MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.
MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.
SuperMemory captures distilled lessons from failures and corrections — not full conversation transcripts — validates them before storage, and improves agents over time through a closed-loop cycle.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"supermemory": {
"command": "uvx",
"args": ["supermemory-agent"],
"env": {
"SUPERMEMORY_STORAGE_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| SUPERMEMORY_STORAGE_PATH | Filesystem location the server is allowed to use. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Model Context Protocol server for Feishu integration
Persistent institutional memory for AI coding agents. Memory that compounds.
A simple Hello World MCP server
Type-safe TypeScript client for the ThingsBoard REST API with Zod v4 runtime validation