ext-apps/examples/budget-allocator-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

316 lines
8.8 KiB
TypeScript
Executable file

/**
* Budget Allocator MCP Server
*
* Provides budget configuration, 24 months of historical allocation data,
* and industry benchmarks by company stage.
*/
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import type {
CallToolResult,
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 BudgetCategorySchema = z.object({
id: z.string(),
name: z.string(),
color: z.string(),
defaultPercent: z.number(),
});
const HistoricalMonthSchema = z.object({
month: z.string(),
allocations: z.record(z.string(), z.number()),
});
const BenchmarkPercentilesSchema = z.object({
p25: z.number(),
p50: z.number(),
p75: z.number(),
});
const StageBenchmarkSchema = z.object({
stage: z.string(),
categoryBenchmarks: z.record(z.string(), BenchmarkPercentilesSchema),
});
const BudgetConfigSchema = z.object({
categories: z.array(BudgetCategorySchema),
presetBudgets: z.array(z.number()),
defaultBudget: z.number(),
currency: z.string(),
currencySymbol: z.string(),
});
const BudgetAnalyticsSchema = z.object({
history: z.array(HistoricalMonthSchema),
benchmarks: z.array(StageBenchmarkSchema),
stages: z.array(z.string()),
defaultStage: z.string(),
});
const BudgetDataResponseSchema = z.object({
config: BudgetConfigSchema,
analytics: BudgetAnalyticsSchema,
});
// Types derived from schemas
type BudgetDataResponse = z.infer<typeof BudgetDataResponseSchema>;
type HistoricalMonth = z.infer<typeof HistoricalMonthSchema>;
type StageBenchmark = z.infer<typeof StageBenchmarkSchema>;
// Internal type (not part of API schema - includes trendPerMonth for data generation)
type BudgetCategoryInternal = z.infer<typeof BudgetCategorySchema> & {
trendPerMonth: number;
};
// ---------------------------------------------------------------------------
// Budget Categories with Trend Data
// ---------------------------------------------------------------------------
const CATEGORIES: BudgetCategoryInternal[] = [
{
id: "marketing",
name: "Marketing",
color: "#3b82f6",
defaultPercent: 25,
trendPerMonth: 0.15,
},
{
id: "engineering",
name: "Engineering",
color: "#10b981",
defaultPercent: 35,
trendPerMonth: -0.1,
},
{
id: "operations",
name: "Operations",
color: "#f59e0b",
defaultPercent: 15,
trendPerMonth: 0.05,
},
{
id: "sales",
name: "Sales",
color: "#ef4444",
defaultPercent: 15,
trendPerMonth: 0.08,
},
{
id: "rd",
name: "R&D",
color: "#8b5cf6",
defaultPercent: 10,
trendPerMonth: -0.18,
},
];
// ---------------------------------------------------------------------------
// Industry Benchmarks by Company Stage
// ---------------------------------------------------------------------------
const BENCHMARKS: StageBenchmark[] = [
{
stage: "Seed",
categoryBenchmarks: {
marketing: { p25: 15, p50: 20, p75: 25 },
engineering: { p25: 40, p50: 47, p75: 55 },
operations: { p25: 8, p50: 12, p75: 15 },
sales: { p25: 10, p50: 15, p75: 20 },
rd: { p25: 5, p50: 10, p75: 15 },
},
},
{
stage: "Series A",
categoryBenchmarks: {
marketing: { p25: 20, p50: 25, p75: 30 },
engineering: { p25: 35, p50: 40, p75: 45 },
operations: { p25: 10, p50: 14, p75: 18 },
sales: { p25: 15, p50: 20, p75: 25 },
rd: { p25: 8, p50: 12, p75: 15 },
},
},
{
stage: "Series B",
categoryBenchmarks: {
marketing: { p25: 22, p50: 27, p75: 32 },
engineering: { p25: 30, p50: 35, p75: 40 },
operations: { p25: 12, p50: 16, p75: 20 },
sales: { p25: 18, p50: 23, p75: 28 },
rd: { p25: 8, p50: 12, p75: 15 },
},
},
{
stage: "Growth",
categoryBenchmarks: {
marketing: { p25: 25, p50: 30, p75: 35 },
engineering: { p25: 25, p50: 30, p75: 35 },
operations: { p25: 15, p50: 18, p75: 22 },
sales: { p25: 20, p50: 25, p75: 30 },
rd: { p25: 5, p50: 8, p75: 12 },
},
},
];
// ---------------------------------------------------------------------------
// Historical Data Generation
// ---------------------------------------------------------------------------
/**
* Seeded random number generator for reproducible historical data
*/
function seededRandom(seed: number): () => number {
return () => {
seed = (seed * 1103515245 + 12345) & 0x7fffffff;
return seed / 0x7fffffff;
};
}
/**
* Generate 24 months of historical allocation data with realistic trends
*/
function generateHistory(
categories: BudgetCategoryInternal[],
): HistoricalMonth[] {
const months: HistoricalMonth[] = [];
const now = new Date();
const random = seededRandom(42); // Fixed seed for reproducibility
for (let i = 23; i >= 0; i--) {
const date = new Date(now);
date.setMonth(date.getMonth() - i);
const monthStr = `${date.getFullYear()}-${String(date.getMonth() + 1).padStart(2, "0")}`;
const rawAllocations: Record<string, number> = {};
for (const cat of categories) {
// Start from default, apply trend over time, add noise
const monthsFromStart = 23 - i;
const trend = monthsFromStart * cat.trendPerMonth;
const noise = (random() - 0.5) * 3; // +/- 1.5%
rawAllocations[cat.id] = Math.max(
0,
Math.min(100, cat.defaultPercent + trend + noise),
);
}
// Normalize to 100%
const total = Object.values(rawAllocations).reduce((a, b) => a + b, 0);
const allocations: Record<string, number> = {};
for (const id of Object.keys(rawAllocations)) {
allocations[id] = Math.round((rawAllocations[id] / total) * 1000) / 10;
}
months.push({ month: monthStr, allocations });
}
return months;
}
// ---------------------------------------------------------------------------
// MCP Server Setup
// ---------------------------------------------------------------------------
const resourceUri = "ui://budget-allocator/mcp-app.html";
/**
* Creates a new MCP server instance with tools and resources registered.
* Each HTTP session needs its own server instance because McpServer only supports one transport.
*/
function createServer(): McpServer {
const server = new McpServer({
name: "Budget Allocator Server",
version: "1.0.0",
});
server.registerTool(
"get-budget-data",
{
title: "Get Budget Data",
description:
"Returns budget configuration with 24 months of historical allocations and industry benchmarks by company stage",
inputSchema: {},
_meta: { [RESOURCE_URI_META_KEY]: resourceUri },
},
async (): Promise<CallToolResult> => {
const response: BudgetDataResponse = {
config: {
categories: CATEGORIES.map(({ id, name, color, defaultPercent }) => ({
id,
name,
color,
defaultPercent,
})),
presetBudgets: [50000, 100000, 250000, 500000],
defaultBudget: 100000,
currency: "USD",
currencySymbol: "$",
},
analytics: {
history: generateHistory(CATEGORIES),
benchmarks: BENCHMARKS,
stages: ["Seed", "Series A", "Series B", "Growth"],
defaultStage: "Series A",
},
};
return {
content: [
{
type: "text",
text: JSON.stringify(response),
},
],
};
},
);
server.registerResource(
resourceUri,
resourceUri,
{ description: "Interactive Budget Allocator UI" },
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;
}
// ---------------------------------------------------------------------------
// Server Startup
// ---------------------------------------------------------------------------
async function main() {
if (process.argv.includes("--stdio")) {
await createServer().connect(new StdioServerTransport());
} else {
const port = parseInt(process.env.PORT ?? "3103", 10);
await startServer(createServer, { port, name: "Budget Allocator Server" });
}
}
main().catch((e) => {
console.error(e);
process.exit(1);
});