Mochi MCP Server
Enables AI agents to manage Mochi.cards flashcards, including browsing decks, searching cards, and creating/updating/deleting cards with safety features like two-phase commits and typed confirmations.
README
Mochi MCP Server
A Model Context Protocol server that enables AI agents (Claude, Codex, etc.) to manage your Mochi.cards flashcards.
Features
- Browse decks and cards
- Search cards by content or tags
- Create/Update cards with two-phase commit (preview before applying)
- Delete cards with typed confirmation (safety first)
- Robust safety - deck deletion disabled by default
Quick Start
# Install
npm install
# Build
npm run build
# Run (needs your Mochi API key)
MOCHI_API_KEY=your_key_here node dist/index.js
Get your API key from the Mochi app: Settings → Account → API Key.
Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"mochi": {
"command": "node",
"args": ["/path/to/mochi-mcp/dist/index.js"],
"env": {
"MOCHI_API_KEY": "your_api_key"
}
}
}
}
Then ask Claude: "List my Mochi decks" or "Search for cards about gradients".
Tools
Read Operations
| Tool | Description |
|---|---|
list_decks |
List all decks |
get_deck |
Get deck with card list |
get_card |
Get full card content |
get_cards |
Get multiple cards by ID |
search_cards |
Search by text, tags, or date. Returns rich results (deckId, createdAt, etc.) |
list_cards_page |
Paginated card listing with bookmark |
find_deck_by_name |
Find decks by name (case-insensitive partial match) |
Write Operations (Two-Phase Commit)
| Tool | Description |
|---|---|
create_card_preview |
Preview new card → returns token |
apply_create_card |
Apply creation with token |
update_card_preview |
Preview edit with diff → returns token |
update_card_fields_preview |
Preview Q/A edit → returns token |
apply_update_card |
Apply update with token |
update_cards_batch_preview |
Preview batch updates |
apply_update_cards_batch |
Apply batch updates |
Tag Operations (Two-Phase)
| Tool | Description |
|---|---|
add_tags_preview |
Preview adding tags to cards |
remove_tags_preview |
Preview removing tags |
apply_tags_update |
Apply tag changes with token |
Delete Operations (Requires Confirmation)
| Tool | Description |
|---|---|
delete_card |
Soft-delete (requires: "delete card <id>") |
delete_deck |
Disabled by default |
Performance Notes
- Global search scans at most 1000 cards
- Per-deck search scans at most 5000 cards
- Use
list_cards_pagewith pagination for larger collections - Date filters use UTC (ISO 8601 format:
YYYY-MM-DDTHH:mm:ss.sssZ)
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
MOCHI_API_KEY |
✅ | - | Your Mochi API key |
MOCHI_ALLOW_DECK_DELETE |
❌ | false |
Enable deck deletion |
MOCHI_TOKEN_EXPIRY_MINS |
❌ | 10 |
Preview token validity |
Safety Design
-
Two-phase commit: Create/update operations show a preview first. You approve by using the returned token.
-
Typed confirmations: Delete requires typing
"delete card <id>"exactly. -
Deck deletion disabled: Must set
MOCHI_ALLOW_DECK_DELETE=trueto enable. -
Soft delete default: Cards go to trash (recoverable in Mochi app).
Development
# Run tests
npm test
# Type check
npm run lint
# Development mode
MOCHI_API_KEY=your_key npm run dev
# Test with MCP Inspector
npm run inspect
License
MIT
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.