ext-apps/examples/cohort-heatmap-server/server.ts
Olivier Chafik c9e37204de
tests: add Playwright E2E tests with screenshot golden testing (+ fix examples session handling) (#115)
* Add Playwright E2E tests with screenshot golden testing

- Add E2E tests for all 8 MCP server examples
- Screenshot golden images for visual regression testing
- CI workflow for running E2E tests
- npm scripts: test:e2e, test:e2e:update, test:e2e:ui

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add default demo code for Three.js example

When no code is provided, show a rotating green cube demo.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add E2E testing documentation to CONTRIBUTING.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update Three.js golden screenshot with 3D cube

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add explicit permissions to CI workflow

Set minimal read-only permissions for security best practices.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix test.setTimeout() to be inside describe blocks

Playwright requires setTimeout to be called within a test or describe block.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Simplify E2E tests - remove excessive timeouts

- Remove explicit setTimeout calls (default 30s is sufficient)
- Replace waitForTimeout(5000/6000) with proper waitForAppLoad()
- Wait for inner iframe visibility instead of fixed delays
- Keep only 500ms stabilization for screenshot animations

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Auto-generate missing snapshots in CI

Use updateSnapshots: 'missing' in CI to handle cross-platform
screenshot differences (macOS vs Linux).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use platform-agnostic golden screenshots

- Remove -chromium-darwin suffix from snapshot filenames
- Configure snapshotPathTemplate for cross-platform compatibility
- Increase tolerance to 5% for rendering differences between platforms

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Refactor tests to use forEach instead of for-of loop

May help with Playwright test discovery issues in CI.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use npm ci and list reporter in CI

- Use npm ci for exact package versions
- Use --reporter=list instead of html to avoid potential re-evaluation issues
- Only upload test-results on failure

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Exclude e2e tests from bun test

Run bun test only on src/ directory to avoid running Playwright tests
with Bun's test runner.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix prettier formatting

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add interaction tests for basic server apps

Test that clicking buttons in the MCP App triggers the corresponding
host callbacks:
- Send Message → host logs "Message from MCP App"
- Send Log → host logs "Log message from MCP App"
- Open Link → host logs "Open link request"

Tests both React and Vanilla JS implementations.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Mask dynamic content in E2E screenshot tests

Add Playwright mask option to handle servers with dynamic/random content:
- basic-react/vanillajs: mask server time display
- system-monitor: mask CPU chart, memory stats, uptime
- cohort-heatmap: mask heatmap grid (random data)
- customer-segmentation: mask scatter chart (random data)

This addresses PR feedback about handling examples with non-deterministic
output. Masking replaces the previous 10% tolerance with proper exclusion
of dynamic elements, allowing tighter 1% tolerance for the rest of the UI.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add wiki-explorer to E2E tests with default URL param

- Add default URL "https://en.wikipedia.org/wiki/Model_Context_Protocol" to
  wiki-explorer-server's get-first-degree-links tool inputSchema
- Update basic-host to automatically populate input field with tool defaults
  extracted from inputSchema.properties
- Add wiki-explorer-server to E2E test suite with dynamic masking for the
  force-directed graph

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Use .default() for threejs tool schema instead of .optional()

This exposes the default code and height values in the JSON Schema,
allowing basic-host to auto-populate the input field with defaults.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Enable parallel E2E tests with timeouts and canvas masking

- Enable fullyParallel with 4 workers locally (2 in CI)
- Add 30s timeout per test
- Mask threejs canvas for stable screenshots
- Update snapshots to reflect default values in input fields

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Add pre-commit check for private registry URLs in package-lock.json

Same check as in CI to catch issues before push.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Increase screenshot diff tolerance to 6% for cross-platform rendering

Font rendering differs between macOS and Linux, causing ~5% pixel differences.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Revert pre-commit artifactory check (moved to separate PR #133)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Format threejs server.ts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update CONTRIBUTING.md to reflect platform-agnostic screenshots

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix(e2e): use factory pattern for MCP servers to support parallel connections

McpServer only supports one transport at a time. When multiple browser
contexts connected in parallel, calling server.connect(transport) for
each session overwrote the previous transport's callbacks, causing
connection corruption and test timeouts.

Changes:
- server-utils.ts: accept factory function instead of single instance
- All 9 example servers: wrap server creation in createServer() function
- playwright.config.ts: re-enable parallel execution (4 workers)
- servers.spec.ts: add toBeEnabled wait for server connection
- Update screenshot baselines for basic-vanillajs and cohort-heatmap

