Firestore Todo List MCP Server
Enables AI assistants to manage todo lists through natural language by creating, listing, updating, completing, and deleting tasks stored in Firebase Firestore. Supports custom system prompts for personalized task management workflows.
README
Firestore Todo List MCP Server
Connect any MCP Client like Claude, Open-WebUI and others to this MCP server to manage todos via AI chat in an opinionated way.
You can simply tell the model to create_todo, list_todos, update_todo, 'complete_todo' and delete_todo
You can setup a custom system prompt as well to get customized answers.
Works very well with Claude, OpenAI and Deepseek models (paid versions). Local models in Ollama also works, but with limitations.
Data is stored on Firebase Firestore because it is "free" for personal usage, easy to run, and easy to setup.
This is an experimental project I created just for learning purposes.
Feel free to try.
Getting Started
Use the Firestore Todo MCP Server on Claude (and others)
Edit the claude_desktop_config.json or the mcp configuration file of your LLM client
{
"mcpServers": {
"firestoreTodoMcp": {
"command": "npx",
"args": [
"firestore-todo-mcp"
],
"env": {
"FIREBASE_SERVICE_ACCOUNT": "base64(serviceAccount.json)",
"FIREBASE_PROJECT_ID": "your-firebase-project-id",
"FIRESTORE_COLLECTION": "test_collection"
},
"type": "stdio"
}
}
}
Don't forget to setup your project on Firebase and to get the Firebase serviceAccount from the project's configuration.
The file content must be 'base64' encoded when passing the value to the json above.
Development Mode
1. Clone the repo
git clone https://github.com/gtoshinakano/firebase-todo-mcp.git
cd firebase-todo-mcp
2.Run Firestore emulator
Install firebase-tools cli, do firebase login, install emulators and run
firebase emulators:start --only firestore --project local-todo-dev
3.Testing on Inspector
Check if all tools are working fine, test input parameters, output params
npx @modelcontextprotocol/inspector \
-e FIRESTORE_EMULATOR_HOST=localhost:3333 \
-e FIREBASE_PROJECT_ID=local-todo-dev \
-e FIRESTORE_COLLECTION=test_collection \
tsx bin/index.ts
4. (Optional) Build and Configure Claude mcp configuration locally
{
"mcpServers": {
"firestore-todo": {
"command": "node",
"args": ["/absolute/path/to/dist/bin/index.js"],
"env": {
"FIRESTORE_EMULATOR_HOST": "localhost:3333",
"FIREBASE_PROJECT_ID": "local-todo-dev",
"FIRESTORE_COLLECTION": "test_collection"
}
}
}
}
5. Create a project with a system prompt from the example
Copy the contents of the system prompts from the path example/
complete: More effective, but token expensive
short: Shorter version for saving tokens. Works fine but less accurate
6. Have fun with your new Task Manager ;)
Try chat like:
Add the task XYZ. Due date tomorrow.
You can be more specific and tell the situation:
I forgot to talk to John regarding XYZ on Friday and I need this ASAP
Or you can be broad and Claude will try to help you split the big task into smaller ones (doesn't work well with Ollama models :/):
I need to create my XYZ Vague Project
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。