ai.workingmemory/memory
WorkingMemory
ai.workingmemory/memory costs 795 tokens of context per session. It has 4 tool definitions. That is 0.4 % of a 200k window. Measured 2026-10-03.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
alive probed 2026-10-03 · HTTP 200
4tools
795tokens for the tool definitions
0.4 %of a 200k context window
1.0 sto initialize
498 msto list tools
- Endpoint
- https://app.workingmemory.ai/mcp (streamable-http)
- Host
- app.workingmemory.ai
- Protocol
- 2025-11-25
- Reports itself as
- workingmemory 1.0.0
- Capabilities
- tools
- Instructions
- 840 characters
- Website
- https://workingmemory.ai
- Registry
- active, updated 2026-07-17 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| search_memory | 293 | 37 % |
| capture_memory | 204 | 26 % |
| save_memory | 203 | 26 % |
| manage_memory | 95 | 12 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:26 | alive | 1.0 s | 4 | 795 |
| 2026-10-03 17:46 | alive | 1.1 s | 4 | 795 |
Badge
[](https://mcp-pulse.ulehla.dev/s/ai.workingmemory/memory)