ckan-mcp-server
Enables browsing and managing CKAN data portals through MCP-compatible clients like Claude Desktop.
README
CKAN MCP Server
A Model Context Protocol (MCP) server for the CKAN API that enables browsing and managing CKAN data portals through MCP-compatible clients.
What is this?
This is an MCP server that provides access to CKAN (Comprehensive Knowledge Archive Network) APIs through the Model Context Protocol. It can be used with MCP-compatible clients like Claude Desktop, IDEs, or other AI applications to interact with CKAN data portals.
Requirements
- Python 3.13 or higher
- pip (Python package installer)
Installation
- Install Python dependencies:
pip install -r requirements.txt
Configuration
Set the following environment variables:
CKAN_URL: The base URL of your CKAN portal (e.g.https://demo.ckan.org)CKAN_API_KEY: (Optional) Your CKAN API key for write operations
Example:
export CKAN_URL="https://demo.ckan.org"
export CKAN_API_KEY="your-api-key-here"
You can also copy .env.example to .env and set your configuration there.
Usage
Running the server directly
python mcp_ckan_server.py
Using Docker
# Build the image
docker build -t ckan-mcp-server .
# Run with environment variables
docker run -e CKAN_URL="https://demo.ckan.org" -e CKAN_API_KEY="your-key" ckan-mcp-server
Using Docker Compose
# Copy environment file and configure
cp .env.example .env
# Edit .env with your settings
# Run the server
docker-compose up
Available Tools
The MCP server provides the following tools:
Packages/Datasets
ckan_package_list: List all packagesckan_package_show: Show details of a specific packageckan_package_search: Search for packages
Organizations
ckan_organization_list: List all organizationsckan_organization_show: Show organization details
DataStore
ckan_datastore_searchSearch DataStore Tables by Resource
Groups and Tags
ckan_group_list: List all groupsckan_tag_list: List all tags
Resources
ckan_resource_show: Show resource details
System
ckan_site_read: Site informationckan_status_show: Status and version information
Examples
Search packages
{
"tool": "ckan_package_search",
"arguments": {
"q": "climate data",
"rows": 5,
"sort": "score desc"
}
}
Show organization
{
"tool": "ckan_organization_show",
"arguments": {
"id": "sample-organization",
"include_datasets": true
}
}
List all tags
{
"tool": "ckan_tag_list",
"arguments": {}
}
Resources
The server also provides the following resources:
ckan://api/docs: API documentationckan://config: Server configuration
Using with MCP Clients
Claude Desktop
Add this to your Claude Desktop configuration file:
{
"mcpServers": {
"ckan": {
"command": "python",
"args": ["/path/to/mcp_ckan_server.py"],
"env": {
"CKAN_URL": "https://demo.ckan.org",
"CKAN_API_KEY": "your-api-key-here"
}
}
}
}
Other MCP Clients
The server communicates via stdio, so any MCP-compatible client can connect to it by running the Python script and communicating through standard input/output.
CKAN API Reference
This MCP server implements the main endpoints of the CKAN API v3. Complete documentation: https://docs.ckan.org/en/latest/api/
License
Mozilla Public License Version 2.0
Author
(C) 2025, Ondics GmbH, https://ondics.de
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。