diff --git a/.github/e2e-stack/select_tests.py b/.github/e2e-stack/select_tests.py
index 183a4208286..a9ca1f88660 100644
--- a/.github/e2e-stack/select_tests.py
+++ b/.github/e2e-stack/select_tests.py
@@ -6,7 +6,6 @@ SELECTABLE: Final = re.compile(r"^tests/e2e/([A-Za-z0-9_.-]+/)*test_[A-Za-z0-9_.
 UNSUPPORTED: Final = re.compile(
     r"^tests/e2e/(ui|claude_code|load)/"
     r"|^tests/e2e/mcp/test_mcp_oauth_happy_path_e2e\.py$"
-    r"|^tests/e2e/mcp/test_mcp_chat_completion_oauth_e2e\.py$"
     r"|^tests/e2e/llm_translation/realtime/test_realtime_pipecat_audio_e2e\.py$"
     r"|^tests/e2e/batches/test_managed_files_enforcement_e2e\.py$"
     r"|^tests/e2e/guardrails/test_presidio_masking_e2e\.py$"
diff --git a/tests/e2e/CONTRIBUTING.md b/tests/e2e/CONTRIBUTING.md
index 99304c50e58..2adac08329f 100644
--- a/tests/e2e/CONTRIBUTING.md
+++ b/tests/e2e/CONTRIBUTING.md
@@ -105,7 +105,7 @@ A couple of logging destinations are configured on the proxy rather than by the
 
 ### The pull request check
 
-Every same-repository PR that adds, modifies, or renames a `tests/e2e/**/test_*.py` file runs those changed files three times. A change to the harness itself, meaning a root-level `tests/e2e/*.py` file or `pytest.ini`, `tests/e2e/gateway/`, `.github/e2e-stack/`, or the workflow, also runs the `access_control` suite and both JWT suites as canaries, because those files have no test of their own that exercises the stack. `.github/e2e-stack/select_tests.py` applies both rules. The stack config at `tests/e2e/gateway/stage_mirror_ci_config.yml` must declare every model the selected suites use; a missing one shows up as a failed test id in the public log. The suite's own single rerun for network errors and 5xx responses (see `pytest.ini`) applies on every pass, so a transport blip does not fail the check while a race inside a test still does. The stage-mirror stack has a control-plane backend, two gateways behind nginx, Postgres, Keycloak, Jaeger, and TLS cluster-mode Valkey. Realm-only edits also trigger these canaries. The stack exports every gateway address in `LITELLM_PROXY_REPLICA_URLS`, so model registration waits until each gateway lists the new model rather than whichever one the load balancer answered from. Documentation, deleted-file, and application-only changes do not start the stack or request environment approval. The `ui/`, `claude_code/`, and `load/` directories, `batches/test_managed_files_enforcement_e2e.py`, `llm_translation/realtime/test_realtime_pipecat_audio_e2e.py`, `guardrails/test_presidio_masking_e2e.py`, `mcp/test_mcp_chat_completion_oauth_e2e.py`, and `mcp/test_mcp_oauth_happy_path_e2e.py` remain outside this check because they use separate tooling or need a differently configured stack: the pipecat audio suite skips itself at import time unless the NLTK `punkt_tab` data is installed, and the presidio suite fails without the analyzer and anonymizer services this stack does not start. The Redis chaos test under `load/` needs a proxy it can pause the Redis of on the same host (`gateway/redis_chaos_ci_config.yml`), which `.github/workflows/test-e2e-redis-chaos.yml` boots, and which the Buildkite `e2e-redis-chaos` step in project-releaser runs co-located with Postgres and Valkey in one pod; it is deselected unless `E2E_REDIS_CHAOS` is set. The two MCP OAuth suites need a saved Linear browser session (`E2E_LINEAR_STORAGE_STATE`) that the stage-mirror stack does not have, and the happy path runs in its own dispatch workflow `.github/workflows/test-mcp-oauth-e2e.yml`
+Every same-repository PR that adds, modifies, or renames a `tests/e2e/**/test_*.py` file runs those changed files three times. A change to the harness itself, meaning a root-level `tests/e2e/*.py` file or `pytest.ini`, `tests/e2e/gateway/`, `.github/e2e-stack/`, or the workflow, also runs the `access_control` suite and both JWT suites as canaries, because those files have no test of their own that exercises the stack. `.github/e2e-stack/select_tests.py` applies both rules. The stack config at `tests/e2e/gateway/stage_mirror_ci_config.yml` must declare every model the selected suites use; a missing one shows up as a failed test id in the public log. The suite's own single rerun for network errors and 5xx responses (see `pytest.ini`) applies on every pass, so a transport blip does not fail the check while a race inside a test still does. The stage-mirror stack has a control-plane backend, two gateways behind nginx, Postgres, Keycloak, Jaeger, and TLS cluster-mode Valkey. Realm-only edits also trigger these canaries. The stack exports every gateway address in `LITELLM_PROXY_REPLICA_URLS`, so model registration waits until each gateway lists the new model rather than whichever one the load balancer answered from. Documentation, deleted-file, and application-only changes do not start the stack or request environment approval. The `ui/`, `claude_code/`, and `load/` directories, `batches/test_managed_files_enforcement_e2e.py`, `llm_translation/realtime/test_realtime_pipecat_audio_e2e.py`, and `guardrails/test_presidio_masking_e2e.py` remain outside this check because they use separate tooling or need a differently configured stack: the pipecat audio suite skips itself at import time unless the NLTK `punkt_tab` data is installed, and the presidio suite fails without the analyzer and anonymizer services this stack does not start. The Redis chaos test under `load/` needs a proxy it can pause the Redis of on the same host (`gateway/redis_chaos_ci_config.yml`), which `.github/workflows/test-e2e-redis-chaos.yml` boots, and which the Buildkite `e2e-redis-chaos` step in project-releaser runs co-located with Postgres and Valkey in one pod; it is deselected unless `E2E_REDIS_CHAOS` is set
 
 Every selected file must execute at least one passing test in each pass, and any test failure, collection error, or entirely skipped or deselected file fails the check. A file whose tests are all marked skip therefore cannot pass this check, so unskip at least one of them, or add the file to `UNSUPPORTED` in `select_tests.py` with the reason, before changing one. A failed pass stops the run. The public log prints pytest's one-line summary for each pass, including the rerun count, and names each failed or errored test as `classname::name`, so a retried network error or a failing test is visible without the raw output. The final `e2e-changed-tests` job succeeds only when no supported test files changed or the approved run completed all three passes. Fork PRs with selected tests fail this gate until a maintainer brings the reviewed change onto a same-repository branch
 
diff --git a/tests/e2e/mcp/test_mcp_chat_completion_oauth_e2e.py b/tests/e2e/mcp/test_mcp_chat_completion_oauth_e2e.py
index 086ec929a17..01e94f7b86f 100644
--- a/tests/e2e/mcp/test_mcp_chat_completion_oauth_e2e.py
+++ b/tests/e2e/mcp/test_mcp_chat_completion_oauth_e2e.py
@@ -27,13 +27,8 @@ from __future__ import annotations
 import os
 
 import pytest
-from e2e_config import (
-    CHEAP_ANTHROPIC_MODEL,
-    LINEAR_MCP_URL,
-    LINEAR_READONLY_TOOL,
-    LINEAR_STORAGE_STATE,
-    unique_marker,
-)
+
+from e2e_config import CHEAP_ANTHROPIC_MODEL, LINEAR_MCP_URL, LINEAR_STORAGE_STATE, unique_marker
 from e2e_http import AuthHeaders
 from lifecycle import ResourceManager
 from models import ChatBody, ChatMessage, KeyGenerateBody, McpChatTool, McpServerCreateBody, ObjectPermission
@@ -55,6 +50,10 @@ pytestmark = [
     ),
 ]
 
+# Pinned from a live dance during verification (never guessed); the gateway
+# prefixes every upstream tool name with the server alias. list_teams is a
+# read-only Linear tool that takes no arguments and returns the caller's teams.
+LINEAR_READONLY_TOOL = "list_teams"
 LINEAR_PROMPT = "Use the list_teams tool to list my Linear teams, then reply with the name of one of them."