Create a new Test Script of the types Plain Text or BDD in a Zephyr Test Case. **Examples:** 1. Create a plain text test script for test case SA-T1 to verify that the axial pump can be enabled ```json { "testCaseKey": "SA-T1", "type": "plain", "text": "1. Navigate to Pump Settings</br>2. E...
Part of the SmartBear MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use zephyr_create_test_script to create or modify resources in SmartBear MCP. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call zephyr_create_test_script repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach SmartBear MCP.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
zephyr_create_test_script:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full SmartBear MCP policy for all 243 tools.
Agents calling write-class tools like zephyr_create_test_script have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Create a new Test Script of the types Plain Text or BDD in a Zephyr Test Case. **Examples:** 1. Create a plain text test script for test case SA-T1 to verify that the axial pump can be enabled ```json { "testCaseKey": "SA-T1", "type": "plain", "text": "1. Navigate to Pump Settings</br>2. Enable Axial Pump</br>3. Verify pump status is 'Active'" } ``` Expected Output: The created test script metadata including its id and self link 2. Create a BDD test script for test case MM2-T15 to validate axial pump activation ```json { "testCaseKey": "MM2-T15", "type": "bdd", "text": "Given the axial pump is installed\nWhen the user enables the axial pump\nThen the pump status should be Active" } ``` Expected Output: The created test script metadata including its id and self link 3. Create a BDD test script for test case QA-T100 for axial pump performance validation ```json { "testCaseKey": "QA-T100", "type": "bdd", "text": "Given the system is running\nWhen the axial pump operates under load\nThen performance metrics should remain within thresholds" } ``` Expected Output: The created test script metadata including its id and self link. It is categorised as a Write tool in the SmartBear MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for zephyr_create_test_script. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the SmartBear MCP MCP server.
zephyr_create_test_script 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 zephyr_create_test_script rule in your Intercept 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 Intercept policy for zephyr_create_test_script. 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.
zephyr_create_test_script is provided by the SmartBear MCP MCP server (@smartbear/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.