> For the complete documentation index, see [llms.txt](https://docs.podigee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podigee.com/documentation/start-here/ai-agents/mcp-reference/security-privacy-and-data-boundaries.md). # Security, privacy, and data boundaries Credential, media, private URL, personal data, audit, and external-system boundaries. ## Credentials Use bearer tokens only with the canonical MCP resource and upload-control origin. Store them in the client's secure credential store. Never place access tokens, refresh tokens, personal access tokens, passwords, or confirmations in documentation or logs. ## Media Media bytes go directly from the capable client to a signed storage URL. Signed URLs are opaque, short-lived secrets. Podigee returns a public upload UUID, not provider storage credentials. ## Listener data Listener email addresses and usernames are personal data. Passwords, access tokens, and private feed URLs are not returned in public listener objects. Treat any complete private feed URL as a credential. ## Tenant data All tools, resources, operations, and audit events remain bound to one selected account or organization. Do not cache or combine records across grants unless the human explicitly manages each account separately. ## Auditing Operations preserve actor, tenant, credential type, scopes, contract version, target IDs, and safe outcomes. Public results and errors are sanitized. Do not add secrets or unnecessary personal data to idempotency keys, client identity, free-text queries, or support notes. ## External systems Podigee can prove its own submission or delivery state. External platforms remain authoritative for account ownership, review, cache refresh, listing, and receipt. Verify important external effects at the destination. Retention statements require current legal and product review before publication. This reference does not promise a retention period for audit or personal data. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.podigee.com/documentation/start-here/ai-agents/mcp-reference/security-privacy-and-data-boundaries.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.