Add embedded data fields to the survey flow. These fields can be set via URL parameters, contact lists, or web services, and referenced in questions with piped text ${e://Field/FieldName}. The embedded data element is inserted at the beginning of the flow (before all blocks) so fields are availab...
AI agents use add_embedded_data to create or update resources in Qualtrics MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qualtrics MCP Server environment.
This tool creates or modifies survey metadata (embedded data fields) reversibly—fields can be edited or removed later. It does not execute arbitrary code, delete data irreversibly, move money, or retrieve existing data without modification. The impact is scoped to survey configuration within Qualtrics.
From the tool's definition Tool description states it 'Add[s] embedded data fields to the survey flow' and 'inserted at the beginning of the flow', which creates and modifies survey configuration data.
Documented attack patterns abuse exactly the kind of access add_embedded_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Qualtrics MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_embedded_data:
{
"version": "1",
"default": "deny",
"tools": {
"add_embedded_data": {
"limits": [
{
"counter": "add_embedded_data_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_embedded_data stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add embedded data fields to the survey flow. These fields can be set via URL parameters, contact lists, or web services, and referenced in questions with piped text ${e://Field/FieldName}. The embedded data element is inserted at the beginning of the flow (before all blocks) so fields are available throughout. It is categorised as a Write tool in the Qualtrics MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qualtrics MCP Server MCP server in PolicyLayer and add a rule for add_embedded_data: 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 Qualtrics MCP Server. Nothing to install.
add_embedded_data 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 add_embedded_data 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 add_embedded_data. 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.
add_embedded_data is provided by the Qualtrics MCP Server MCP server (yrvelez/qualtrics-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Qualtrics 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.
57 Qualtrics MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.