Consolidate two entities into one — moves source
AI agents use graph_merge 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 modifies the knowledge graph by merging entities, which is a Write operation (creates/modifies data reversibly). It is not Destructive because the source entity's data is moved rather than permanently deleted—it could theoretically be recovered or reversed by unmerging.
From the tool's definition Tool name is 'graph_merge' with description 'Consolidate two entities into one — moves source'. The verb 'consolidate' and action 'moves source' indicate modification of existing data by merging entities, which is reversible through graph reconstruction or…
Attacks that exploit this kind of access
Consolidate two entities into one — moves source. 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_merge: 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_merge 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_merge 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_merge. 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_merge 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 →