AI agents call get_code_patterns to retrieve information from Handoff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves stored code patterns from a shared memory hub without side effects. Filtering and searching do not constitute modification or execution. The blast radius of misuse is minimal—an agent could access code patterns but cannot execute them, delete them, or modify project state. Classified as Read with low severity.
From the tool's definition Tool name contains 'get_' and description explicitly states 'Retrieve code patterns' with optional filtering—classic read-only retrieval with no modification, deletion, or execution implied.
Attacks that exploit this kind of access
Retrieve code patterns for a project, optionally filtered by category, language, or keyword search. It is categorised as a Read tool in the Handoff MCP Server, which means it retrieves data without modifying state.
Register the Handoff MCP server in PolicyLayer and add a rule for get_code_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 Handoff. Nothing to install.
get_code_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_code_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_code_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_code_patterns is provided by the Handoff MCP server (juan-severiano/handoff-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 →