Queue a document for asynchronous extraction into the memory graph (mode=
AI agents use graph_ingest to create or update resources in Graph-Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Graph-Memory environment.
This tool ingests/queues a document for processing and extraction into the knowledge graph, which is a write operation — it creates new nodes/relationships in the graph from document content. It is reversible in principle (the added data could be deleted), so Write is appropriate rather than Destructive.
From the tool's definition Queue a document for asynchronous extraction into the memory graph
Attacks that exploit this kind of access
Queue a document for asynchronous extraction into the memory graph (mode=. It is categorised as a Write tool in the Graph-Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Graph-Memory MCP server in PolicyLayer and add a rule for graph_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 Graph-Memory. Nothing to install.
graph_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 graph_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 graph_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.
graph_ingest is provided by the Graph-Memory MCP server (stevepridemore/graph-memory). 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 →