Sprig MCP: Answering All Your Questions about Data Security
Sprig MCP is designed so an AI client sees only the survey data your Sprig role already permits, scoped by OAuth and enforced at every tool call. Agents can create studies in draft only, users approve before anything reaches respondents, and admins hold an org-wide kill switch. Unlike a CSV export, MCP leaves no permanent, unscoped copy of your data.Data Handling and Retention
1. What happens to Sprig data inside the LLM conversation? Is it retained or used for training?
When your team prompts Sprig through MCP, the returned data becomes part of that conversation on the LLM provider’s side. MCP introduces no new data exposure category beyond what your organization already accepted by adopting the LLM tool. Sprig does not store copies with the provider and does not control the provider’s retention.- In transit, tool calls run over TLS between the client and mcp.sprig.com.
- In context, the data lives inside the conversation for its duration.
- After the conversation, retention, training treatment, and provider-side access are governed by your organization’s agreement with the LLM provider, not by Sprig.
2. Does Sprig or the LLM provider train models on our response data?
Sprig does not use your response data to train models. Data returned through MCP is subject to your LLM provider’s own data handling terms, so enterprise customers should confirm their Claude, OpenAI, Gemini or Copilot agreement excludes training on API and connector traffic, which enterprise plans typically do.3. How is MCP different from exporting a CSV and uploading it to an LLM?
A CSV export is a permanent, unscoped copy; MCP is scoped, live access with no lasting copy. Once a CSV is downloaded, it sits outside Sprig’s permission model: anyone with the file can share it, upload it anywhere, and retain it indefinitely, with no way for you to revoke it. MCP inverts that. Data is fetched at prompt time, scoped to what the authenticated user is allowed to see, and access ends the moment an admin revokes the token or disables the server. A CSV upload is a one-time transfer with zero ongoing control; MCP is live access with your controls intact.Access and Permissions
Sprig MCP lets AI clients, like Claude, ChatGPT, and Cursor, query your Sprig research data with no standing copy leaving Sprig. Access is scoped by OAuth to your existing Sprig role and enforced on every request. Agents draft studies but never launch them, admins can cut off all access instantly, and Sprig never trains on your responses.- Permissions are checked at every tool call, not once at connection time.
- Agents create studies in draft state only.
- Admins can revoke all MCP connections org-wide, instantly, from one setting.
- Data returned into an LLM conversation follows your provider agreement, meaning enterprise plans from Anthropic, OpenAI, and Microsoft exclude it from model training.