded /tmp/ path with std::env::temp_dir() in test helper.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* test(mcp): add E2E trace test for MCP extension lifecycle with mock server

Add a full MCP extension lifecycle E2E test that exercises:
- Turn 1: tool_search → tool_install → text (extension discovery and install)
- Token injection + activate (simulating OAuth completion)
- Turn 2: MCP tool calls (notion-search → notion-fetch → text)

Includes a mock MCP server (tests/support/mock_mcp_server.rs) with OAuth
discovery, DCR, token exchange, and JSON-RPC endpoints. The mock server
validates Bearer auth and serves pre-configured tool responses.

Also adds inject_registry_entry() to ExtensionManager for test use and
exposes extension_manager from TestRig.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address PR review findings (round 2)

- Only fall back to manual token entry on AuthNotSupported, propagate
  real errors from auth_mcp_build_url() instead of masking them
- Use mcp:-prefixed provider string in PendingOAuthFlow for consistency
  with CLI MCP auth token storage
- Only persist client_id_secret_name for DCR flows (not pre-configured OAuth)
- Fix gateway_callback_redirect_uri to use /oauth/callback path
- Bypass exchange proxy when flow has RFC 8707 resource parameter
- Remove client_id double-prefix in oauth callback handler
- Remove weak tests that didn't exercise production logic
- Add clarifying comments for exchange_oauth_code delegation

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: keep OAuth success independent of activation, fix wait_for_responses scoping

- OAuth success is now reported accurately even when auto-activation
  fails (tokens are already stored, so auth succeeded)
- E2E test waits for turn1_count + 1 responses to ensure turn-2
  behavior is actually observed

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Illia Polosukhin
2026-03-12 11:16:23 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 0b81342b5c
commit 8a26cfae73
14 changed files with 1241 additions and 92 deletions
+52 -3
View File
@@ -581,7 +581,12 @@ async fn oauth_callback_handler(
let exchange_proxy_url = std::env::var("IRONCLAW_OAUTH_EXCHANGE_URL").ok();
let result: Result<(), String> = async {
let token_response = if let Some(ref proxy_url) = exchange_proxy_url {
let token_response = if let (Some(proxy_url), None) = (&exchange_proxy_url, &flow.resource)
{
// Use the platform exchange proxy when configured and no resource
// parameter is needed. The proxy holds client_secret server-side so
// the container never sees it. MCP flows (resource.is_some()) bypass
// the proxy because it doesn't forward the RFC 8707 resource param.
let gateway_token = flow.gateway_token.as_deref().unwrap_or_default();
oauth_defaults::exchange_via_proxy(
proxy_url,
@@ -594,7 +599,10 @@ async fn oauth_callback_handler(
.await
.map_err(|e| e.to_string())?
} else {
oauth_defaults::exchange_oauth_code(
// Direct token exchange: uses exchange_oauth_code_with_resource so MCP
// flows can include the RFC 8707 `resource` parameter to scope the
// issued token to the specific MCP server.
oauth_defaults::exchange_oauth_code_with_resource(
&flow.token_url,
&flow.client_id,
flow.client_secret.as_deref(),
@@ -602,6 +610,7 @@ async fn oauth_callback_handler(
&flow.redirect_uri,
flow.code_verifier.as_deref(),
&flow.access_token_field,
flow.resource.as_deref(),
)
.await
.map_err(|e| e.to_string())?
@@ -628,6 +637,19 @@ async fn oauth_callback_handler(
.await
.map_err(|e| e.to_string())?;
// For MCP OAuth flows (identified by resource field), persist the
// client_id so token refresh works without re-authentication.
// The CLI flow stores this in authorize_mcp_server(); the gateway
// callback must do the same.
if let Some(ref client_id_secret) = flow.client_id_secret_name {
let params = crate::secrets::CreateSecretParams::new(client_id_secret, &flow.client_id)
.with_provider(flow.provider.as_ref().cloned().unwrap_or_default());
flow.secrets
.create(&flow.user_id, params)
.await
.map_err(|e| e.to_string())?;
}
Ok(())
}
.await;
@@ -659,12 +681,35 @@ async fn oauth_callback_handler(
}
}
// After successful OAuth, auto-activate the extension so it moves
// from "Installed (Authenticate)" → "Active" without a second click.
// OAuth success is independent of activation — tokens are already stored.
// Report auth as successful and attempt activation as a bonus step.
let final_message = if success {
match ext_mgr.activate(&flow.extension_name).await {
Ok(result) => result.message,
Err(e) => {
tracing::warn!(
extension = %flow.extension_name,
error = %e,
"Auto-activation after OAuth failed"
);
format!(
"{} authenticated successfully. Activation failed: {}. Try activating manually.",
flow.display_name, e
)
}
}
} else {
message
};
// Broadcast SSE event to notify the web UI
if let Some(ref sender) = flow.sse_sender {
let _ = sender.send(SseEvent::AuthCompleted {
extension_name: flow.extension_name,
success,
message,
message: final_message.clone(),
});
}
@@ -2966,6 +3011,8 @@ mod tests {
secrets,
sse_sender: None,
gateway_token: None,
resource: None,
client_id_secret_name: None,
created_at: std::time::Instant::now()
.checked_sub(std::time::Duration::from_secs(600))
.expect("System uptime is too low to run expired flow test"),
@@ -3075,6 +3122,8 @@ mod tests {
secrets,
sse_sender: None,
gateway_token: None,
resource: None,
client_id_secret_name: None,
// Expired — handler will reject after lookup (no network I/O)
created_at: std::time::Instant::now()
.checked_sub(std::time::Duration::from_secs(600))