Push any JSON. Your agent gets a live, queryable schema, graph relationships, and semantic search — inferred automatically. No pipeline. No separate stores. No schema to design.
Rushdb Memory Layer For Ai Agents And Apps is an MCP project maintained in the rush-db/rushdb repository. The maintainer describes its purpose as “Push any JSON. Your agent gets a live, queryable schema, graph relationships, and semantic search — inferred automatically. No pipeline. No separate stores. No schema…”. Read the project documentation for the complete scope.
The documented npm package is @rushdb/mcp-server. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares RUSHDB_API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
{
"mcpServers": {
"rushdb": {
"command": "npx",
"args": [
"@rushdb/mcp-server"
],
"env": {
"RUSHDB_API_KEY": "YOUR_RUSHDB_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| RUSHDB_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
An MCP server that can read online documents to solve problems accordingly!
AI helpdesk by Spatie. Read, triage and reply to tickets, and edit your knowledge base.
A fairly customizable MCP server for Logseq
Persistent memory and context window caching for LLM conversations. Save, retrieve, and manage memories with intelligent context archiving. MongoDB-backed storage.