AI agents use replace_all_matching_properties to create or update resources in Pen — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pen environment.
This tool creates or modifies data reversibly across potentially many nodes in a document tree. The recursive scope and bulk nature of the replacement increase the severity (high rather than medium) due to the blast radius—a mistake could affect many properties at once—but the operation is reversible and does not permanently delete or destroy data, so it falls short of Destructive. Write is the correct category.
From the tool's definition Tool description states 'replace all matching property values on the node tree' — this modifies existing properties recursively across multiple nodes. The word 'replace' indicates reversible data modification.
Attacks that exploit this kind of access
Recursively replace all matching property values on the node tree under provided parent IDs. It is categorised as a Write tool in the Pen MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pen MCP server in PolicyLayer and add a rule for replace_all_matching_properties: 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 Pen. Nothing to install.
replace_all_matching_properties 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 replace_all_matching_properties 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 replace_all_matching_properties. 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.
replace_all_matching_properties is provided by the Pen MCP server (@zseven-w/pen-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 →