CURSOR · MCP

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.

Zero code changes. Cursor supports MCP natively. Add one config block and Dakera's 83 memory tools are available to the AI.

Quick Start

Get persistent memory working in Cursor in under 2 minutes:

1

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
2

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"
      }
    }
  }
}
3

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:

CategoryToolsExample Use
Memorystore, recall, search, forgetRemember project patterns and decisions
Sessionsstart, end, list, memoriesGroup context by coding session
Knowledge Graphentities, traverse, linkMap relationships between code concepts
Namespacescreate, list, configureIsolate memory per project or team
Searchhybrid, fulltext, vectorFind relevant past context by meaning
Decayconfig, statsAuto-forget outdated information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

VariableDescriptionDefault
DAKERA_URLDakera server addresshttp://localhost:3300
DAKERA_API_KEYAuthentication keyRequired
DAKERA_AGENT_IDUnique identifier for this agent"default"
DAKERA_NAMESPACEMemory namespace isolation"default"
Works with Cursor Pro and Business. Any Cursor plan that supports MCP servers works with Dakera. The memory server runs on your own infrastructure — no additional costs beyond your Cursor subscription.

Next Steps