Skip to content

fix(mcp): relay the OAuth callback when the redirect cannot reach the backend - #16545

Open
SimiPrambos wants to merge 2 commits into
OpenHands:mainfrom
SimiPrambos:fix/15430-mcp-oauth-callback-relay
Open

SimiPrambos wants to merge 2 commits into
OpenHands:mainfrom
SimiPrambos:fix/15430-mcp-oauth-callback-relay

Conversation

@SimiPrambos

@SimiPrambos SimiPrambos commented Aug 12, 2026 •

Copy link
Copy Markdown

HUMAN:
I reproduced this in Docker with only -p 8000:8000 published, using Attlasian Rovo.
The OAuth redirect failed with ERR_CONNECTION_REFUSED exactly as described in the
issue #15430, because the callback port lives inside the container. With this change I
copied the URL from the failed tab, pasted it into the "Redirect didn't work?"
field, and the flow completed, the server saved and mcp connected.

AGENT:

Implementation was done with Claude Code; the end-to-end Docker verification
against a live OAuth provider was done by the human contributor — see the HUMAN
section and Video/Screenshots.

Automated verification on this branch:

npm run lint       # pass
npm test           # 562 files, 4502 passed / 5 skipped / 9 todo
npm run build      # pass
npm run build:lib  # pass

Why

MCP OAuth cannot complete whenever the browser can't reach the agent-server's
loopback interface. The agent-server drives the handshake through FastMCP,
whose callback handler starts an HTTP listener on a random port and
registers http://localhost:<port>/callback as the redirect URI.

In Docker that listener lives inside the container while the OAuth provider
redirects the host browser to it, and the image publishes only port 8000 —
so the redirect dies with ERR_CONNECTION_REFUSED, the authorization code
never reaches the agent-server, and the status poll times out. The same failure
hits any deployment where the browser can't reach that loopback interface,
including remote and SSH-tunnelled backends.

The agent-server already supports an out-of-band relay:
POST /api/mcp/oauth/callback/{job_id} accepts a callback URL and fetches it
from inside its own network namespace, where the port is reachable.
McpService.submitOAuthCallback already wrapped that endpoint — but nothing in
the UI ever called it. This PR supplies the missing browser half.

The browser can't read the failed popup's URL on its own: it's cross-origin,
and after a connection error there's no readable document. A manual copy is the
only workable trigger.

Summary

  • McpService.authorizeOAuth accepts an optional onJobStarted callback that
    hands the OAuth probe job id to the UI; the return type is unchanged, so the
    existing single-argument call sites are unaffected.
  • New OauthCallbackFallback — a collapsed "Redirect didn't work?" disclosure
    that relays a pasted callback URL through the existing endpoint. Wired into
    the add/edit modal, the install modal, and the reauthorize action (token
    expiry is the most common way an existing install hits this).
  • The interactive wait gets its own 300s budget so a hand-pasted URL fits, and
    the add/edit modal is no longer undismissable while that wait runs.

Issue Number

Closes #15430

How to Test

  1. Build and run the Docker image publishing only -p 8000:8000.
  2. Customize → MCP → Add MCP Server; configure an HTTP server with OAuth
    (the GitLab MCP server is the reported case).
  3. Authorize in the popup. The redirect still fails with
    ERR_CONNECTION_REFUSED — that's the environment, not the bug.
  4. Copy the failed tab's full URL, expand "Redirect didn't work?", paste, submit.
  5. The flow completes and the server is saved with its OAuth state.

Without this PR, step 4 has no UI at all and the flow dead-ends.

Video/Screenshots

screen-recording-2026-08-12-at-152500_1oswFNwo.mp4

Type

  • Bug fix
  • Feature
  • Refactor
  • Breaking change
  • Docs / chore

Notes

No new SSRF surface. The relayed URL is fetched server-side, but the
agent-server's _validate_callback_url already pins the scheme to http, the
host to loopback, and both port and path to the values that job itself
generated. Client-side validation is deliberately looser than the server's
(scheme + loopback host only): pinning the path or requiring a code param in
the browser would assert knowledge the browser doesn't have, and would reject
provider denial redirects (?error=access_denied) that are useful to relay so
the backend can fail the job immediately instead of burning the full wait.

The 300s wait matches the agent-server's own callback_timeout in
software-agent-sdk
(openhands-agent-server/openhands/agent_server/mcp_router.py,
_BrowserCoordinatedOAuth.callback_handler). It is a separate constant:
OAUTH_MCP_TEST_TIMEOUT_SECONDS is untouched because it also sets HTTP client
timeouts. Raising the interactive wait also exposed that the add/edit modal
blocked Escape, backdrop click and its close button for the whole duration, so
that modal is now dismissable while OAuth is pending — matching what the install
modal already did.

