Ratary Memory MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 10 Aug 2026.
Persistent coding memory for AI assistants. MCP stdio, hybrid search, graph, context.
Today is the operative word: we check Ratary Memory MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ratary -- npx -y @ratary/mcp-server
{
"mcpServers": {
"ratary": {
"args": [
"-y",
"@ratary/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.ratary]
command = "npx"
args = ["-y", "@ratary/mcp-server"]
{
"mcpServers": {
"ratary": {
"args": [
"-y",
"@ratary/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ratary": {
"args": [
"-y",
"@ratary/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
RATARY_API_KEY (Ratary API key (aic_...)), RATARY_BASE_URL (Ratary REST base URL (default https://ratary.ontorata.com)).
The author declared them in the registry entry; get the values from the project itself.
Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.
Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.
Persistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
Cognitive memory for AI coding assistants — persistent memory across sessions
Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.
Cross-tool persistent memory and context for AI assistants over MCP.
Answers built from our own checks of this server.