memory_ingest
AI agents use memory_ingest to create or update resources in Eve Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Eve Memory environment.
The name 'memory_ingest' implies writing or storing data into the shared memory service. Sibling tools like 'memory_forget' (likely destructive) and 'memory_search' (likely read) provide context that this tool creates or adds memory entries. Without a description, confidence is reduced, but 'ingest' strongly implies a write/store operation.
From the tool's definition Tool name 'memory_ingest' suggests ingesting/writing data into memory; description is empty and uninformative.
Attacks that exploit this kind of access
memory_ingest. It is categorised as a Write tool in the Eve Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Eve Memory MCP server in PolicyLayer and add a rule for memory_ingest: 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 Eve Memory. Nothing to install.
memory_ingest 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_ingest 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_ingest. 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_ingest is provided by the Eve Memory MCP server (sherifkozman/eve-mcp). 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 →