Error text. The shared retrieveAxiosErrorMessage reads error/message
but not FastAPI's detail, so backend rejections surfaced as "Request failed".
A small file-local helper in the new component reads detail first and falls
back to the shared util. Kept local since no other module needs it today;
happy to promote it to src/utils/type-guards.ts if you'd prefer.

Translations. The two new prose keys were machine-translated into the 14
non-English locales. Corrections from native speakers are very welcome — they
are MCP$OAUTH_CALLBACK_FALLBACK_LABEL and MCP$OAUTH_CALLBACK_INVALID_URL.
The URL placeholder is a technical example and is allowlisted in
IDENTICAL_VALUE_ALLOWLIST, matching the existing MCP OAuth placeholders.

Not addressed here: making the agent-server bind a fixed callback port. That
lives in software-agent-sdk, needs a coordinated release, and would still fail
for anyone who doesn't publish the port — so this fix is deliberately
frontend-only and works for every unreachable-loopback deployment.

Jev-Fast-Audit

⚡ Jev fast audit · estimates · 0.54s · commit 4181c36
Strongest signal: No primary concern selected.
Evidence: No primary concern to locate.
Coverage: ⚠️ reduced context — partial coverage; 30/33 hunks, 15/15 files (context budget: 29, hunk budget: 3).

All estimates and evidence
Estimate Likelihood / value Direct evidence
SQL injection 3.0% No direct hunk selected
Command injection 3.0% No direct hunk selected
Weakened authentication 9.0% No direct hunk selected
Weakened authorization 13.0% No direct hunk selected
Contract regression 11.0% No direct hunk selected
Data loss 5.0% No direct hunk selected
Sensitive data disclosure 8.0% No direct hunk selected
Unexpected data transfer 6.0% No direct hunk selected
Credential misuse 9.0% No direct hunk selected
Untrusted instruction authority 3.0% No direct hunk selected
Package source redirection 4.0% No direct hunk selected
Unverified remote execution 2.0% No direct hunk selected
Privileged environment access 2.0% No direct hunk selected
Security assessment bypass 8.0% No direct hunk selected
Prohibited workload 3.0% No direct hunk selected
Primary concern None selected; confidence 69.0% No primary concern to locate

… backend

MCP OAuth fails whenever the browser cannot reach the agent-server's
loopback interface. The agent-server starts its callback listener on a
random port; in Docker that port lives inside the container, so the
provider's redirect to the host browser dies with ERR_CONNECTION_REFUSED
and the OAuth job never completes.

The agent-server already accepts an out-of-band relay at
POST /api/mcp/oauth/callback/{job_id} and fetches that URL from inside
its own network namespace. McpService.submitOAuthCallback already
wrapped the endpoint, but nothing in the UI ever called it.

authorizeOAuth now hands the probe job id to its caller, and a new
OauthCallbackFallback lets the user paste the URL their browser failed
to load. It is wired into the add/edit modal, the install modal, and the
reauthorize action. The browser cannot read the failed popup's URL
itself -- it is cross-origin, with no readable document after a
connection error -- so a manual copy is the only workable trigger.

Client-side validation stays deliberately loose (http + loopback host):
the agent-server pins scheme, host, port and path to the values its own
job generated, and returns a specific message this UI surfaces inline.

The interactive wait moves to a separate 300s budget so a hand-pasted
URL fits, and the OAuth modal is no longer undismissable while it runs.

Closes OpenHands#15430

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@github-actions github-actions Bot added the type: fix A bug fix label Aug 12, 2026
@github-actions

Copy link
Copy Markdown
Contributor

✅ Mock-LLM E2E Tests

62/62 passed

Commit: ba000898 · Workflow run · Test artifacts

Details
Status Test Duration
✅ automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 1: setup LLM profile and register automation trajectory 6.5s
✅ automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 2: create automation and dispatch run via the UI 28.4s
✅ automations/mock-llm-automation.spec.ts › mock-LLM automation lifecycle › step 3: verify automation and run on the automations page 5.9s
✅ automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › automation card sends the correct slash command to a conversation 15.1s
✅ automations/mock-llm-preset-automation.spec.ts › preset automation → slash command conversation › direct slash command from home page triggers skill activation 12.7s
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: fresh install with runtime-injected key › reaches the onboarding modal without pre-seeded localStorage 1.3s
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: non-public key rotation › recovers when localStorage has a stale session API key 5.4s
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › shows first-run onboarding before the auth screen when no key is configured 1.3s
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › rejects an incorrect key with an inline error 1.4s
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › allows access after pasting the correct key 1.4s
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › skips auth screen for returning user with valid stored key 786ms
✅ backends/mock-llm-auth-modes.spec.ts › auth mode: public gate › re-prompts when the server rotates its key (stale localStorage) 1.3s
✅ backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → backend-only › frontend-only connects to a separate backend-only instance 17.3s
✅ backends/mock-llm-cross-connect.spec.ts › cross-connect: frontend-only → multiple backends › connects to two separate backends and switches between them 21.7s
✅ backends/mock-llm-cross-connect.spec.ts › cross-connect: sidebar links pin their backend › cmd-clicking a sidebar conversation opens it on the owning backend 31.6s
✅ backends/mock-llm-partial-stack.spec.ts › partial stack: --frontend-only › serves the frontend but returns 503 for backend routes 7.3s
✅ backends/mock-llm-partial-stack.spec.ts › partial stack: --backend-only › serves backend APIs but returns 503 for the frontend root 15.1s
✅ backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › fails with a clear error when the ingress port is occupied 100ms
✅ backends/mock-llm-partial-stack.spec.ts › partial stack: port conflict › starts successfully on a free port after a conflict 6.0s
✅ conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 1: create an LLM profile pointing at the mock LLM server 6.2s
✅ conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 2: activate the mock-llm profile and verify settings API 6.1s
✅ conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 3: run a conversation with the mock LLM 7.3s
✅ conversations/mock-llm-conversation.spec.ts › mock-LLM agent-server conversation › step 4: resume conversation from sidebar after navigating away 5.7s
✅ conversations/mock-llm-image-upload.spec.ts › mock-LLM image upload › attaching an image embeds it as base64 in the LLM completion call 12.8s
✅ files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 1: ensure mock LLM profile is configured 6.4s
✅ files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 2: start conversation and attach workspace metadata 11.8s
✅ files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 3: git control bar shows workspace pill and git actions 25.3s
✅ files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 4: files tab can enable diff view for attached workspace 5.9s
✅ files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 5: browser tab shows empty state 6.3s
✅ files/mock-llm-files-and-git.spec.ts › files tab, git control bar, and browser tab › step 6: files tab defaults to file-tree view without attached workspace 8.2s
✅ home/mock-llm-folder-workspace.spec.ts › mock-LLM folder browser → workspace → conversation › step 1: browse to a folder, add it as a workspace, and launch a conversation with the correct working_dir 7.5s
✅ mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 1: GitHub card is visible on the MCP marketplace page 5.5s
✅ mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 2: clicking GitHub add control opens the install modal with correct fields 5.7s
✅ mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 3: full install flow — fill PAT, submit, verify installed 11.8s
✅ mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › step 4: installed GitHub server can be deleted 5.9s
✅ mcp/mock-llm-mcp-github.spec.ts › MCP GitHub server install flow › regression: sibling create, edit, and delete preserve GitHub credentials with one MCP request each 12.5s
✅ mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: invalid Slack credentials are blocked with a credential-check error 5.7s
✅ mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: a valid token missing only a scope still installs (missing_scope is not a credential failure) 5.8s
✅ mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › install: an older agent server that omits tool_result still installs (compat) 5.8s
✅ mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection verifies the stored credentials and surfaces a credential failure 5.7s
✅ mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › edit: Test Connection reports success for valid stored credentials 5.7s
✅ mcp/mock-llm-mcp-slack-credentials.spec.ts › MCP Test Connection credential verification (Slack) › custom (non-catalog) server: Test Connection attaches no verification probe 5.8s
✅ onboarding/mock-llm-onboarding-happy-path.spec.ts › onboarding happy path › completes the full onboarding flow and launches a conversation 4.4s
✅ onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › keeps the modal open on backdrop click and Escape 1.5s
✅ onboarding/mock-llm-onboarding-regressions.spec.ts › onboarding recent regressions › defaults the LLM setup step to OpenAI GPT-5.5 1.5s
✅ regressions/mock-llm-ui-regressions.spec.ts › UI regressions › scopes standalone styles to the agent-server-ui shell 1.4s
✅ regressions/mock-llm-ui-regressions.spec.ts › UI regressions › renders critic results on agent messages and finish actions 1.4s
✅ regressions/mock-llm-ui-regressions.spec.ts › UI regressions › loads older events when scrolling up 1.8s
✅ regressions/mock-llm-ui-regressions.spec.ts › UI regressions › selected workspace persists after navigating away and returning 2.1s
✅ regressions/mock-llm-ui-regressions.spec.ts › UI regressions › cleared sessionStorage yields empty workspace selection 1.3s
✅ settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 1: configure ACP agent via Settings → Agent UI 13.0s
✅ settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 2: reload and verify ACP settings are persisted in UI 5.7s
✅ settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 3: start ACP conversation and verify agent reply 6.3s
✅ settings/mock-llm-acp-agent.spec.ts › mock-LLM ACP agent conversation › step 4: resume ACP conversation from sidebar after navigating away 5.7s
✅ settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 1: configure LLM, create switch-target profile, register trajectory 6.9s
✅ settings/mock-llm-model-switch.spec.ts › mock-LLM /model slash command › step 2: start conversation, switch profile via /model, verify switch 7.7s
✅ settings/mock-llm-profile-management.spec.ts › active profile deletion + reconciliation › active profile is deletable and reconciliation activates another profile 9.3s
✅ settings/mock-llm-profile-management.spec.ts › same-model profile identity › chat header shows the correct profile when two profiles share the same model 14.4s
✅ settings/mock-llm-profile-management.spec.ts › OpenHands provider hidden base_url preservation › re-saving an OpenHands profile from Basic view preserves hidden base_url 7.3s
✅ skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › project skill in workspace/.agents/skills/ triggers on matching keyword 13.0s
✅ skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › user skill in ~/.openhands/skills/ triggers on matching keyword 7.6s
✅ skills/mock-llm-skills.spec.ts › skill loading: project, user, and deletion › deleting a user skill removes it from subsequent conversations 7.8s

Posted by the Mock-LLM E2E workflow · results are deterministic (scripted LLM responses)

@all-hands-bot

all-hands-bot commented Aug 12, 2026 •

Copy link
Copy Markdown
Collaborator

🚦 CI is currently failing on this PR's latest commit.

Please fix the failing checks before OpenHands reviews it - this is re-checked automatically once you push a new commit. (A maintainer can also request @all-hands-bot as a reviewer to have it reviewed regardless of CI status.)

This is an automated check - no AI was used to generate this comment.

@github-actions

Copy link
Copy Markdown
Contributor

PR Artifacts Notice

This PR contains a .pr/ directory with temporary PR-specific documents. Because this is a fork PR, the workflow will open or update a cleanup PR against main after merge.

@VascoSch92

Copy link
Copy Markdown
Member

@SimiPrambos Nice work :-)

Two things I noticed while testing it:

  1. Closing the modal mid-OAuth doesn't actually abandon the flow

The new comment on ModalBackdrop says there's nothing to orphan beyond the backend job, but that isn't quite true. authorizeOAuth has no abort, so after the modal closes the poll keeps going. If the user then finishes consent in the popup anyway, the .then in handleSubmit still calls addMcpServer / updateMcpServer, and the server gets saved even though they walked away. The editor has unmounted by then, so if that save fails the user never sees an error. React Query skips the per-call onError once the observer has no listeners, and the hooks don't define their own.

To be fair, the Cancel button could already do this before the PR (it's only disabled on isPending). This PR adds Escape, backdrop click and the close button on top, though, and the comment makes it look intentional. I think we should either cancel the flow when the modal closes (an abort signal into authorizeOAuth, or at least ignore the result once it's unmounted), or keep dismiss blocked while isOauthTesting is true.

  1. The backend's detail message never shows up in the fallback

extractCallbackErrorMessage checks error instanceof AxiosError, but submitOAuthCallback goes through the typescript-client MCPClient, which uses fetch and throws HttpError. On that error the body is at error.response.detail, not error.response.data.detail. So a 400 like "Unexpected OAuth callback URL" ends up displayed as the raw HTTP request failed (400 Bad Request): {"detail":"Unexpected OAuth callback URL"}. The test passes because it mocks an AxiosError, which this client never throws. There's already an isSdkHttpError helper in src/api/agent-server-compatibility.ts that should work here, and the test should mock an HttpError instead.

@all-hands-bot all-hands-bot left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This review was posted by an AI agent (OpenHands).

Scope check: frontend-only fix in the correct repository. The relay endpoint POST /api/mcp/oauth/callback/{job_id} already lives in software-agent-sdk, and this PR only supplies the missing browser half plus UI wiring — that is Agent Canvas work. A manual paste is a defensible trigger, since the failed popup is cross-origin and has no readable document.

