Skip to main content
Glama
dqj1998

Japan Company Info — MCP Server (Free Edition)

by dqj1998
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Japan Company Info — MCP Server (Free Edition)

Verified Japanese corporate data for Claude, Cursor, and any MCP client — served locally over stdio. Query EDINET statutory filings (XBRL 5-year financials), National Tax Agency 13-digit corporate numbers, major shareholders, and gBizINFO certifications/subsidies, with a built-in J-GAAP / US GAAP / IFRS mapping dictionary.

This package is the Free edition: 192 large-cap blue-chip listed companies (EDINET-listed). The full dataset — 3,193+ listed companies with complete XBRL financials, major shareholders, gBizINFO details, and 財務省 法人企業統計調査 industry benchmarks — is available as a one-time purchase at mcporb.store.

Use cases: cross-border equity analysis, KYB / due-diligence entity verification, M&A target screening, and reading Japanese filings in English without mistranslating 営業利益 (Operating Income) vs 経常利益 (Ordinary Income, a J-GAAP-only concept).

How it works

The server bundles the mcporb-runtime binary and a pre-indexed Orb (BM25 + trigram + optional dense-vector retrieval). Retrieval runs on your machine. On first launch the runtime downloads its query-embedding model (~220MB) in the background to enable the semantic vector method; until that finishes — and forever after, offline — the bm25, trigram, and auto methods work without any network access. Your queries are not sent to a third-party API by this server.

It exposes one tool:

  • search_knowledge(query, method?, top_k?) — search the corporate knowledge base. method ∈ auto (default) · bm25 (exact keyword) · trigram (fuzzy / identifier) · vector (semantic) · hybrid (RRF fusion).

Related MCP server: EDINET DB MCP Server

Quick start

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "japan-company-info": {
      "command": "npx",
      "args": ["-y", "japan-company-info-mcp-bridge"]
    }
  }
}

(Before the package is published to npm, use the GitHub form: "args": ["-y", "github:dqj1998/japan-company-info-mcp-bridge"].)

Cursor

Add the same server under Settings → MCP → Add Server (command npx, args as above).

Local (from a clone)

npx .

Platform support

Bundled runtime binaries in bin/ (no external system libraries required — run on minimal/headless images):

  • macOS Apple Silicon (arm64) — mcporb-runtime-darwin-arm64

  • Linux x86-64 — mcporb-runtime-linux-x64

  • Linux arm64 — mcporb-runtime-linux-arm64

  • Windows x64 — mcporb-runtime-win32-x64.exe

Not bundled: macOS Intel (x86-64). index.js resolves mcporb-runtime-<platform>-<arch> and exits with a clear message if no matching binary is found.

Example queries

Most reliable retrieval is by corporate number or securities code (exact identifiers), then Japanese company name; English company-name search covers companies with an official English name (best-effort otherwise).

Intent

Example

By corporate number

search_knowledge("1180301018771") → Toyota Motor Corporation

By securities code

search_knowledge("72030", method="trigram") → Toyota Motor Corporation

By Japanese name

search_knowledge("トヨタ自動車", method="hybrid")

GAAP concept

search_knowledge("経常利益はUS GAAPでどう表現するか")

Coverage note: this Free edition indexes 192 blue-chip companies. Queries for companies outside that set return the closest available matches; unlock the full 3,193+ company dataset at mcporb.store.

Data sources & attribution

  • 法人番号公表サイト (National Tax Agency) — corporate registration

  • EDINET (Financial Services Agency) — 有価証券報告書 XBRL financials

  • gBizINFO (METI) — certifications, subsidies, commendations

  • 財務省 法人企業統計調査 — industry benchmarks (full edition)

Data is redistributed under each source's terms; see NOTICE.

License

Bridge code is MIT (see LICENSE). The bundled Orb data and mcporb-runtime binary are not MIT — they are licensed separately; see NOTICE.

Keywords: MCP · EDINET · Japanese GAAP · US GAAP · IFRS · Operating Income · Ordinary Income · Balance Sheet · Statutory Audit · Corporate Number · National Tax Agency · Due Diligence · Entity Verification · AML · KYB · gBizINFO · JSIC · Operating Margin · Industry Benchmark · Credit Risk

Available Tools

2 tools
get_web_ui_urlA

Get the local Web UI URL for this Orb when GUI mode is enabled

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full disclosure burden. It reveals the GUI-mode precondition but does not say what happens when GUI mode is off (error, null, empty string), nor whether any auth or state is required. For a simple read-only getter this is a moderate but real gap.

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?

