AI agents use set_summary to create or update resources in Memora — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memora environment.
This tool creates or modifies metadata (a summary field) on an entity within the knowledge graph. It is reversible—summaries can be updated or cleared. It has minimal blast radius: incorrect summaries affect only local cached knowledge and can be easily corrected. No data is deleted, no external operations triggered, and no financial impact. This is a straightforward Write operation on entity attributes.
From the tool's definition Tool description states 'Set a short summary on an entity' and 'Pass summary='' to clear', indicating modification of existing entity metadata.
Attacks that exploit this kind of access
Set a short summary on an entity. Pass summary='' to clear. It is categorised as a Write tool in the Memora MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memora MCP server in PolicyLayer and add a rule for set_summary: 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 Memora. Nothing to install.
set_summary 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 set_summary 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 set_summary. 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.
set_summary is provided by the Memora MCP server (vnemaidev/memora). 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 →