Manage relationships between nodes. Operations: add, delete, get, neighbors, subgraph. Build knowledge graphs by linking nodes (e.g.,
AI agents call memory_edge to permanently remove resources in M I M I R Multi Agent Intelligent Memory & Insight Repository — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool spans multiple categories: 'get', 'neighbors', and 'subgraph' are Read operations, 'add' is a Write operation, but 'delete' is a Destructive operation that can irreversibly remove edges from the persistent graph database. Per the rules, the most severe applicable category must be chosen, making this Destructive.
From the tool's definition Operations: add, delete, get, neighbors, subgraph — the 'delete' operation can irreversibly remove relationships between nodes in the knowledge graph
Documented attack patterns abuse exactly the kind of access memory_edge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and M I M I R Multi Agent Intelligent Memory & Insight Repository, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_edge:
{
"version": "1",
"default": "deny",
"hide": [
"memory_edge"
]
}memory_edge disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
All 13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools →
Manage relationships between nodes. Operations: add, delete, get, neighbors, subgraph. Build knowledge graphs by linking nodes (e.g.,. It is categorised as a Destructive tool in the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP server in PolicyLayer and add a rule for memory_edge: 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 M I M I R Multi Agent Intelligent Memory & Insight Repository. Nothing to install.
memory_edge is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the memory_edge 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_edge. 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_edge is provided by the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP server (orneryd/mimir). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools catalogued and risk-classified — across an index of 42,500+ MCP servers.