test(e2e-ui): check the MCP Tools tab against the upstream's own tools/list (#42397)

* test(e2e-ui): check the MCP Tools tab against the upstream's own tools/list

DeepWiki renamed ask_question to ask_wiki_question, and the spec hardcoded the old name, so
e2e_ui_testing went red on main for something that is not a litellm regression. The spec now asks
the upstream server for its tool list with the official MCP TypeScript SDK and expects the tab to
show exactly those cards, so a vendor rename cannot turn the job red again.

* test(e2e-ui): cite the pinned DeepWiki tool name and drop the helper docstring

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>

tests/e2e/ui/helpers/mcp.ts

@@ -1,8 +1,21 @@
 import { expect, Page as PwPage } from "@playwright/test";
+import { Client } from "@modelcontextprotocol/sdk/client/index.js";
+import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";
 import { navigateToPage } from "./navigation";
 import { Page } from "../fixtures/pages";
 import { masterKey } from "./traffic";
 
+export async function listUpstreamToolNames(url: string): Promise<string[]> {
+  const client = new Client({ name: "litellm-ui-e2e", version: "0.0.0" });
+  await client.connect(new StreamableHTTPClientTransport(new URL(url)));
+  try {
+    const { tools } = await client.listTools();
+    return tools.map((tool) => tool.name);
+  } finally {
+    await client.close();
+  }
+}
+
 /** Creates an MCP server through the UI's discovery to custom-form flow and returns its name. */
 export async function createMcpServer(page: PwPage, url: string): Promise<string> {
   await navigateToPage(page, Page.McpServers);

tests/e2e/ui/package.json

@@ -9,6 +9,7 @@
     "e2e:migration:root": "playwright test --config migration.serverRootPath.config.ts"
   },
   "devDependencies": {
+    "@modelcontextprotocol/sdk": "1.30.0",
     "@playwright/test": "1.58.1",
     "@types/node": "20.19.37",
     "typescript": "5.9.3"

tests/e2e/ui/tests/mcp/mcpTools.spec.ts

@@ -1,17 +1,20 @@
 import { test, expect, Locator } from "@playwright/test";
 import { ADMIN_STORAGE_PATH } from "../../constants";
-import { createMcpServer, deleteMcpServerByName, openMcpToolsTab } from "../../helpers/mcp";
+import { createMcpServer, deleteMcpServerByName, listUpstreamToolNames, openMcpToolsTab } from "../../helpers/mcp";
 
 // Listing and calling MCP tools, which needs a server that really answers; the create-only spec
 // points at an unreachable URL on purpose.
 //
-// This spec makes a read-only network call to DeepWiki's public MCP server, from the proxy rather
-// than the browser. It needs no credentials, so there is no secret to leak from a public repo.
+// This spec makes read-only network calls to DeepWiki's public MCP server: from the proxy, and from
+// the test runner to learn which tools the upstream advertises today, so the tool list is never
+// pinned here. It needs no credentials, so there is no secret to leak from a public repo.
 //
 // A DeepWiki outage turns this red for something that is not a litellm regression. That is left
 // visible rather than auto-skipped: skipping on connection trouble also skips when the proxy's own
 // MCP client breaks, which is the regression this exists to catch. E2E_SKIP_EXTERNAL_MCP=1 opts out.
 const MCP_SERVER_URL = "https://mcp.deepwiki.com/mcp";
+// Read from DeepWiki's tools/list on 2026-09-22. One name has to be pinned so the call-tool test can
+// fill a known input (repoName); the listing test checks it is still advertised before the UI checks.
 const TOOL_NAME = "read_wiki_structure";
 const TOOL_ARG_REPO = "BerriAI/litellm";
 
@@ -36,14 +39,17 @@ test.describe("MCP Tools", () => {
   });
 
   test("MCP Tools tab lists the tools the upstream server advertises", async ({ page }) => {
+    const upstreamTools = await listUpstreamToolNames(MCP_SERVER_URL);
+    expect(upstreamTools).toContain(TOOL_NAME);
+
     // Fetched through the proxy on mount, so allow for a cold upstream connection.
     const toolList = page.locator(".mcp-tools-scrollable");
     await expect(toolList).toBeVisible({ timeout: 30_000 });
 
-    // Non-empty would still pass if the proxy returned some other server's tools.
-    await expect(toolCard(toolList, TOOL_NAME)).toBeVisible();
-    await expect(toolCard(toolList, "ask_question")).toBeVisible();
-    await expect(toolCard(toolList, "read_wiki_contents")).toBeVisible();
+    for (const name of upstreamTools) {
+      await expect(toolCard(toolList, name)).toBeVisible();
+    }
+    await expect(toolList.locator("h4.font-mono")).toHaveCount(upstreamTools.length);
 
     // No other tool's name or description contains this string, so exactly one card survives.
     await page.getByPlaceholder("Search tools...").fill(TOOL_NAME);