Verification on head 4181c36:

  • Focused tests pass: npx vitest run on the 5 changed test files (oauth-callback-fallback, custom-server-editor, install-server-modal, mcp-server-health, mcp-service.api) → 54 passed.
  • CI: test-and-build (ubuntu) and test-and-build (windows) pass. Validate PR description fails on this exact head with: None of the linked issues (#15430) carry the ready-for-dev label. Issue #15430 currently carries only bug, docker, mcp — no readiness label. That is the repository's own pre-merge gate (.github/workflows/pr-description-check.yml), so a maintainer/label action is required before merge.
  • Live evidence: the HUMAN Docker reproduction against a real provider plus the attached video satisfy the UI before/after evidence requirement.

Two correctness findings, detailed inline:

  1. extractCallbackErrorMessage can never match in production. submitOAuthCallback goes through MCPClient → the shared HttpClient, which uses fetch and throws HttpError, not AxiosError. So the whole point of the helper — surfacing the backend's detail instead of HTTP request failed (400 …) — is not achieved, and the new test passes only because it mocks a shape this call path never produces.

  2. Dropping isOauthTesting from isDismissBlocked makes the modal dismissible mid-OAuth, but the in-flight authorizeOAuth is not aborted, so completing consent after dismissing still persists the server, and a failing save goes unreported. The comment claiming "there is nothing to orphan" is inaccurate.

🔄 CHANGES REQUESTED

*/
function extractCallbackErrorMessage(error: unknown): string {
if (
error instanceof AxiosError &&

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

submitOAuthCallback reaches the agent-server through MCPClient → the shared HttpClient, which uses fetch and throws HttpError (name: "HttpError", parsed body directly on error.response). It never throws an AxiosError, so error instanceof AxiosError is false on every real rejection. The fallback retrieveAxiosErrorMessage then treats HttpError as a plain Error and returns error.message, i.e. the user sees HTTP request failed (400 Bad Request): {"detail":"Unexpected OAuth callback URL"} instead of the backend's detail — exactly the behaviour this helper was added to prevent. The new test passes only because it constructs an AxiosError, a shape this call path never produces.

Smallest fix: use the existing getApiErrorMessage(error, fallback) from #/utils/api-error-message.ts, which already reads message/detail from both transports (error.response for HttpError, error.response.data for axios), and update the test to reject with an HttpError-shaped error, e.g. Object.assign(new Error("HTTP request failed"), { name: "HttpError", status: 400, response: { detail: "Unexpected OAuth callback URL" } }).

// Deliberately excludes `isOauthTesting`: that wait is interactive (the user
// is off in a provider popup, for up to 300s) and abandoning it must stay
// possible. See the ModalBackdrop comment below.
const isDismissBlocked = isPending || isTesting || showDeleteConfirm;

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

authorizeOAuth is awaited and has no abort path, so closing the modal here does not abandon the flow. McpService.authorizeOAuth(...).then(...) is still pending, and when the user finishes consent in the popup the .then runs addMcpServer/updateMcpServer with onSuccess: onSaved → onClose(). The server is persisted after the user walked away.

If that save then fails, handleError is supplied as the mutation's per-call onError, and @tanstack/query-core's MutationObserver.#notify only invokes #mutateOptions.onError when hasListeners() is true (verified in the installed 5.101.4 build). After unmount the observer is gone, so the toast never fires and the failure is silent.

The comment above this line — "there is nothing to orphan beyond a backend job that times out on its own" — is therefore not accurate. Either thread an AbortSignal into authorizeOAuth and stop polling/saving on unmount, or ignore the resolved result once the editor has unmounted, or keep dismissal blocked while isOauthTesting is true.

@neubig

neubig commented Nov 14, 2026

Copy link
Copy Markdown
Member

Thanks for working on this and for reproducing it in Docker. The maintainers' direction for #15430 and #18888 is to make normal browser authorization complete, without a manual relay step. #19744 together with OpenHands/software-agent-sdk#6221 does that: the agent-server registers a redirect URI on the URL the browser already uses (<Canvas backend URL or OH_WEB_URL>/api/mcp/oauth/redirect) and serves that route itself. The paste-the-callback-URL fallback is then no longer needed. Before/after screenshots for the Docker case are in #19744. I suggest closing this PR in favor of #19744.

This comment/PR was created by an AI agent (OpenHands) on behalf of Graham Neubig.

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

type: fix A bug fix

Projects

None yet

Development

Successfully merging this pull request may close these issues.

OAuth MCP callback fails in Docker: localhost redirect port not exposed

4 participants