eur-lex-mcp-server

---

Overview

EU legislation, CJEU case law, and treaties from EUR-Lex. Search documents and case law, fetch full text, resolve citations, trace how acts amend and cite each other, and browse the EuroVoc subject thesaurus.

Tools

Tool	Description
eurlex_search_documents	Search EU legislation, treaties, and preparatory acts by type, date, EuroVoc subject, author institution, and in-force status
eurlex_get_document	Fetch metadata (including ELI, Official Journal reference, and dates of effect) and full text (HTML, Markdown, or Formex4 XML) for an act or case by CELEX, ELI, or work URI, with a section outline of either
eurlex_lookup_celex	Resolve a CELEX number, ELI URI, ECLI, OJ citation (Regulation (EU) 2016/679), or Official Journal reference (OJ L 119, 4.5.2016, p. 1) to its canonical CELLAR work
eurlex_get_cases	Search CJEU and General Court case law by case number, court, case type, and date range
eurlex_get_relations	Traverse the CELLAR relationship graph — amendments, repeals, consolidations, legal basis and the works adopted under it, the proposal an act adopts, interpreting rulings (by article), citations, transpositions
eurlex_browse_subjects	Search the EuroVoc thesaurus to resolve terms to concept URIs
eurlex_query_sparql	Run a raw, read-only SPARQL SELECT against the CELLAR endpoint

Resources

Resource	Description
eurlex://document/{celexNumber}	Metadata snapshot for a CELLAR work
eurlex://document/{celexNumber}/relations	One-hop relationship summary for a CELLAR work

All resource data is also reachable via tools.

Prompts

Prompt	Description
eurlex_comparative_analysis	Frame a comparative EU/US legal analysis for a policy domain

Skills

Skill	Description
eur-lex-guide	For agents calling the tools: where each CELEX, ELI, ECLI, and case-number form comes from, the checks to run before concluding an act is in force, repealed, uninterpreted, or final, and a CELLAR SPARQL and CDM reference for eurlex_query_sparql

The skill is in skills/. Plugin installs, the .mcpb bundle, the npm package, and the Docker image include it, and the server serves it to MCP clients through the Skills extension (skills/list, skill:// resources).

---

Capability reference

eurlex_search_documents _tool

• At least one filter: keyword (English titles, plus CELEX numbers or fragments such as 2016R0679; a keyword with letters and no digit, such as R(01), scans every CELEX and can take tens of seconds; no body search), document_type (REG, DIR, DEC, TREATY, JUDG, OPIN_AG, PROP, REC), date_from/date_to, eurovoc_concept (from eurlex_browse_subjects), author_institution, or in_force (true/false; false covers repealed, expired, and not-yet-in-force acts)
• Pages of up to 100 via offset/limit (a larger limit is served at 100 and reported in limit_clamp), newest first; each row flags is_consolidated and is_corrigendum, and corrigenda and consolidated texts appear only under include_corrigenda and include_consolidated. Paging stops at row 10,000: the last page carries no next_offset and a notice giving the date_from/date_to window that continues past it
• No match returns an empty page with a notice on how to broaden the filters; typed errors: no_filters, invalid_date_range, invalid_author_institution and invalid_keyword (no letters or digits), offset_past_window (offset 10,000 or more)
• author_institution matches English authority labels and national-court names returned by eurlex_get_document, such as European Parliament or Supremo Tribunal de Justiça, with or without date bounds

---

eurlex_get_document _tool

• Exactly one of celex_number, eli_uri, or work_uri (pasted forms such as a CELEX: prefix or EUR-Lex URL are accepted); body as html (default), markdown, or xml (Formex4) in any of the 24 EUR-Lex languages, falling back to English. Case law also carries ecli, formation, referring_court, subject_matter, and case_reference; a consolidated text reports its base act as base_act_celex
• content_mode "paged" (default), "full", or "metadata_only", capped at 100,000 characters per call (a larger limit is reported in limit_clamp) with content_chars_total/has_more to page on; outline: true lists headings with offsets, and select (e.g. { articles: "1,5,17" }) returns just those sections. For judgments and AG opinions the outline lists section headings, and select: { operative_part: true } returns the ruling alone
• is_superseded flags a newer consolidated version (current_consolidated_celex, consolidated_as_of), and resolve: "current_consolidated" serves it; in_force: false comes with repealed_by, end_of_validity, or entry_into_force where CELLAR records one. Typed errors: invalid_identifier_args, not_found, content_challenge (a WAF bot-challenge in place of text)
• Citation facts, each absent when CELLAR records none: eli (a consolidated text keeps its own point-in-time ELI); oj_reference, the Official Journal reference (OJ L 119, 4.5.2016, p. 1–88; no series letter before 1968, a class letter as in OJ L 42I, OJ L, 2024/1689, 12.7.2024 for act-by-act publication), with pages from the English edition or, before 1973, the original-language editions, and the earliest issue for a reprinted act; dates_of_effect, every recorded date as { date, type? } with type one of entry_into_force, application, partial_application, provisional_application, takes_effect, takes_partial_effect; and transposition_deadlines for a directive. entry_into_force keeps its meaning of an entry still ahead on a not-in-force act. A consolidated text reports its base act's oj_reference, dates_of_effect, and transposition_deadlines
• Available legacy HTML/Markdown bodies may carry content_omissions: { tables }: missing-table markers counted across the full source, including outside the returned window. Paging cannot recover these tables. alternative_representations lists PDF streams advertised for the served work and language when discovery succeeds; XML availability remains independent. Metadata-only calls do not inspect source omissions
• National implementing measures carry sparse national_measure citation fields: journal, number, pages, publication_date, and notification_date, including metadata-only calls. Numbers and pages retain their source spelling; publication, notification, and document dates are distinct. When the body is unavailable, use the gazette citation to retrieve it; no national-portal URL is inferred, and notification does not prove complete transposition

---

eurlex_lookup_celex _tool

• A CELEX number, ELI URI, ECLI, or OJ citation naming its act type and year (Regulation (EU) 2016/679, Directive 95/46/EC, optionally followed by its parenthesized OJ reference, Directive 95/46/EC (OJ L 281, 23.11.1995, p. 31)); pasted forms (a CELEX: prefix, a EUR-Lex page URL, an ELI with or without scheme or language segment) are normalized and echoed in celex_number. A citation without its act type (95/46/EC) or year (Regulation No 17) is not parsed
• An Official Journal reference resolves to the act starting on the cited page: issue, publication date, and first page (OJ L 281, 23.11.1995, p. 31, also of 23.11.1995, a page range, a class letter as in OJ L 42I, OJ C, and before 1968 the series-less OJ 13, 21.2.1962, p. 204/62); the year-first OJ 1995 L 281, p. 31 and OJ 1995 L 281/31; and act-by-act OJ L, 2024/1689, 12.7.2024 and OJ C, C/2024/2664, 29.4.2024. A cited date must equal the issue's publication date. Pages are matched on the English edition, or on any language before 1973 when the issue has no English pages. A reference without its year or first page (OJ L 281, OJ L 119/1) is not parsed. Recognized only under auto
• identifier_type auto-detects the format or sets it; ambiguous_identifier fires when auto-detection can't classify the input (including an OJ reference without its year or first page). A case number (C-131/12) returns found: false with a notice pointing to eurlex_get_cases
• Returns work URI, confirmed CELEX number, resource type, date, and the case's ECLI; found: false with a notice for a well-formed identifier that matches no work, for an OJ reference whose date or page matches nothing, and for one whose first page starts several acts (the notice names each CELEX)

---

eurlex_get_cases _tool

• Filters: case_number (C-131/12, T-22/20, F-12/05, or a pre-1989 26/62; reaches every judgment, order, and AG opinion filed under it), court (CJEU or GC), case_type (judgment, order, ag_opinion), keyword (English titles, plus CELEX numbers or fragments such as 2013CJ0131), and date_from/date_to; primary records only unless include_derivative adds notices, abstracts, summaries, and corrigenda
• Pages of up to 100 via offset/limit (a larger limit is served at 100 and reported in limit_clamp), newest first; each case carries its ECLI where recorded, plus formation, advocate_general, display_title, parties, referring_court, subject_matter, and case_reference, and the raw title only when those fields miss part of it. Paging stops at row 10,000: the last page carries no next_offset and a notice giving the date_from/date_to window that continues past it
• No match returns an empty page with a notice on how to broaden the filters; typed errors: invalid_case_number, invalid_date_range, invalid_keyword (no letters or digits), offset_past_window (offset 10,000 or more)
• case_type: "ag_opinion" includes Advocate General opinions (OPIN_AG) and views (VIEW_AG); resource_type distinguishes AG Opinion from AG View

---

eurlex_get_relations _tool

• Exactly one of celex_number or work_uri; relation_types narrows to any of cites, amends, amended_by, repeals, repealed_by, implicitly_repeals, implicitly_repealed_by, legal_basis, basis_for, interprets, interpreted_by, consolidated_version, national_transposition, adopts, adopted_by (omit for all fifteen)
• basis_for lists the works naming the act among their legal bases; interpreted_by lists the CJEU and General Court rulings interpreting it, and interprets what a ruling interprets; adopts lists the works an act adopts (usually its Commission proposal) and adopted_by the act that adopted a work. member_states narrows national_transposition to named member states (ISO 3166-1 alpha-3 or two-letter codes, echoed as alpha-3); using it without national_transposition fails as member_states_not_applicable
• article narrows interpreted_by to rulings with a recorded provision in one article of the act (17, 6a, Article 17, Art. 17, any case; blank is omitted; a paragraph, range, or Roman numeral is rejected). It matches at any depth, ignores leading zeros, and a letter also matches its Latin ordinal (28c reaches Article 28 quater); rulings CELLAR records no provision for are left out, as the notice says, and the echoed article is the normalized form. Using it without interpreted_by fails as article_not_applicable
• Amendment, repeal, interpretation, and adoption rows carry provisions, the provisions CELLAR records the edge as targeting, in compact codes (A17P1LC is Article 17(1)(c)) or authority-token codes (AR 43 PA 4); a row without them records none, which does not mean the edge reaches the whole act. A page that cannot fit its provisions within the budget at depth 1 withholds them whole, largest first, and reports each row's count as provisions_withheld; a provisions lookup CELLAR fails returns the rows without them, named in the notice
• One hop, paged per relation type and direction via offset/limit (up to 100, default 100; a larger limit is reported in limit_clamp), newest first. Each type and direction pages to row 10,000, then a notice routes older works to eurlex_query_sparql with a ready-to-run query
• Each complete response surface is budgeted independently at 64,000 UTF-8 bytes, including JSON and enrichment. Oversize pages retain the largest common per-type/direction depth that fits, with whole rows and titles; the notice gives requested/applied limits and rows withheld. Continue at next_offset (the current offset plus the applied depth). A depth-1 page is returned whole even if it exceeds the budget, with disclosure. Fitting pages are unchanged; omitting relation_types equals listing all fifteen types
• Each relation carries relation_type, direction (outgoing/incoming), related_work_uri, and where known related_celex_number, related_date, related_title (English only), and related_member_state on national_transposition rows; empty_relation_types separates "no edges of this type" from "paged out". Typed errors: invalid_identifier_args, member_states_not_applicable, article_not_applicable, not_found, offset_past_window

---

eurlex_browse_subjects _tool

• Matches preferred and alternative EuroVoc labels, so a common synonym resolves to its concept, in any EU official language (default English); offset/limit pagination (up to 50; a larger limit is served at 50 and reported in limit_clamp), to row 10,000 (offset_past_window beyond)
• Returns concept URI, preferred label, code, broader (parent) label, and the alternative label that matched when one did; an empty page with a notice when nothing matches
• Exact label matches rank first, then label or word-start matches, then other substring matches, so "AI" leads with artificial intelligence

