AI agents use add_rule to create or update resources in Starlog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Starlog environment.
This tool creates or adds new rules/guidelines to a project, which is a Write-category operation (creates data reversibly). The severity is medium because misuse could pollute project guidelines with incorrect standards, but the effects are documentational rather than operational and can be corrected by deleting or updating the rules.
From the tool's definition The tool description states 'Create new project guideline or standard' and the name 'add_rule' indicates creation of new data. This is a reversible write operation that establishes documentation artifacts.
Attacks that exploit this kind of access
Create new project guideline or standard. Use this to establish coding standards, project conventions, or other guidelines during development. It is categorised as a Write tool in the Starlog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Starlog 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 Starlog. 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 Starlog MCP server (sancovp/starlog-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 →