Skip to main content
Glama
deenesjakoruzh
joshua-bailey

eiu-mcp-server

by joshua-bailey
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

eiu-mcp-server

Model Context Protocol サーバー。Claude(または MCP 互換の LLM クライアント)に、EIU データ API への構造化された、トークン効率の高いアクセスを提供します。約200か国、320の経済指標シリーズ、履歴と予測をカバーしています。

以下の3つのツールを公開しています:

ツール

目的

eiu_browse

利用可能な地域とシリーズを一覧表示。キーワードでフィルタリング可能

eiu_search

シリーズカタログ全体をキーワード検索(例:"current account")

eiu_get_data

国とシリーズコードでデータを取得。頻度と日付のフィルター付き

リファレンスデータはセッションごとに1回取得され、メモリにキャッシュされるため、ブラウズと検索では追加の API 呼び出しは発生しません。

前提条件

  • EIU API Developer Portal へのアクセス。 セルフサービスではありません。economicssupport@economist.com にメールで Developer Portal へのアクセスをリクエストしてください。アカウントは手動で設定されます。ポータルのメールアドレス、ポータルのパスワード、ポータルに表示されている API キーの3つすべてが必要です。

  • マシンに uv がインストールされていること。ワンライナー:

    curl -LsSf https://astral.sh/uv/install.sh | sh

このリポジトリをクローンしたり、仮想環境を管理したりする必要はありません。uvx が git URL からすべてを処理します。

Related MCP server: EODHD MCP Server

インストール

Claude Code

ワンラインインストールは、.env に EIU の3つの値が含まれるフォルダーから実行します。シェルが値を読み取るため、認証情報が会話に表示されることはありません:

set -a; source .env; set +a
claude mcp add --scope user eiu \
  -e EIU_API_KEY="$EIU_API_KEY" \
  -e EIU_EMAIL="$EIU_EMAIL" \
  -e EIU_PASSWORD="$EIU_PASSWORD" \
  -- uvx --from git+https://github.com/joshua-bailey/eiu-mcp-server.git eiu-mcp-server

または、.mcp.json にエントリを手動で追加します:

{
  "mcpServers": {
    "eiu": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/joshua-bailey/eiu-mcp-server.git",
        "eiu-mcp-server"
      ],
      "env": {
        "EIU_API_KEY": "${EIU_API_KEY}",
        "EIU_EMAIL": "${EIU_EMAIL}",
        "EIU_PASSWORD": "${EIU_PASSWORD}"
      }
    }
  }
}

その後、Claude Code を再起動します。3つの eiu_* ツールが /mcp の下に表示されるはずです。

Claude Desktop

同じ JSON スニペットを、次の場所の mcpServers の下に配置します:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Claude Desktop は ${VAR} 参照を展開しないため、代わりにリテラル値をそこに記述してください。

バージョンの固定

uvx はデフォルトで main の最新コミットをインストールします。タグ付きリリースに固定するには、git URL の末尾に @<tag> を追加します。例:

"git+https://github.com/joshua-bailey/eiu-mcp-server.git@v0.1.0"

環境変数

変数

必須？

目的

EIU_API_KEY

はい

Developer Portal から取得した EIU API キー。

EIU_EMAIL

はい

ポータルアカウントで使用するメールアドレス。

EIU_PASSWORD

はい

ポータルのパスワード。

3つすべてが必要です。サーバーはメールアドレスとパスワードでログインしてベアラートークンを取得し、そのトークンを API キーとともに毎回のリクエストで送信します。トークンはメモリにキャッシュされ、期限が切れる前に更新されます。

使い方

MCP が登録されると、Claude に次のようなことを依頼できます:

  • 「EIU で経常収支のシリーズを検索して」

  • 「消費者物価をカバーする EIU のシリーズコードはどれ？」

  • 「2015年から2030年までの米国、英国、中国の EIU 年間 GDP 成長率 (DGDP) を取得して」

  • 「ブラジル、メキシコ、チリの EIU 四半期インフレ予測を見せて」

Claude が適切なツールを選択して呼び出します。

コード

  • 地域 (Geographies) は大文字の ISO 2文字コード:US、GB、CN、BR。

  • シリーズ (Series) は大文字の EIU 独自の短いコード。例:DGDP、DCPI。推測せずに eiu_search または eiu_browse で見つけてください。

  • 頻度 (Frequency) は Yearly、Quarterly、Monthly のいずれかです。

eiu_get_data はトークン効率を維持するため、レスポンスを200データポイントに制限し、切り詰めた場合にはその旨を通知します。残りを確認するには、日付範囲または国リストを絞り込んでください。

API リファレンス

基盤となる API は developer.eiu.com/help/overview に文書化されています。サーバーは https://api.eiu.com/v1 と通信します。

ライセンス

MIT — LICENSE を参照してください。このリポジトリ内のラッパーコードにのみ適用されます。依存関係はそれぞれ独自のライセンスを保持します。EIU データは有料サブスクリプションであり、その利用規約はこのラッパーとは独立して適用されます。

Available Tools

3 tools
eiu_browseA

Browse available EIU geographies and data series.

Call with no filter to see all available geographies/series. Use filter to narrow results by keyword.

Args: filter: Optional keyword (e.g. 'Brazil', 'GDP', 'inflation') show: 'geographies', 'series', or 'both' (default)

NameRequiredDescriptionDefault
showNoboth
filterNo

Output Schema

NameRequiredDescription
resultYes

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden. It explains what happens with no filter versus with a filter and describes the show options. It does not mention output format or pagination, but the presence of an output schema reduces the need for that detail.

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?

The description is compact and well-organized: a summary line, short usage guidance, and a clean args list. Every sentence contributes value, with no repetition or filler.

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?

For a simple two-parameter browse tool, the description is complete. It covers all parameters, defaults, and core behavior, and the output schema exists to document return values. The lack of explicit sibling routing is the only minor omission, but the intended use is clear.

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

Parameters5/5

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

Schema coverage is 0%, and the description fully compensates. It defines filter as an optional keyword with concrete examples, and show as selecting 'geographies', 'series', or 'both' with the default noted. This is meaningful semantic content beyond the bare schema.

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 opens with a specific verb and resource: 'Browse available EIU geographies and data series.' This clearly distinguishes it from siblings like eiu_get_data and eiu_search, which presumably retrieve or search data rather than browse the catalog.

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?

The description gives clear operational context: 'Call with no filter to see all available geographies/series. Use filter to narrow results by keyword.' It explains how to use the tool and the effect of each parameter, though it does not explicitly state when to prefer eiu_search or eiu_get_data.

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

eiu_get_dataA

Fetch EIU forecast/indicator data by country and series codes.

Use eiu_browse or eiu_search first to find valid codes.

Args: geography_codes: ISO 2-char codes (e.g. ['US', 'BR', 'CN']) series_codes: EIU series codes (e.g. ['DGDP', 'DCPI']) frequency: 'Yearly', 'Quarterly', or 'Monthly' min_date: Start date YYYY-MM-DD (default: 5 years ago) max_date: End date YYYY-MM-DD (default: 5 years ahead)

NameRequiredDescriptionDefault
max_dateNo
min_dateNo
frequencyNoQuarterly
series_codesYes
geography_codesYes

Output Schema

NameRequiredDescription
resultYes

TDQS

A4.8/5.0
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 clearly implies a read-only fetch operation, states the prerequisite of finding valid codes first, and documents default date ranges and accepted frequency values. It could add error/rate-limit behavior, but the default date behavior and non-destructive nature are usefully conveyed.

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?

The description is compact and well-structured. The high-level purpose is front-loaded, the prerequisite is stated in a single sentence, and the Args block is clean and easy to scan. No sentence is wasted or redundant.

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?

Given the tool has an output schema, return-value documentation is not needed. The description covers all five parameters, provides valid examples, explains the required discovery workflow, and states defaults. Everything an agent needs to invoke the tool correctly is present.

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

Parameters5/5

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

Schema description coverage is 0%, so the description fully compensates. It explains every parameter: ISO 2-char geography codes with examples, EIU series codes with examples, allowed frequency values, and date format/defaults for min_date and max_date. This is far beyond the bare schema.

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 uses a specific verb ('Fetch') and a specific resource ('EIU forecast/indicator data') with clear scope by country and series codes. This distinguishes it well from the sibling tools eiu_browse and eiu_search, which are for finding codes rather than retrieving data.

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

Usage Guidelines5/5

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

It explicitly explains the intended workflow: use eiu_browse or eiu_search first to find valid codes, then call this tool. This is clear guidance on when to use this tool versus the alternatives, leaving no ambiguity for the agent.

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. 3 tool updatesv0.1.0
    • First observedeiu_browse
    • First observedeiu_get_data
    • First observedeiu_search
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

A4.1/5.0

Scored across 3 tools

Disambiguation3/5

eiu_browse and eiu_search both support keyword-based series discovery, so agents may be unsure which to call when looking up series codes. eiu_browse is broader because it also covers geographies, while eiu_search is narrowly focused on series, but the boundary is somewhat blurred. eiu_get_data is clearly distinct.

Naming Consistency4/5

All tools share the eiu_ prefix and use lower_snake_case, making the naming pattern predictable. However, eiu_browse and eiu_search are bare verbs while eiu_get_data is verb_noun, which is a minor inconsistency.

Tool Count4/5

Three tools is a reasonable, compact set for a browse/search/fetch data workflow. The count is appropriate, though eiu_browse and eiu_search overlap enough that the set could arguably be reduced to two tools.

Completeness4/5

The core workflow of discovering geographies and series, then fetching EIU data, is covered without dead ends. Minor gaps exist around metadata details or available date ranges, but agents can complete the primary task effectively.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • econstats-mcp

    joshfwaldman1
    A
    license
    Not graded
    quality
    D
    maintenance
    Economic data MCP server that connects FRED, BLS, BEA, IMF, World Bank, and ECB to any MCP-compatible client, with built-in methodology rules to guide LLMs in selecting appropriate economic indicators.
    MIT
  • EODHD MCP Server by EodHistoricalData

    EODHD MCP Serverofficial

    EodHistoricalData
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables interaction with EOD Historical Data APIs, providing access to 75 read-only tools for financial data including fundamentals, news, screeners, and options via MCP transports.
    23
    MIT

  • world-bank-server

    gu-dsan6725
    F
    license
    Not graded
    quality
    D
    maintenance
    Exposes World Bank development data and country information via MCP resources and tools, enabling AI agents to query historical indicators and live API data.
    -