AI agents call get_runs to retrieve information from TestRail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
TestRail's 'get_runs' retrieves run data from the system. Given the context of sibling tools like 'add_run', 'close_run', and 'delete_run', this tool is clearly a read-only query that retrieves existing test runs without side effects. This poses minimal security risk as it only accesses data.
From the tool's definition Tool name 'get_runs' indicates retrieval of test runs without modification. Absence of action verbs like 'create', 'update', 'delete', or 'execute' combined with the verb 'get' (a standard read operation) confirms this is a query operation.
Documented attack patterns abuse exactly the kind of access get_runs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TestRail MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_runs:
{
"version": "1",
"default": "deny",
"tools": {
"get_runs": {}
}
}get_runs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_runs. It is categorised as a Read tool in the TestRail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TestRail MCP Server MCP server in PolicyLayer and add a rule for get_runs: 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 MCP Server. Nothing to install.
get_runs 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 get_runs 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 get_runs. 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.
get_runs is provided by the TestRail MCP Server MCP server (sker65/testrail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TestRail MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 TestRail MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.