Skip to main content
Glama
metaneutrons

German Legal MCP Server

by metaneutrons

icu:search

Search Court of Justice of the European Union decisions via InfoCuria to find case numbers, ECLI identifiers, dates, and document IDs for legal research.

Instructions

Search for decisions and opinions of the Court of Justice of the European Union (CJEU) via InfoCuria. Returns list with case numbers, ECLI, dates, and document IDs for retrieval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch term (e.g., "Pelham", "Sampling", "Urheberrecht")
languageYesLanguage code (e.g., "DE", "FR", "EN"). Default: DEDE
limitYesMaximum number of results (default: 10)

Implementation Reference

  • The handleSearch method within the IcuProvider class performs the API request to InfoCuria and formats the search results into Markdown.
    private async handleSearch(args: Record<string, unknown>): Promise<ToolResult> {
      const { query, language = 'DE', limit = 10 } = args as { query: string; language?: string; limit?: number };
    
      logger.info('Searching InfoCuria', { query, language });
    
      const response = await axios.post(SEARCH_URL, {
        searchTerm: query,
        multiSearchTerms: [],
        sortTermList: [{ sortDirection: 'DESC', sortTerm: 'ALL_DATES' }],
        pagination: { pageNumber: 0, pageSize: limit, from: 1, to: limit * 2 },
        language: language.toUpperCase(),
        tabName: 'tout_jurisprudence',
        isAllTabsRequest: false,
        isSearchExact: true,
        searchSources: ['document', 'metadata'],
        ecli: '', publishedId: '', usualName: '', logicDocId: '',
      }, { headers: HEADERS });
    
      const hits = response.data.searchHits || [];
      const markdown = hits.map((hit: Record<string, Record<string, string>>, i: number) => {
        const c = hit.content;
        return `${i + 1}. **${c.docType}, ${c.docDate}, ${c.idPublished}**\n` +
          `   - ECLI: ${c.ecli || 'n/a'}\n` +
          `   - CELEX: \`${c.celex}\`\n` +
          `   - Court: ${c.affairJurisdiction}\n` +
          `   - Logic Doc ID: \`${c.logicDocId}\``;
      }).join('\n\n');
    
      return {
        content: [{ type: 'text', text: `Found ${response.data.totalHits} results (showing ${hits.length}):\n\n${markdown}` }],
      };
    }
  • Definition and input validation schema for the 'icu:search' tool.
    {
      name: 'icu:search',
      description:
        'Search for decisions and opinions of the Court of Justice of the European Union (CJEU) via InfoCuria. ' +
        'Returns list with case numbers, ECLI, dates, and document IDs for retrieval.',
      inputSchema: z.object({
        query: z.string().describe('Search term (e.g., "Pelham", "Sampling", "Urheberrecht")'),
        language: z.string().optional().default('DE').describe('Language code (e.g., "DE", "FR", "EN"). Default: DE'),
        limit: z.number().optional().default(10).describe('Maximum number of results (default: 10)'),
      }),
    },
  • Tool call dispatching to the handler in the IcuProvider.
    if (toolName === 'icu:search') return this.handleSearch(args);
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It successfully discloses the return structure (list with case numbers, ECLI, dates, document IDs), clarifying this returns metadata rather than full documents. It does not explicitly state read-only/safe status or error behaviors, though these are reasonably implied by the search verb.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste: the first establishes scope and domain, the second specifies return values. Every word earns its place; no redundancy or filler present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the straightforward 3-parameter search operation with primitive types and no output schema, the description adequately covers purpose and return values. It could be improved by explicitly mentioning the companion retrieval tool (icu:get_document) to complete the usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing detailed descriptions for query, language, and limit. The tool description does not add parameter-specific semantics beyond this (e.g., example search strategies, valid language code constraints), meriting the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action (search), the exact resource (decisions and opinions of the CJEU), and the source system (InfoCuria). It distinguishes from siblings like arxiv (academic), dip (German parliamentary), and legis (legislation) by specifying the Court of Justice context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'document IDs for retrieval' implies this tool finds documents rather than returning full text, suggesting a separate retrieval step. However, it does not explicitly name the sibling tool (icu:get_document) or provide explicit when-to-use guidance versus other legal search tools like eul:search or rii:search.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/metaneutrons/german-legal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server