graph_lookup_patterns
AI agents call graph_lookup_patterns to retrieve information from IMS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the 'lookup' nomenclature and context among sibling tools that use explicit action verbs (create, blocking_analysis, drift), this tool most likely retrieves or queries graph patterns without side effects. However, confidence is moderate (0.6) rather than high because the description is empty, leaving some ambiguity about whether it might perform graph traversal with unintended effects.
From the tool's definition Tool name 'graph_lookup_patterns' suggests a lookup/query operation on a graph structure. The name implies retrieving or searching patterns rather than modifying state.
Attacks that exploit this kind of access
graph_lookup_patterns. It is categorised as a Read tool in the IMS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IMS MCP Server MCP server in PolicyLayer and add a rule for graph_lookup_patterns: 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 IMS MCP Server. Nothing to install.
graph_lookup_patterns is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the graph_lookup_patterns 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_lookup_patterns. 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_lookup_patterns is provided by the IMS MCP Server MCP server (jdelon02/ims-mcp). 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 →