Update an existing property. Only include fields you want to change.
AI agents use update_property to create or update resources in REP Helper — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your REP Helper environment.
This tool creates or modifies data in a reversible manner (Write category). The severity is medium because: (1) it modifies property records that are used for IRS tax documentation, so errors could affect tax compliance, (2) changes are reversible/updatable, and (3) the blast radius is limited to property metadata rather than financial transactions themselves.
From the tool's definition Tool name 'update_property' combined with description 'Update an existing property. Only include fields you want to change' indicates modification of existing data records.
Attacks that exploit this kind of access
Update an existing property. Only include fields you want to change. It is categorised as a Write tool in the REP Helper MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the REP Helper MCP server in PolicyLayer and add a rule for update_property: 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 REP Helper. Nothing to install.
update_property 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 update_property 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 update_property. 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.
update_property is provided by the REP Helper MCP server (rephelper-ai/mcp-server). 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 →