Self-hosted MCP server for AI agent memory — 14 core tools, profile-based tiering (86+ available). 88.2% LoCoMo. Works with Claude, Cursor, Windsurf.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add dakera -- docker run -i --rm ghcr.io/dakera-ai/dakera-mcp:0.12.2~/.codex/config.toml
[mcp_servers.dakera]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/dakera-ai/dakera-mcp:0.12.2"]
# codex mcp add dakera -- docker run -i --rm ghcr.io/dakera-ai/dakera-mcp:0.12.2~/.cursor/mcp.json
{
"mcpServers": {
"dakera": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/dakera-ai/dakera-mcp:0.12.2"
]
}
}
}.vscode/mcp.json
{
"servers": {
"dakera": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/dakera-ai/dakera-mcp:0.12.2"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"dakera": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/dakera-ai/dakera-mcp:0.12.2"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"dakera": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/dakera-ai/dakera-mcp:0.12.2"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"dakera": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/dakera-ai/dakera-mcp:0.12.2"
]
}
}
}