AI agents use add_rule to create or update resources in Prompts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompts environment.
This tool creates new rules that are stored persistently in a project system. While this modifies project configuration and behavior, the changes are reversible (rules can presumably be removed or updated later). It does not delete data, execute arbitrary code, move money, or trigger destructive operations.
From the tool's definition Tool description indicates the tool 'adds a project specification rule' and that 'rules will be persistently stored and automatically loaded at each session startup.' The verb 'add' combined with 'persistently stored' confirms this creates/modifies data…
Attacks that exploit this kind of access
【添加规则】添加一条项目规范规则。规则会持久化存储,在每次会话启动时自动加载。. It is categorised as a Write tool in the Prompts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prompts MCP server in PolicyLayer and add a rule for add_rule: 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 Prompts. Nothing to install.
add_rule 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_rule 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_rule. 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_rule is provided by the Prompts MCP server (thana0623/pmcp-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 →