Save a user-approved or project-relevant memory with audit logging.
AI agents use memory_write to create or update resources in Lore Context — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lore Context environment.
This tool creates or modifies memory artifacts in a governed AI-agent context. While reversible and audited, it qualifies as Write rather than Read (it persists data) or Execute (it doesn't trigger external code execution). The 'user-approved' constraint and audit logging mitigate risk but do not prevent misuse by an agent to pollute memory with false or misleading information.
From the tool's definition Tool description states 'Save a user-approved or project-relevant memory with audit logging', which explicitly indicates creation or modification of data (memory records) with reversible persistence via audit-logged writes.
Attacks that exploit this kind of access
Save a user-approved or project-relevant memory with audit logging. It is categorised as a Write tool in the Lore Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lore Context MCP server in PolicyLayer and add a rule for memory_write: 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 Lore Context. Nothing to install.
memory_write 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_write 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_write. 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_write is provided by the Lore Context MCP server (Lore-Context/lore-context). 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 →