eRegulations MCP Server

@unctad-ai

eRegulations MCP Server について

概要はまだありません

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "eregulations-mcp-server-unctad-ai": {
      "command": "docker",
      "args": [
        "pull",
        "ghcr.io/unctad-ai/eregulations-mcp-server:latest"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is eRegulations MCP Server?

A Model Context Protocol (MCP) server that provides structured, AI-friendly access to eRegulations API data. It enables AI models to answer user questions about administrative procedures by querying procedures, steps, requirements, and costs from eRegulations instances.

How to use eRegulations MCP Server?

Run the server with Docker, setting the required environment variable EREGULATIONS_API_URL to the target eRegulations API base URL. The server listens for MCP JSON requests on standard input and sends responses to standard output. Alternatively, install via Smithery (preferred) or use the now-deprecated npx command.

Key features of eRegulations MCP Server

Access eRegulations data through a standardized MCP protocol
Query procedures, steps, requirements, and costs
MCP prompt templates to guide LLM tool usage
Streamlined implementation using standard I/O connections
Four built-in tools: listProcedures, getProcedureDetails, getProcedureStep, searchProcedures

Use cases of eRegulations MCP Server

AI assistants answering citizens’ questions about administrative procedures
Integrating eRegulations data into conversational agents and chatbots
Automating retrieval of procedure details, requirements, and costs for reporting
Searching procedures by keyword to find relevant administrative steps

FAQ from eRegulations MCP Server

What configuration is required to run the server?

You must set the EREGULATIONS_API_URL environment variable to the base URL of the eRegulations API you wish to connect to (e.g., https://api-tanzania.tradeportal.org).

How is the server typically deployed?

The recommended method is using a published Docker image from GitHub Container Registry (GHCR). The npm-based npx method is deprecated due to potential environment inconsistencies.

What tools does the server provide?

It provides four tools: listProcedures, getProcedureDetails, getProcedureStep, and searchProcedures. Each accepts parameters like procedureId, stepId, or keyword.

What are MCP prompt templates and why are they useful?

The server includes prompt templates that guide LLMs in using the available tools correctly. Client applications that support MCP prompt templates automatically receive these instructions, improving the AI’s ability to interact with the eRegulations API.

Does the server have any known limitations regarding search?

The searchProcedures tool currently searches related objectives based on the underlying API and may include results beyond direct procedure names.

よくある質問

What configuration is required to run the server?

You must set the `EREGULATIONS_API_URL` environment variable to the base URL of the eRegulations API you wish to connect to (e.g., `https://api-tanzania.tradeportal.org`).

How is the server typically deployed?

The recommended method is using a published Docker image from GitHub Container Registry (GHCR). The npm-based `npx` method is deprecated due to potential environment inconsistencies.

What tools does the server provide?

It provides four tools: `listProcedures`, `getProcedureDetails`, `getProcedureStep`, and `searchProcedures`. Each accepts parameters like `procedureId`, `stepId`, or `keyword`.

What are MCP prompt templates and why are they useful?

Does the server have any known limitations regarding search?

The `searchProcedures` tool currently searches related objectives based on the underlying API and may include results beyond direct procedure names.

基本情報

カテゴリ

その他

トランスポート

stdio

公開者

unctad-ai

「その他」の他のコンテンツ

ACI: Open-Source Infra to Power Unified MCP Servers

aipotheosis-labs

ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.

4.8K