eur-lex-mcp-server: Instructions file for Codex

Developer Protocol

Server: eur-lex-mcp-server Version: 0.19.1 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: ^4.6.7

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.

---

What's Next?

When the user asks what's next or needs direction, suggest options based on the current project state. Common next steps:

1. Field-test definitions — exercise tools/resources/prompts with real inputs using the field-test skill, get a report of issues and pain points
2. Run the security-pass skill — audit handlers for MCP-specific security gaps: output injection, scope blast radius, input sinks, tenant isolation
3. Run devcheck — lint, format, typecheck, and security audit
4. Add tools/resources/prompts — scaffold new definitions using the add-tool, add-resource, add-prompt skills
5. Run the maintenance skill — investigate changelogs, adopt upstream changes, and sync skills after bun update --latest

Tailor suggestions to what's actually missing or stale — don't recite the full list every time.

---

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.
• Caller values reach SPARQL only through the shared guards. A tool or resource input enters a generated CELLAR query only through escapeSparqlLiteral or celexLiteral (a "…" literal), isSafeSparqlIri (a <…> IRI, checked at the schema), or keywordTitlePhrase (a bif:contains phrase), unless its schema already admits no SPARQL-significant character. tests/sparql-lexical-safety.test.ts enforces this in bun run test: it sends hostile values to every string input, nested ones included (a new input must be tested or explicitly exempted), and fails when one lands outside a well-formed literal, IRI, or phrase.
• 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.