reflect_add_prompt_step

SERVERSmartBear MCP SOURCESmartBear/smartbear-mcp

High RISK CLASS

Category Execute

Parameters 22 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/smartbear-mcp/reflect-add-prompt-step.md

WHAT IT DOES

What reflect_add_prompt_step does on SmartBear MCP

AI agents invoke reflect_add_prompt_step to trigger actions in SmartBear MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`prompt`	string	Yes	The natural language prompt describing the test step. The prompt should describe a single action, assertion, or query. The prompt can only contain literal text;
`sessionId`	string	Yes	The ID of the Reflect recording session

Parameters from the server's own tool schema.

RISK

Why reflect_add_prompt_step is rated High

This tool executes actions within a live browser/recording session. The prompt drives real browser interactions (navigation, clicks, key presses), meaning it triggers external operations whose effects depend on the arguments provided. This qualifies as Execute rather than Write, since it's not just storing data but actively performing browser-level actions in a running session.

From the tool's definition Add a natural language prompt step to an active Reflect recording session — the prompt describes actions such as 'Click on the back button', 'Navigate to https://www.example.com', triggering external browser operations

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs reflect_add_prompt_step safely

PolicyLayer is an MCP gateway: it sits between your AI agents and SmartBear MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reflect_add_prompt_step, this is the rule to start with:

reflect_add_prompt_step Rate-limited

reflect_add_prompt_step stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "reflect_add_prompt_step": {
      "limits": [
        {
          "counter": "reflect_add_prompt_step_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect SmartBear MCP, apply this rule, and every reflect_add_prompt_step call is checked against it from then on.

FAQ

Questions about reflect_add_prompt_step

What does the reflect_add_prompt_step tool do? +

Add a natural language prompt step to an active Reflect recording session Parameters: - sessionId (string) *required*: The ID of the Reflect recording session - prompt (string) *required*: The natural language prompt describing the test step. The prompt should describe a single action, assertion, or query. The prompt can only contain literal text; it cannot contain template variables, secrets, or other dynamic syntax. If we are in a Web recording, the prompt can perform browser navigation (e.g. "Click on the back button", "Navigate to https://www.example.com") and use the tab and enter keys to navigate (e.g. "Press the tab key", "Press the enter key"). It is categorised as a Execute tool in the SmartBear MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does reflect_add_prompt_step accept? +

reflect_add_prompt_step accepts 2 parameters: prompt, sessionId. Required: prompt, sessionId. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on reflect_add_prompt_step? +

Register the SmartBear MCP server in PolicyLayer and add a rule for reflect_add_prompt_step: 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 SmartBear MCP. Nothing to install.

What risk level is reflect_add_prompt_step? +

reflect_add_prompt_step is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit reflect_add_prompt_step? +

Yes. Add a rate_limit block to the reflect_add_prompt_step 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.

How do I block reflect_add_prompt_step completely? +

Set action: deny in the PolicyLayer policy for reflect_add_prompt_step. 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.

What MCP server provides reflect_add_prompt_step? +

reflect_add_prompt_step is provided by the SmartBear MCP server (SmartBear/smartbear-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on SmartBear, and thousands of servers like it.

This server

All 240 SmartBear tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →