jgrants-mcp-serverofficial
A
licenseNot graded
qualityD
maintenanceMCP server for Japan's Jグランツ grant application system, enabling LLMs to search and retrieve subsidy information via natural language.
50
MIT
Japan Subsidy Search MCP
by easakura
Japan Subsidy Search MCP — 日本の補助金・助成金検索
Give your AI agent real-time access to Japanese government subsidies and grants.
This MCP server searches the official Japanese government subsidy database (jGrants, operated by the Digital Agency) in real time. Perfect for AI agents serving SMEs, accountants, administrative scriveners (行政書士), and consultants working with the Japanese market.
Why this server?
Japan runs thousands of subsidy programs — national, prefectural, and municipal — but the data is fragmented and Japanese-only. Foreign AI tools are effectively blind to it. This server makes the entire live database queryable by any MCP-compatible agent (Claude, ChatGPT, custom agents).
Related MCP server: @localgov-jp/mcp-server
Tools
search_subsidies
Search open subsidy programs by keyword and prefecture. Returns results sorted by application deadline with:
Days until deadline (computed automatically)
Maximum grant amount (formatted, e.g. "5億円" / "3,500万円")
Direct link to the official application page
When a prefecture filter yields zero hits, automatically reports matching programs in other regions so your agent can offer alternatives
get_subsidy_detail
Retrieve full details by subsidy ID: purpose, eligibility requirements, subsidy rate, application rounds with current deadlines, and contact information — converted from rich-text HTML into clean, LLM-ready plain text.
Example queries your agent can now answer
「東京都の会社で使える省エネ補助金、締切が近い順に教えて」
"Find manufacturing subsidies open for applications in Osaka with deadlines this quarter"
「創業支援の補助金で、従業員10人以下でも申請できるものは？」
Data source & freshness
Official jGrants API (Digital Agency of Japan). Data is fetched live on every call — no stale caches. This server adds normalization, deadline computation, region merging, and LLM-friendly formatting on top of the raw government data.
Pricing
Pay per tool call. One search or one detail retrieval = one event. No subscription, no minimum.
日本語
日本政府公式の補助金データベース（デジタル庁 jGrants）をAIエージェントからリアルタイム検索できるMCPサーバーです。締切までの残り日数計算、地域限定＋全国対象の自動マージ、AIが読みやすい整形済みテキストを提供します。士業・中小企業支援・コンサルティング向けAIに最適です。
Get started
This is a hosted (remote) MCP server, available on Apify Store:
👉 https://apify.com/e-asakura/japan-subsidy-search-mcp
The store page includes setup instructions for Claude, ChatGPT, Cursor, and any MCP-compatible client. Pay-as-you-go: $0.02 per tool call, no subscription.
Built by Edward Asakura — Japanese data infrastructure for AI agents. Part of the SEKISHO series: subsidies / laws / parliament.
Available Tools
2 toolsget_subsidy_detail補助金の詳細を取得A
補助金IDを指定して、目的・応募資格・補助率・応募期間・問い合わせ先などの詳細情報を取得する。IDはsearch_subsidiesの結果に含まれる。
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | 補助金ID（例: a0WJ200000CDczHMAT） |
TDQS
A4/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It indicates a read operation returning details, but lacks disclosure on idempotency, authorization needs, or potential errors. Minimal beyond the core function.
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 concise sentences, front-loaded with purpose. No wasted text.
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 simple input (one param) and no output schema, the description covers essential context: what is retrieved and where ID comes from. Could mention return format but not necessary.
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 coverage is 100% with a well-described id parameter. Description does not add extra meaning beyond the schema, so baseline score of 3 is appropriate.
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?
Description explicitly states '取得する' (obtain) and lists specific details like purpose, eligibility, subsidy rate, etc. It clearly distinguishes from sibling search_subsidies by referencing that IDs come from its results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage context: use after search_subsidies to get details. It mentions the ID source, but doesn't explicitly exclude scenarios or mention when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_subsidies日本の補助金・助成金を検索A
日本政府の公式データベース（jGrants）から補助金・助成金をリアルタイム検索する。募集中の案件を締切が近い順に返す。都道府県を指定すると、その地域限定の補助金と全国対象の補助金の両方を返す。各結果には申請ページURL・上限額・締切までの残り日数が含まれる。
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | 検索キーワード（2文字以上。例: IT導入 / 省エネ / 創業 / 賃上げ / 観光） | |
| prefecture | No | 都道府県名で絞り込み（例: 東京都 / 大阪府）。省略時は全地域 | |
| max_results | No | 最大件数（1〜50） | |
| only_accepting | No | trueなら現在募集中の案件のみ（デフォルト）。falseで過去・予定分も含む |
TDQS
A4.5/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
動作の特性をよく開示：リアルタイム性、締切順ソート、都道府県フィルタの挙動、結果に含まれる情報。アノテーションがない中で、読み取り専用であることは暗黙的に理解できる。
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?
3文で本質を過不足なく伝える。各文が目的、動作、返却内容をカバーし、無駄がない。
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
出力スキーマがない中で、各結果に含まれる情報（URL、上限額、残り日数）を明示。ソート順やフィルタ挙動も説明し、検索ツールとして完結。
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?
スキーマカバレッジ100%だが、説明は都道府県パラメータの挙動（地域限定＋全国）や締切順ソートの補足を追加しており、スキーマ以上の価値を提供。
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?
明確な動詞「リアルタイム検索する」とリソース「補助金・助成金」、データベース「jGrants」を特定。兄弟ツールget_subsidy_detail（詳細取得）と明確に区別される。
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
募集中の案件を締切順に返すと明示。都道府県指定時の挙動（地域＋全国両方）を説明。代替ツールへの言及はないが、兄弟ツール名から検索と詳細の使い分けが推察可能。
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.
2 tool updates
v0.1.0- First observed
get_subsidy_detail - First observed
search_subsidies
TDQS
A4.2/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: search_subsidies for finding subsidies and get_subsidy_detail for retrieving details by ID. No overlap in functionality.
Naming Consistency5/5
Both tools use a consistent verb_noun snake_case pattern (search_subsidies, get_subsidy_detail), which makes the naming predictable and easy to understand.
Tool Count3/5
With only 2 tools, the server is minimal but still functional for its core purpose of search and detail retrieval. It could benefit from additional tools like filtering or listing categories.
Completeness4/5
The tool surface covers the essential search and detail retrieval operations for Japanese subsidies. Minor gaps exist, such as lack of filtering by amount or category, but the core workflow is complete.
Maintenance
ActivityStale
ResponsivenessNo issues
Related MCP Connectors
Search Japanese subsidies and public company data using J-Grants, gBizINFO, and EDINET.
Japan central + municipal subsidies (20,810 grants, 1,627 munis). 8 tools beyond Jグランツ MCP.
Japanese public-sector business opportunities for AI agents: tenders, subsidies, sanctions. x402.
Search Japanese company credit, financials, subsidies, and procurement via AI agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that provides access to Japan's central and municipal subsidies, covering over 20,000 municipal grants not exposed by official APIs, with tools for search, comparison, citation verification, and practitioner referrals.1350MIT
- AlicenseNot gradedqualityDmaintenanceExposes deadline-driven Japanese public-sector business opportunity data (tenders, subsidies, sanctions) to AI agents, with per-call payment via the x402 protocol.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables LLMs to search and retrieve Japanese government subsidy and grant information via natural language, wrapping the Jグランツ public API.MIT
