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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.