Lists system/coding patterns, optionally filtered by tags. Returns most recent first. Use to review established patterns or find patterns by tag. There is no FTS search for patterns — for keyword search across patterns, use semantic_search_engrams with filter_item_types=[
AI agents call get_system_patterns to retrieve information from Engrams without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and filters stored pattern data. It retrieves information for review without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal — an AI could retrieve patterns it shouldn't see, but cannot alter state or trigger side effects. This is classic Read category behavior.
From the tool's definition Tool name 'get_system_patterns' and description 'Lists system/coding patterns' indicate retrieval/querying of existing data. The tool 'optionally filtered by tags' and 'returns most recent first' confirms it performs filtering and retrieval operations only.
Documented attack patterns abuse exactly the kind of access get_system_patterns gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Engrams, and nothing reaches the server without passing your rules. This is the rule we recommend for get_system_patterns:
{
"version": "1",
"default": "deny",
"tools": {
"get_system_patterns": {}
}
}get_system_patterns is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Lists system/coding patterns, optionally filtered by tags. Returns most recent first. Use to review established patterns or find patterns by tag. There is no FTS search for patterns — for keyword search across patterns, use semantic_search_engrams with filter_item_types=[. It is categorised as a Read tool in the Engrams MCP Server, which means it retrieves data without modifying state.
Register the Engrams MCP server in PolicyLayer and add a rule for get_system_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 Engrams. Nothing to install.
get_system_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 get_system_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 get_system_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.
get_system_patterns is provided by the Engrams MCP server (stevebrownlee/engrams). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Engrams, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
42 Engrams tools catalogued and risk-classified — across an index of 43,000+ MCP servers.