AI agents use pattern_import_kg to create or update resources in Musubix — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Musubix environment.
The tool creates or modifies data within a knowledge graph system by importing patterns. This is reversible (patterns can be removed or updated later) and has side effects limited to the knowledge graph state. It is not a Read operation (it modifies state), not Destructive (patterns can be undone), not Execute (it doesn't run arbitrary code), and not Financial.
From the tool's definition Tool description states 'Import learned patterns into the ontology knowledge graph' — this modifies the knowledge graph by adding patterns, which is a data creation/modification operation without explicit deletion.
Attacks that exploit this kind of access
Import learned patterns into the ontology knowledge graph for semantic reasoning. It is categorised as a Write tool in the Musubix MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Musubix MCP server in PolicyLayer and add a rule for pattern_import_kg: 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 Musubix. Nothing to install.
pattern_import_kg 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 pattern_import_kg 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 pattern_import_kg. 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.
pattern_import_kg is provided by the Musubix MCP server (@nahisaho/musubix-mcp-server). 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 →