A single, front-loaded sentence with no filler. The resource ('local Web UI URL for this Orb') is stated before the conditional clause, which is the right ordering.

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?

For a zero-argument getter with no output schema, the description covers the essential facts: what it returns and the condition under which it is meaningful. The remaining gap is the unspecified behavior when GUI mode is disabled, which is minor for a tool this simple.

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

Parameters4/5

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

The tool takes zero parameters, so the schema has nothing to document and there is no parameter semantics burden on the description. Baseline of 4 applies for a parameterless tool.

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

Purpose4/5

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

The description states a specific verb and resource: 'Get the local Web UI URL for this Orb'. It is unambiguous about what is returned. The only sibling, search_knowledge, is unrelated, so no explicit differentiation is needed.

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 'when GUI mode is enabled' gives an implied precondition for calling the tool, which is useful context. However, it never states what to do if GUI mode is disabled or what alternatives exist, leaving usage guidance partial.

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

search_knowledgeC

Search the japan-company-info-free knowledge base

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query
top_kNoNumber of results (default: 5)
methodNoSearch method (default: auto). 'auto': automatically picks the best available method(s). 'bm25': exact keyword match, best for precise term lookup. 'trigram': fuzzy/typo-tolerant character-level match. 'vector': semantic similarity search, best for conceptual or paraphrase queries. 'hybrid': fuses all available rankers via RRF, recommended for mixed queries.

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden, and it discloses almost nothing: no mention of read-only nature, ranking/score behavior, result freshness, index scope, or error conditions. A search is implicitly a safe read, but that is inference rather than stated behavior.

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

Conciseness4/5

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

A single tight sentence with the resource front-loaded and zero filler. It is efficient, though its brevity is partly under-specification rather than disciplined concision.

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

Completeness3/5

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

With three parameters, 100% schema coverage, and no output schema, the core contract is covered, but the description is thin for a retrieval tool: it says nothing about what a result set looks like, how top_k interacts with ranking, or when this beats other retrieval paths (e.g., web lookup). Adequate but with clear gaps.

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%, including a well-documented method enum, so the schema already explains all three parameters. The description adds no additional parameter meaning, which fits the baseline 3 when the schema does the heavy lifting.

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

Purpose4/5

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

States a specific verb (Search) and a named resource (the japan-company-info-free knowledge base), which is enough for an agent to know what it does. The only gap is that it gives no differentiation from siblings, though the sole sibling (get_web_ui_url) is unrelated, so this is minor.

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

Usage Guidelines2/5

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

The description offers no guidance on when to use this tool, when not to, or what alternatives exist. The only 'when to use' information in the whole definition lives in the schema's method enum descriptions, not in the description itself.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updates
    • First observedget_web_ui_url
    • First observedsearch_knowledge
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

B3.3/5.0

Scored across 2 tools

Disambiguation5/5

The two tools are entirely distinct: get_web_ui_url retrieves a local UI address while search_knowledge queries a knowledge base. There is no overlap and an agent can easily choose between them.

Naming Consistency5/5

Both names use a consistent snake_case verb_noun pattern (get_web_ui_url, search_knowledge). The convention is predictable and readable across the set.

Tool Count3/5

Two tools is thin for a company-information server; get_web_ui_url is incidental infrastructure rather than a domain capability. It is borderline rather than clearly mismatched.

Completeness2/5

The domain implies retrieving Japanese company details, but only a generic knowledge-base search is offered with no structured lookup, listing, or field-specific retrieval. Agents will hit dead ends for anything beyond free-text queries.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • tdnet-disclosure-mcp

    ajtgjmdjp
    A
    license
    Not graded
    quality
    A
    maintenance
    MCP server for Japan's TDnet (Timely Disclosure network). Search and retrieve timely disclosure documents from listed companies on Japanese stock exchanges.
    5
    Apache 2.0

  • EDINET DB MCP Server

    edinetdb
    A
    license
    A
    quality
    C
    maintenance
    Structured financial data for ~3,800 Japanese listed companies from EDINET regulatory filings — financials, major shareholders, segments, executive compensation, and corporate history. Remote MCP over HTTPS with OAuth 2.0, free tier.
    13
    1
    MIT

  • edinet-mcp

    reanimatedead
    A
    license
    A
    quality
    B
    maintenance
    Lets AI assistants query normalized financial statements (P/L, B/S, C/F) of 3,634 Japanese listed companies from official EDINET filings, unified across J-GAAP, IFRS, and US GAAP with English keys. Zero setup: npx -y edinet-mcp.
    4
    6 npm
    MIT