Skip to main content
Glama
y0mulab

japan-ir-search

by y0mulab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
EDINET_API_KEYYesEDINET API Subscription-Key

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_filingsA

有価証券報告書のテキストを全文検索します。

Args:
    query: 検索クエリ（例: "半導体 サプライチェーン リスク"）
    section: セクション指定（risk_factors, md_and_a, business_overview,
             corporate_governance, financial_summary, full_text）
    company: 企業名フィルタ（部分一致）
    limit: 最大件数（デフォルト20）

Returns:
    マッチした書類一覧（企業名、セクション、スニペット付き）
get_filing_sectionA

書類の特定セクション全文を取得します。

Args:
    doc_id: EDINET書類ID（例: "S100VWVY"）
    section: セクションキー（risk_factors, md_and_a, business_overview,
             corporate_governance, financial_summary, full_text）

Returns:
    セクションの全文テキストとメタデータ
list_indexed_companiesA

インデックス済み企業の一覧を取得します。

Args:
    query: 企業名フィルタ（部分一致、省略で全企業）
    limit: 最大件数

Returns:
    企業一覧（EDINETコード、証券コード、企業名、書類数）
get_index_statsA

検索インデックスの統計情報を取得します。

Returns:
    インデックス済み書類数、企業数、総文字数等
compare_sectionsA

2つの書類の同一セクションを比較します（例: 前期 vs 当期のリスク記述）。

Args:
    doc_id_1: 比較元の書類ID
    doc_id_2: 比較先の書類ID
    section: セクションキー（デフォルト: risk_factors）

Returns:
    両方のテキスト、文字数差分、新出キーワード、消失キーワード

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct operation: full-text search, section retrieval, company listing, index statistics, and section comparison. No two tools have overlapping purposes, making selection unambiguous.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (search_filings, get_filing_section, list_indexed_companies, get_index_stats, compare_sections). The naming is uniform and predictable.

Tool Count5/5

With only 5 tools, the server is well-scoped for its purpose of searching and comparing Japanese securities filings. Each tool provides a distinct capability without unnecessary bloat or missing essentials.

Completeness4/5

The core search and retrieval lifecycle is covered, including full-text search, section fetching, and comparison. A minor gap exists: there is no direct way to list all filings for a company without a search query, but this can be worked around by using a broad search.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources