Update an existing memory by ID. Re-embeds if content changes.
AI agents use memory_update to create or update resources in Mcp Recall — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Recall environment.
This tool modifies data (the memory entry) reversibly. It does not delete data (ruling out Destructive), does not execute arbitrary code (ruling out Execute), and does not move money (ruling out Financial). The ability to update memories could allow an agent to alter stored facts, but the change is reversible and limited in scope to a specific memory record.
From the tool's definition Tool name 'memory_update' and description 'Update an existing memory by ID. Re-embeds if content changes.' explicitly indicates modification of existing data. The re-embedding behavior confirms the content is being altered.
Attacks that exploit this kind of access
Update an existing memory by ID. Re-embeds if content changes. It is categorised as a Write tool in the Mcp Recall MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Recall MCP server in PolicyLayer and add a rule for memory_update: 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 Mcp Recall. Nothing to install.
memory_update 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_update 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_update. 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_update is provided by the Mcp Recall MCP server (jensimogit/mcp-recall). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →