AI agents call load-routines to retrieve information from Routine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists routine data with no side effects. It is a read-only operation that allows users to access previously created routines. While the sibling tools (create-routine, delete-routine, update-routine) perform write/destructive operations, load-routines itself only performs data retrieval, making it a Read category tool with low severity.
From the tool's definition The tool name 'load-routines' and description 'Load routines' indicate a retrieval operation that queries or fetches existing routine definitions without modifying them.
Attacks that exploit this kind of access
Load routines. It is categorised as a Read tool in the Routine MCP Server, which means it retrieves data without modifying state.
Register the Routine MCP server in PolicyLayer and add a rule for load-routines: 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 Routine. Nothing to install.
load-routines 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 load-routines 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 load-routines. 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.
load-routines is provided by the Routine MCP server (mquan/mcp-routine). 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 →