Search for patterns based on a query across all fields
AI agents call search_patterns to retrieve information from MCPatterns without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries stored coding patterns without modifying, deleting, or executing anything. It is a straightforward read operation that retrieves information to help users find relevant patterns. No destructive, financial, or code execution occurs. Confidence is high because the description clearly indicates a search/retrieval function.
From the tool's definition Tool name is 'search_patterns' and description states 'Search for patterns based on a query across all fields' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search for patterns based on a query across all fields. It is categorised as a Read tool in the MCPatterns MCP Server, which means it retrieves data without modifying state.
Register the MCPatterns MCP server in PolicyLayer and add a rule for search_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 MCPatterns. Nothing to install.
search_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 search_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 search_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.
search_patterns is provided by the MCPatterns MCP server (nicholasrubright/mcpatterns). 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 →