Add new code examples to existing patterns
AI agents use add_code_examples to create or update resources in MCPatterns — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPatterns environment.
The tool modifies a pattern resource by adding code examples to it. This is a Write operation: it's reversible (examples can be removed via delete_code_examples), creates new sub-resources, and has no destructive or side-effect-triggering behavior.
From the tool's definition Tool description states 'Add new code examples to existing patterns' — this creates/appends data to an existing resource without deletion or overwrite.
Attacks that exploit this kind of access
Add new code examples to existing patterns. It is categorised as a Write tool in the MCPatterns MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPatterns MCP server in PolicyLayer and add a rule for add_code_examples: 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.
add_code_examples is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_code_examples 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 add_code_examples. 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.
add_code_examples 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 →