AI agents call prepare_runs_diff to retrieve information from Testrail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool compares two TestRail test runs to identify differences in test results (regressions, fixes, coverage changes) and returns the computed delta. It performs a query/analysis operation with no side effects—it does not create, modify, delete, or execute anything. The operation is purely informational and reversible in nature, consistent with the 'Read' category for data retrieval and analysis tools.
From the tool's definition Tool name 'prepare_runs_diff' and description 'Compute the regression / fix / coverage delta between two runs and return' indicate data retrieval and comparison operations without modification or deletion.
Attacks that exploit this kind of access
Compute the regression / fix / coverage delta between two runs and return. It is categorised as a Read tool in the Testrail MCP Server, which means it retrieves data without modifying state.
Register the Testrail MCP server in PolicyLayer and add a rule for prepare_runs_diff: 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 Testrail. Nothing to install.
prepare_runs_diff is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the prepare_runs_diff 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 prepare_runs_diff. 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.
prepare_runs_diff is provided by the Testrail MCP server (sergey-bl/testrail-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 →