sh-mcp/packages/shared/src/mcp.test.ts

/**
 * MCP conformance + tool-hiding over the protocol (build-plan §5).
 *
 * Uses the SDK's in-memory linked transport to drive a real Client against our
 * `createMcpServer`: handshake, scope-filtered `tools/list`, a successful
 * `tools/call` round-trip, server-side scope enforcement on a forced hidden
 * call, and validation that every advertised tool carries a JSON-Schema input.
 */

import { describe, it, expect } from 'vitest';

import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { InMemoryTransport } from '@modelcontextprotocol/sdk/inMemory.js';

import { ToolRegistry, defineTool } from './registry.js';
import { createMcpServer } from './mcp.js';
import { NoopAuditLogger } from './audit.js';
import { NoopRateLimiter } from './rate-limit.js';
import type { AuthContext, Scope } from './types.js';
import type { DispatchDeps } from './dispatch.js';

const deps: DispatchDeps = {
  auditLogger: new NoopAuditLogger(),
  rateLimiter: new NoopRateLimiter(),
};

function buildRegistry(): ToolRegistry {
  const r = new ToolRegistry();
  r.register(
    defineTool<{ id: string }, { id: string; ok: boolean }>({
      name: 'lookup_thing',
      description: 'look up a thing',
      tier: 'ops',
      requiredScope: 'ops:read',
      inputSchema: {
        type: 'object',
        required: ['id'],
        properties: { id: { type: 'string' } },
      },
      handler: async (input) => ({ id: input.id, ok: true }),
    }),
  );
  r.register(
    defineTool<{ vendor: string }, unknown>({
      name: 'lookup_payment',
      description: 'finance only',
      tier: 'finance',
      requiredScope: 'finance:read',
      inputSchema: { type: 'object', properties: { vendor: { type: 'string' } } },
      handler: async () => ({ secret: true }),
    }),
  );
  return r;
}

async function connect(scopes: Scope[]): Promise<Client> {
  const ctx: AuthContext = { sub: 'u@seahavenind.com', scopes, aud: 'sh-mcp-ops' };
  const server = createMcpServer(buildRegistry(), ctx, deps, {
    name: 'sh-mcp-test',
    version: '0.0.1',
  });
  const [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair();
  await server.connect(serverTransport);
  const client = new Client({ name: 'test-client', version: '0.0.1' });
  await client.connect(clientTransport);
  return client;
}

describe('MCP conformance', () => {
  it('completes the handshake and lists scope-permitted tools', async () => {
    const client = await connect(['ops:read']);
    const { tools } = await client.listTools();
    const names = tools.map((t) => t.name);
    expect(names).toContain('lookup_thing');
    // finance tool is hidden from an ops-only caller.
    expect(names).not.toContain('lookup_payment');
    // every advertised tool carries a JSON-Schema input.
    for (const t of tools) {
      expect(t.inputSchema).toBeDefined();
      expect((t.inputSchema as { type?: string }).type).toBe('object');
    }
    await client.close();
  });

  it('round-trips a successful tools/call', async () => {
    const client = await connect(['ops:read']);
    const res = await client.callTool({ name: 'lookup_thing', arguments: { id: 'WO-1' } });
    expect(res.structuredContent).toEqual({ id: 'WO-1', ok: true });
    await client.close();
  });

  it('hides finance tools but STILL enforces scope on a forced call (hiding is not the boundary)', async () => {
    const client = await connect(['ops:read']);
    await expect(
      client.callTool({ name: 'lookup_payment', arguments: { vendor: 'x' } }),
    ).rejects.toThrow();
    await client.close();
  });

  it('rejects malformed input through the protocol', async () => {
    const client = await connect(['ops:read']);
    await expect(
      client.callTool({ name: 'lookup_thing', arguments: { wrong: 'field' } }),
    ).rejects.toThrow();
    await client.close();
  });

  it('reveals finance tools to a finance caller', async () => {
    const client = await connect(['finance:read']);
    const names = (await client.listTools()).tools.map((t) => t.name);
    expect(names).toContain('lookup_payment');
    expect(names).not.toContain('lookup_thing');
    await client.close();
  });
});