All integrations
Hypermemory logo

One memory for your MCP clients, and every tool you will use

Cursor, Claude Code, custom agents, or internal tools: point them at Hypermemory and share one graph. Switch clients without exporting chats or re-indexing files.

Why This Works

Hypermemory is accessed via MCP and the CLI, the same memory graph either way. MCP clients use the connector URL with OAuth or API keys; agents without MCP use the CLI and skill. Every path exposes the same 12 hm_ tools on your tenant.

Quick Setup

MCP URL: https://api.hypermemory.io/mcp

  1. Copy the MCP URL below and add it as a custom connector in your client.
  2. Connect and log in with your account info (or use an API key and graph ID from the app).
  3. Add the Hypermemory skill or enable the hm_ tools in your agent.
  4. Start storing and recalling, one graph across every client you connect.

Available Tools

ToolDescription
hm_find_relatedTraverse connected knowledge from a starting node
hm_forgetDelete a node with optional cascade
hm_get_overviewGraph stats, top nodes, and type distribution
hm_ingestDecompose dense text into graph entities in one pass
hm_list_filesQuery uploaded files by type or name
hm_list_orphansList disconnected nodes for cleanup
hm_recallHybrid search across your graph (BM25, vector, edges)
hm_storeCreate a memory node; background enrichment runs automatically
hm_timelineTemporal recall by period or date range
hm_timeline_writeWrite an explicit diary-style timeline entry
hm_updateUpdate a node; re-embeds when the description changes
hm_upload_fileUpload a file into memory (summary + graph node)

Use Case

Engineering uses Cursor with Hypermemory for codebase decisions; product uses Claude for roadmap notes; ops uses an internal MCP agent for incidents. All three write to one graph, you switch tools, not memory silos.