Decrease an edge
AI agents use graph_weaken 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.
Weakening an edge is a reversible modification to graph data (it can be strengthened again), placing it in the Write category. It does not delete the edge outright, so Destructive is not warranted. Misuse could degrade knowledge graph quality by systematically weakening important relationships, hence medium severity.
From the tool's definition "Decrease an edge" — modifies the weight/strength of an existing relationship in the knowledge graph
Attacks that exploit this kind of access
Decrease an edge. 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_weaken: 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_weaken 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_weaken 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_weaken. 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_weaken 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 →