met-museum-mcp-server: Instructions file for Claude Code

Developer Protocol

Server: met-museum-mcp-server Version: 0.9.0 Framework: @cyanheads/mcp-ts-core ^0.13.15 Engines: Bun ≥1.4.0, Node ≥24.0.0 MCP SDK: @modelcontextprotocol/server ^2.3.1 Zod: ^4.6.6

Read the framework docs first: node_modules/@cyanheads/mcp-ts-core/CLAUDE.md contains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.

Core Rules

• Logic throws, framework catches. Tool/resource handlers are pure — throw on failure, no try/catch. Plain Error is fine; the framework catches, classifies, and formats. Use error factories (notFound(), validationError(), etc.) when the error code matters.
• Use ctx.log for request-scoped logging. No console calls.
• Use ctx.state for tenant-scoped storage. Never access persistence directly.
• Need input the caller didn't supply? return ctx.requestInput(...) and read ctx.inputs when the handler is re-entered. Never await for user input mid-handler.
• Secrets in env vars only — never hardcoded.
• Cut noise. Add only what earns its place: no speculative generality, no guards for states the framework already prevents (Zod-validated params, classified errors), no abstraction until a third caller proves it, no option nothing sets.
• Close the loop on issues. When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.

Patterns

Tool

import { tool, z } from '@cyanheads/mcp-ts-core';
import { getMetService } from '@/services/met/met-service.js';

export const metSearchCollections = tool('met_search_collections', {
  description: 'Search the Metropolitan Museum of Art collection by keyword and optional filters.',
  annotations: { readOnlyHint: true, idempotentHint: true },
  input: z.object({
    q: z.string().min(1).describe('Keyword query.'),
    limit: z.number().int().min(1).max(500).default(20).describe('Max object IDs to return.'),
  }),
  output: z.object({
    total: z.number().int().describe('Total matching objects.'),
    objectIDs: z.array(z.number().int().describe('A Met object ID.')).describe('Matching IDs.'),
    returned: z.number().int().describe('Count of IDs in this response.'),
    truncated: z.boolean().describe('True when total > returned.'),
  }),

  async handler(input, ctx) {
    const result = await getMetService().search({ q: input.q, limit: input.limit }, ctx);
    ctx.log.info('Met search', { q: input.q, total: result.total });
    return result;
  },

  // format() populates content[] — the markdown twin of structuredContent.
  // Different clients read different surfaces (Claude Code → structuredContent,
  // Claude Desktop → content[]); both must carry the same data.
  // Enforced at lint time: every field in `output` must appear in the rendered text.
  format: (result) => [{
    type: 'text',
    text: `**Total:** ${result.total} | **Returned:** ${result.returned}${result.truncated ? ' (truncated)' : ''}\n\n${result.objectIDs.join(', ')}`,
  }],
});