Fetch a test plan by identifier (TP-*) from BrowserStack Test Management. Returns plan metadata, the full list of linked test runs, total test-case count across runs, and a status summary — suitable for generating test documentation or QA status reports.
AI agents call getTestPlan to retrieve information from BrowserStack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing test plan data without creating, modifying, deleting, or executing any operations. It is purely informational and suitable for generating documentation or reports. The blast radius of misuse is minimal — at worst, an agent could retrieve test plan information it shouldn't have access to, but no data would be altered or operations triggered.
From the tool's definition Tool name 'getTestPlan' and description 'Fetch a test plan by identifier' indicate a retrieval operation. The description explicitly states it 'Returns plan metadata, the full list of linked test runs, total test-case count across runs, and a status summary'…
Attacks that exploit this kind of access
Fetch a test plan by identifier (TP-*) from BrowserStack Test Management. Returns plan metadata, the full list of linked test runs, total test-case count across runs, and a status summary — suitable for generating test documentation or QA status reports. It is categorised as a Read tool in the BrowserStack MCP Server, which means it retrieves data without modifying state.
Register the BrowserStack MCP server in PolicyLayer and add a rule for getTestPlan: 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 BrowserStack. Nothing to install.
getTestPlan 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 getTestPlan 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 getTestPlan. 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.
getTestPlan is provided by the BrowserStack MCP server (browserstack/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.