Cursor Integration
Give your Cursor AI coding assistant persistent memory. Dakera's MCP server connects directly to Cursor — your AI remembers project architecture, coding decisions, debugging context, and team patterns across every session.
Quick Start
Get persistent memory working in Cursor in under 2 minutes:
Start Dakera
docker run -d --name dakera \
-p 3300:3300 \
-e DAKERA_API_KEY=dk-your-key-here \
-v dakera-data:/data \
ghcr.io/dakera-ai/dakera:latest
Configure Cursor MCP
Create or edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"dakera": {
"command": "docker",
"args": ["run", "--rm", "-i",
"--network", "host",
"ghcr.io/dakera-ai/dakera-mcp:latest"],
"env": {
"DAKERA_URL": "http://localhost:3300",
"DAKERA_API_KEY": "dk-your-key-here",
"DAKERA_AGENT_ID": "cursor-dev"
}
}
}
}
Start Coding with Memory
Restart Cursor. The AI now has access to persistent memory tools. Try asking:
- "Remember that we use the repository pattern for database access in this project"
- "What architecture decisions have we made so far?"
- "Store this debugging approach for the payment module"
What Cursor Gets
With Dakera connected, Cursor's AI has access to 83 MCP tools organized into categories:
| Category | Tools | Example Use |
|---|---|---|
| Memory | store, recall, search, forget | Remember project patterns and decisions |
| Sessions | start, end, list, memories | Group context by coding session |
| Knowledge Graph | entities, traverse, link | Map relationships between code concepts |
| Namespaces | create, list, configure | Isolate memory per project or team |
| Search | hybrid, fulltext, vector | Find relevant past context by meaning |
| Decay | config, stats | Auto-forget outdated information |
Use Cases for Coding
Project Architecture Memory
Store architectural decisions, patterns, and conventions. When Cursor starts a new session, it can recall the project's design philosophy without you re-explaining.
// Cursor will automatically use these tools:
// dakera_store: "This project uses hexagonal architecture with ports and adapters"
// dakera_store: "Database migrations use sqlx with versioned SQL files"
// dakera_recall: "What's our authentication approach?"
Cross-Session Debugging Context
When debugging a complex issue over multiple sessions, Dakera preserves the investigation trail — what you tried, what failed, and what clues you found.
Team Knowledge Sharing
Multiple developers can connect to the same Dakera instance with different agent IDs. Cross-agent recall lets the AI access shared team knowledge while maintaining individual context.
Code Pattern Library
Store reusable patterns with importance scoring. Frequently accessed patterns score higher and surface more readily in future recalls.
Configuration Options
| Variable | Description | Default |
|---|---|---|
| DAKERA_URL | Dakera server address | http://localhost:3300 |
| DAKERA_API_KEY | Authentication key | Required |
| DAKERA_AGENT_ID | Unique identifier for this agent | "default" |
| DAKERA_NAMESPACE | Memory namespace isolation | "default" |
Next Steps
- Full MCP Server documentation — all 83 tools explained
- Quick Start guide — detailed setup walkthrough
- Memory Patterns — common patterns for coding workflows
- Claude Desktop integration — same memory, different client