Split a falsely merged entity back into two separate entities, redistributing specified edges. Use when entity resolution made a mistake (e.g. merged
AI agents use graph_unmerge 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 creates two separate entities from one and redistributes edges, which is a structural modification to the knowledge graph. It is reversible in principle (you could re-merge), so it falls under Write rather than Destructive.
From the tool's definition 'Split a falsely merged entity back into two separate entities, redistributing specified edges' — creates new entities and redistributes relationships
Attacks that exploit this kind of access
Split a falsely merged entity back into two separate entities, redistributing specified edges. Use when entity resolution made a mistake (e.g. merged. 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_unmerge: 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_unmerge 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_unmerge 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_unmerge. 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_unmerge 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 →