Admina MCP Server
Enables interaction with the Admina API to manage and query organizational SaaS resources including devices, user identities, service integrations, and account information across multiple services.
README
admina-mcp-server
MCP server for the Admina API.
Tools and API Documentation
- get_devices: Return a list of devices. Get Devices API
- get_identities: Return a list of identities. Get Identities API
- get_services: Return a list of services integrations that belongs to organization along with a preview of accounts. Organization Services API
- get_service_accounts: Return a list of accounts for a specific service. Get Service Accounts API
- get_people_accounts: Return a list of all SaaS accounts belonging to a person. Get People Accounts API
Configuration
To configure the admina-mcp-server, you will need the organizationId and an API key. For more details on obtaining your API key, please refer to the Getting Started Guide.
MCP Client Configuration
To configure this MCP server, add the following configuration to your mcp settings.
{
"mcpServers": {
"admina-mpc-server": {
"command": "npx",
"args": [
"-y",
"@moneyforward_i/admina-mcp-server"
],
"env": {
"ADMINA_ORGANIZATION_ID": <Organization Id>,
"ADMINA_API_KEY": <API Key>
}
}
}
}
For local set up, run yarn build:dev and set the path to the root dir.
Releasing
Preparing a release
- Bump up a package version of
package.json. A Git commit will be created automatically.
yarn version --new-version <new version>
- Push the change to the main branch as usual.
Creating a release
- Create a new release in GitHub by clicking on "Releases" and then "Draft a new release"
- Set the Tag version to a new tag
- Set the Target as main.
- Set the Release title to the tag you created, vX.Y.Z
- Click "Publish release" to save and publish your release.
- GitHub Actions workflow will be triggerd by publishing a new release and the package will be released.
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。