Furikake
A local CLI & API for MCP management that allows users to download, install, manage, and interact with MCPs from GitHub, featuring process state management, port allocation, and HTTP API routes.
README
🍃 Furikake (or furi) (WIP)
Furikake is an easy to use, local CLI & API for MCP management.
- Download MCPs [from GitHub]
- Fully featured CLI (with pretty loading)
- HTTP API Routes (uses Bun http, stdio to http, clear and standard routes)
- Process state management [with PM2]
- Logs for each process
- Uses npm to configure and run an MCP
- Built with Bun and Typescript
- is good with rice
Supports MCP's built with Typescript/Javascript;
Installation (macOS/Linux)
curl -fsSL https://bun.sh/install | bash
How to use
Manage MCPS
Furikake works with any public github repo as follows:
furi add <author/repo>
eg. furi add smithery-ai/mcp-fetch
Delete an MCP
furi delete <author/repo>
eg. furi delete smithery-ai/mcp-fetch
List installed MCPs
Show all installed MCPs
furi list
Start an MCP
furi start <author/repo> -e <env>
-e env is optional and dependant on the MCP server downloaded, in order to view the env variables for an MCP, use:
furi env <author/repo>
Stop an MCP
furi stop <author/repo>
Restart an MCP
furi restart <author/repo>
Check the status of an MCP
furi status <author/repo>
List all running MCPs
furi status all
Call a running MCP
furi call <author/repo> <method> <data>
Using the HTTP API
- Any MCP that is running, will automatically have an http route.
- Turning an MCP on/off can only be done via the cli.
To access your MCP's via http, you can turn on the proxy via:
furi http on
To turn off the route, you can use:
furi http off
Routes
- /api/status (to get a list of all running MCPs)
- /api/tools (to get a list of all available tools for all MCPs that are online)
- /api/
mcp-name/status - /api/
mcp-name/restart - /api/
mcp-name/logs - /api/
mcp-name/tools (to get a list of all available tools for the defined MCP)
mcp-name is either author/repo or alias.
Closing notes
If you've made it this far, I hope you find Furikake useful and time saving. I built this for fun as a way for me to work with MCP's more hands on. If you wish to contribute, feel free to open an issue or a pull request, I will merge it after I check out your changes.
If you think this is a good idea, please star the repo. If you think this is a bad idea, please star the repo and leave a comment.
Also check out Bun if you haven't already!
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。