Skip to main content

​
MCP Integration

Kernle provides an MCP (Model Context Protocol) server that exposes memory operations as tools for AI assistants.

​
What is MCP?

MCP is a protocol that allows AI assistants to use external tools. When you add Kernle as an MCP server, your AI assistant gains access to memory operations like:
  • Loading working memory
  • Saving checkpoints
  • Recording episodes and notes
  • Searching memory
  • Managing beliefs and values

​
Starting the MCP Server

kernle -a <agent_id> mcp
This starts an MCP server using stdio transport. The server stays running and responds to tool calls from the connected client.

​
Available Tools

When connected, the MCP server exposes these tools:
ToolDescription
memory_loadLoad working memory
memory_checkpoint_saveSave checkpoint with task description
memory_checkpoint_loadLoad previous checkpoint
memory_episodeRecord an experience
memory_noteCapture a note
memory_rawQuick capture
memory_searchSearch across memory
memory_statusGet memory status
memory_anxietyCheck memory health
memory_beliefManage beliefs
memory_valueManage values
memory_goalManage goals

​
Client Configuration

​
Claude Code

Add Kernle as an MCP server using the Claude CLI: 
claude mcp add kernle -- kernle -a <agent_id> mcp
This registers Kernle with Claude Code. You can verify with: 
claude mcp list

​
General MCP Configuration

For clients that use a JSON configuration file: 
{
  "mcpServers": {
    "kernle": {
      "command": "kernle",
      "args": ["-a", "<agent_id>", "mcp"]
    }
  }
}
Replace <agent_id> with your actual agent identifier.

​
Usage Example

Once configured, your AI assistant can use memory tools naturally: 
"Let me save my current progress..."
→ Tool call: memory_checkpoint_save(task="Working on user auth")

"What have I learned about caching?"
→ Tool call: memory_search(query="caching")

"I should remember this insight about rate limiting."
→ Tool call: memory_note(content="Rate limits are per-user, not per-key", type="insight")

​
Best Practices

Session Start: Always call memory_load at the beginning of a session to restore context.
Save Often: Use memory_checkpoint_save before context gets full, not just at session end.
Record Lessons: Use memory_episode with lessons when you learn something significant.

​
Troubleshooting

​
Server Not Starting

Verify Kernle is installed and accessible: 
which kernle
kernle --version

​
Tools Not Appearing

  1. Restart your MCP client
  2. Check the MCP configuration path
  3. Verify the agent ID exists: kernle -a <agent_id> status

​
Permission Issues

The MCP server runs with the same permissions as your user. Ensure ~/.kernle/ is accessible.