OpenBudget MCP Server
Provides access to Israel's OpenBudget API, allowing users to query and search various government budget datasets including budget items, contracts, and support payments.
README
OpenBudget MCP Server
An MCP server that provides access to the OpenBudget API, allowing you to query and search various budget-related datasets.
Description
This project provides a FastMCP server that interfaces with Israel's OpenBudget data.</br> Allowing easy access to budget data, contracts, and supports information.</br> It serves as a bridge between the OpenBudget API and MCP clients.
This project is possible only thanks to amazing work of OpenBudget/BudgetKey team.</br> See their UsingTheAPI for more details about the API used in this MCP server.</br> If you wish to craft your own queries or tool you can use their Redash to test them (You can see my queries in ILBudgetServer.py).
Features
- Full access to Israel's governmental budget data
- Real-time integration with the OpenBudget API
- Comprehensive search capabilities across multiple data categories
- Historical budget tracking and analysis
- Contract and support payment information retrieval
- Easy-to-use MCP interface for client applications
Requirements
- Python 3.10 or higher
- uv package manager
Installation
git clone <repository-url>
cd OpenBudget-mcp
uv venv
.venv\Scripts\activate
uv pip install -r pyproject.toml
uv lock
Usage
Install and run the server using one of these methods:
-
For use with Visual Studio Code (using Copilot):</br> Go to vscode/mcp.json and replace {YOUR-LOCAL-PATH} with the path you cloned the repo.</br> VSCode should discover you server automatically.</br> If that doesn't work, make sure you enabled MCP & MCP.Discovery in vscode://settings/mcp.</br> Make sure to enable agent mode in your vscode copilot.</br>

-
For use with Claude AI Assistant:
fastmcp install server.py
- For testing with MCP Inspector (Learn how at MCP Inspector):
fastmcp dev server.py
Available Datasets
The following datasets are available:
- budget_items_data
- income_items_data
- supports_data
- contracts_data
- entities_data
- budgetary_change_requests_data
- budgetary_change_transactions_data
MCP Tools
get_dataset_info
Get information about a dataset's structure, including its columns and database schema.
search_dataset
Perform a full-text search within a dataset.
query_dataset
Execute SQL queries on a dataset.
MCP Resources
available_datasets
Get a list of all available datasets.
Error Handling
The tools will return appropriate error messages in the following cases:
- Invalid dataset name
- Invalid SQL query
- API request failures
- Network connectivity issues
API Documentation
The server is based on the OpenBudget API. For more details about the API endpoints and data structure, refer to the OpenAPI specification in budgetkey.yaml.
Contributing
We welcome contributions to help improve the DataGov Israel MCP server.</br> Whether you want to add new tools, enhance existing functionality, or improve documentation, your input is valuable.
For examples of other MCP servers and implementation patterns, see the Model Context Protocol servers repository.
License
This project is dual-licensed under:
- MIT License
- Creative Commons Attribution-ShareAlike 4.0 International License
See the LICENSE file for details.
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。