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-12-13 20:57:27 +00:00

219 lines
6 KiB
TypeScript

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import type { ReadResourceResult } from "@modelcontextprotocol/sdk/types.js";
import fs from "node:fs/promises";
import path from "node:path";
import { z } from "zod";
import { RESOURCE_MIME_TYPE, RESOURCE_URI_META_KEY } from "../../dist/src/app";
import { startServer } from "../shared/server-utils.js";
const DIST_DIR = path.join(import.meta.dirname, "dist");
// Schemas - types are derived from these using z.infer
const GetCohortDataInputSchema = z.object({
metric: z
.enum(["retention", "revenue", "active"])
.optional()
.default("retention"),
periodType: z.enum(["monthly", "weekly"]).optional().default("monthly"),
cohortCount: z.number().min(3).max(24).optional().default(12),
maxPeriods: z.number().min(3).max(24).optional().default(12),
});
const CohortCellSchema = z.object({
cohortIndex: z.number(),
periodIndex: z.number(),
retention: z.number(),
usersRetained: z.number(),
usersOriginal: z.number(),
});
const CohortRowSchema = z.object({
cohortId: z.string(),
cohortLabel: z.string(),
originalUsers: z.number(),
cells: z.array(CohortCellSchema),
});
const CohortDataSchema = z.object({
cohorts: z.array(CohortRowSchema),
periods: z.array(z.string()),
periodLabels: z.array(z.string()),
metric: z.string(),
periodType: z.string(),
generatedAt: z.string(),
});
// Types derived from schemas
type CohortCell = z.infer<typeof CohortCellSchema>;
type CohortRow = z.infer<typeof CohortRowSchema>;
type CohortData = z.infer<typeof CohortDataSchema>;
// Internal types (not part of API schema)
interface RetentionParams {
baseRetention: number;
decayRate: number;
floor: number;
noise: number;
}
// Retention curve generator using exponential decay
function generateRetention(period: number, params: RetentionParams): number {
if (period === 0) return 1.0;
const { baseRetention, decayRate, floor, noise } = params;
const base = baseRetention * Math.exp(-decayRate * (period - 1)) + floor;
const variation = (Math.random() - 0.5) * 2 * noise;
return Math.max(0, Math.min(1, base + variation));
}
// Generate cohort data
function generateCohortData(
metric: string,
periodType: string,
cohortCount: number,
maxPeriods: number,
): CohortData {
const now = new Date();
const cohorts: CohortRow[] = [];
const periods: string[] = [];
const periodLabels: string[] = [];
// Generate period headers
for (let i = 0; i < maxPeriods; i++) {
periods.push(`M${i}`);
periodLabels.push(i === 0 ? "Month 0" : `Month ${i}`);
}
// Retention parameters vary by metric type
const paramsMap: Record<string, RetentionParams> = {
retention: {
baseRetention: 0.75,
decayRate: 0.12,
floor: 0.08,
noise: 0.04,
},
revenue: { baseRetention: 0.7, decayRate: 0.1, floor: 0.15, noise: 0.06 },
active: { baseRetention: 0.6, decayRate: 0.18, floor: 0.05, noise: 0.05 },
};
const params = paramsMap[metric] ?? paramsMap.retention;
// Generate cohorts (oldest first)
for (let c = 0; c < cohortCount; c++) {
const cohortDate = new Date(now);
cohortDate.setMonth(cohortDate.getMonth() - (cohortCount - 1 - c));
const cohortId = `${cohortDate.getFullYear()}-${String(cohortDate.getMonth() + 1).padStart(2, "0")}`;
const cohortLabel = cohortDate.toLocaleDateString("en-US", {
month: "short",
year: "numeric",
});
// Random cohort size: 1000-5000 users
const originalUsers = Math.floor(1000 + Math.random() * 4000);
// Number of periods this cohort has data for (newer cohorts have fewer periods)
const periodsAvailable = cohortCount - c;
const cells: CohortCell[] = [];
let previousRetention = 1.0;
for (let p = 0; p < Math.min(periodsAvailable, maxPeriods); p++) {
// Retention must decrease or stay same (with small exceptions for noise)
let retention = generateRetention(p, params);
retention = Math.min(retention, previousRetention + 0.02);
previousRetention = retention;
cells.push({
cohortIndex: c,
periodIndex: p,
retention,
usersRetained: Math.round(originalUsers * retention),
usersOriginal: originalUsers,
});
}
cohorts.push({ cohortId, cohortLabel, originalUsers, cells });
}
return {
cohorts,
periods,
periodLabels,
metric,
periodType,
generatedAt: new Date().toISOString(),
};
}
function createServer(): McpServer {
const server = new McpServer({
name: "Cohort Heatmap Server",
version: "1.0.0",
});
// Register tool and resource
const resourceUri = "ui://get-cohort-data/mcp-app.html";
server.registerTool(
"get-cohort-data",
{
title: "Get Cohort Retention Data",
description:
"Returns cohort retention heatmap data showing customer retention over time by signup month",
inputSchema: GetCohortDataInputSchema.shape,
_meta: { [RESOURCE_URI_META_KEY]: resourceUri },
},
async ({ metric, periodType, cohortCount, maxPeriods }) => {
const data = generateCohortData(
metric,
periodType,
cohortCount,
maxPeriods,
);
return {
content: [{ type: "text", text: JSON.stringify(data) }],
};
},
);
server.registerResource(
resourceUri,
resourceUri,
{},
async (): Promise<ReadResourceResult> => {
const html = await fs.readFile(
path.join(DIST_DIR, "mcp-app.html"),
"utf-8",
);
return {
contents: [
{
uri: resourceUri,
mimeType: RESOURCE_MIME_TYPE,
text: html,
},
],
};
},
);
return server;
}
async function main() {
if (process.argv.includes("--stdio")) {
await createServer().connect(new StdioServerTransport());
} else {
const port = parseInt(process.env.PORT ?? "3104", 10);
await startServer(createServer, { port, name: "Cohort Heatmap Server" });
}
}
main().catch((e) => {
console.error(e);
process.exit(1);
});