---

eurlex_query_sparql _tool

• Read-only SELECT only (update forms and ASK/CONSTRUCT/DESCRIBE are rejected); cdm:, skos:, and xsd: prefixes are auto-injected; optional timeout_hint (1000–55000 ms)
• Results capped at MAX_SPARQL_RESULTS (default 100); a truncated result's notice says to add ORDER BY and repeat with a higher OFFSET, up to row 10,000. A zero-row result from an untyped string literal gets a notice to type it (^^xsd:string, ^^xsd:anyURI for an ELI) or language-tag it
• Typed errors: not_read_only (a SPARQL Update), unsupported_query_form (ASK, CONSTRUCT, DESCRIBE, or no SELECT), sparql_error, sparql_timeout

---

eurlex://document/{celexNumber} _resource

• Metadata snapshot as application/json — resource type, author institution(s) labelled as eurlex_get_document labels them, Advocates General, date, English title, in-force flag, eli, oj_reference, dates_of_effect, transposition_deadlines, legal basis, EuroVoc subjects (the four citation fields as in eurlex_get_document); a consolidated text keeps its own eli, adds base_act_celex, and reads authors, in-force flag, oj_reference, dates_of_effect, transposition_deadlines, legal basis, and subjects from that act
• celexNumber comes from eurlex_search_documents, eurlex_get_cases, or eurlex_lookup_celex

---

eurlex://document/{celexNumber}/relations _resource

• One-hop relationship summary over all fifteen eurlex_get_relations types, with no provisions, each related work with its related_date and English related_title where it has them, capped at 25 per relation type and direction (newest kept)
• truncated plus a continuation pointer to eurlex_get_relations when more relations exist

---

eurlex_comparative_analysis _prompt

• Arguments: domain required; focus optional, folded into its matching analysis axis or added as its own section
• Returns a research plan that restates the domain in EU legal vocabulary ("antitrust" → "competition law"), chains eurlex_browse_subjects → eurlex_search_documents → eurlex_get_document → eurlex_get_relations for the EU side and courtlistener_search_opinions for the US side, plus a six-axis analysis framework

---

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

EUR-Lex-specific:

• No API key required — CELLAR SPARQL and the EUR-Lex REST content endpoints are both publicly accessible
• SPARQL is POSTed with CDM prefix declarations built in; server-side LIMIT enforcement (max 100) guards against Virtuoso timeouts
• Act text is fetched via CELLAR content negotiation; HTML passes through as served, multi-part Formex4 XML is assembled into one document, and Markdown is converted server-side
• Syntax, compile, and sort-window errors fail at once as sparql_error (a sort-window error, SR353, hints to lower OFFSET or narrow the query) and timeouts as sparql_timeout, neither retried; gateway pages and other transient failures are retried inside the call's shared query budget (SPARQL_QUERY_TIMEOUT_MS), and a retry ladder the budget cuts short reports the last attempt's own failure
• Automatic English fallback when a requested translation is unavailable, with requested/effective language reported

Agent-friendly output:

• EuroVoc prerequisite guidance in server-level instructions — agents are directed to eurlex_browse_subjects before concept-filtered searches
• eurlex_lookup_celex confirms CELEX/ELI/ECLI existence upfront, preventing downstream errors in document or relation fetches
• content_status, content_unavailability_reason, and requested/effective language fields distinguish skipped, available, absent, upstream-failed, and incomplete content without string parsing
• Typed reason codes on every tool's error contract let agents branch on outcomes programmatically

---

Getting started

Connect to the hosted instance, no install:

claude mcp add --transport http eur-lex-mcp-server https://eur-lex.caseyjhand.com/mcp

Or run it locally:

claude mcp add eur-lex-mcp-server -- npx -y @cyanheads/eur-lex-mcp-server

For other clients, add this to the MCP config file:

{
  "mcpServers": {
    "eur-lex-mcp-server": {
      "command": "npx",
      "args": ["-y", "@cyanheads/eur-lex-mcp-server"]
    }
  }
}

No API key is required. For Docker or a source build, see Running the server.

---

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts.

Variable	Description	Default
CELLAR_SPARQL_ENDPOINT	CELLAR SPARQL endpoint URL override (e.g., for a local Virtuoso mirror).	http://publications.europa.eu/webapi/rdf/sparql
EURLEX_CONTENT_BASE_URL	EU Publications Office CELLAR content resolver base URL override.	http://publications.europa.eu
SPARQL_QUERY_TIMEOUT_MS	Client-side timeout in milliseconds, an integer from 1 to 2147483647: the budget a call's CELLAR queries share (a call that chains queries spends it once, not per query) and the ceiling on any single query; an EUR-Lex content fetch gets its own timeout of this length, outside the shared budget.	55000
MAX_SPARQL_RESULTS	Enforced ceiling on LIMIT in all generated SPARQL queries.	100
MCP_TRANSPORT_TYPE	Transport: stdio or http.	stdio
MCP_HTTP_PORT	Port for HTTP server.	3010
MCP_AUTH_MODE	Auth mode: none, jwt, or oauth.	none
MCP_SESSION_MODE	Session handling: stateful, stateless, or auto (auto resolves to stateful).	stateless
MCP_LOG_LEVEL	Log level (RFC 5424).	info
LOGS_DIR	Directory for log files (Node.js only).	<project-root>/logs
LOG_TOOL_FAILURE_PAYLOADS	Log failed tool calls' arguments and result, redacted by key name (free-form values are not), capped at LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES (default 16384).	false
OTEL_ENABLED	Enable OpenTelemetry instrumentation.	false

See .env.example for the full list of optional overrides.

---

Running the server

Local development

Requires Bun v1.4.0 or higher (or Node.js v24+).

• Clone and install:

  git clone https://github.com/cyanheads/eur-lex-mcp-server.git
  cd eur-lex-mcp-server && bun install
  cp .env.example .env   # optional: every variable has a default
  

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http   # listens at http://localhost:3010/mcp
  

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker run --rm -p 3010:3010 ghcr.io/cyanheads/eur-lex-mcp-server:latest

The image defaults to HTTP transport, stateless session mode, and logs to /var/log/eur-lex-mcp-server. To run it over stdio from an MCP client, use "command": "docker" with "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/eur-lex-mcp-server:latest"]. To build locally, docker build -t eur-lex-mcp-server . then docker run --rm -p 3010:3010 eur-lex-mcp-server; OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

---

Project structure

Directory	Purpose
src/index.ts	createApp() entry point — registers tools, resources, prompts, and the published skills; initializes services.
src/config	Server-specific environment variable parsing and validation with Zod.
src/services/cellar-sparql	CELLAR SPARQL service — POST client, binding mapper, LIMIT enforcement, CDM PREFIX declarations.
src/services/eurlex-content	CELLAR content service — content-negotiation GET client for /resource/celex/{CELEX} (Accept / Accept-Language) with English language fallback, and an in-process cache of served bodies so paging an act fetches it once.
src/mcp-server/tools	Tool definitions (*.tool.ts). Seven tools across document search, retrieval, resolution, case law, relations, EuroVoc, and raw SPARQL.
src/mcp-server/resources	Resource definitions (*.resource.ts). Metadata and relations resources.
src/mcp-server/prompts	Prompt definitions (*.prompt.ts). Comparative analysis prompt.
skills/	Agent Skills published to the agents that call the tools (eur-lex-guide).
tests/	Unit and integration tests mirroring src/.

---

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Register new tools and resources via the barrels in src/mcp-server/*/definitions/index.ts
• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

---

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

---

License

Apache-2.0 — see LICENSE for details.