memory_save
Save an insight, decision, observation, or error to the workspace memory database.
This record as markdown: /tools/cowork-os/memory-save.md
What memory_save does on CoWork OS
AI agents use memory_save to create or update resources in CoWork OS, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CoWork OS environment.
Why memory_save is rated Medium
This tool writes data to a persistent storage system (workspace memory database). It is not destructive (data can be retrieved and overwritten later), does not execute arbitrary code, and has no financial impact.
From the tool's definition Tool description explicitly states 'Save...to the workspace memory database' — a create/modify operation that persists data.
Attacks that exploit this kind of access
The rule that runs memory_save safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For memory_save, this is the rule to start with:
memory_save stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every memory_save call is checked against it from then on.
Questions about memory_save
Save an insight, decision, observation, or error to the workspace memory database. It is categorised as a Write tool in the CoWork OS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CoWork OS MCP server in PolicyLayer and add a rule for memory_save: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CoWork OS. Nothing to install.
memory_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memory_save rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for memory_save. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
memory_save is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
This server
Across the catalogue