Provision organization members with roles (including the read-only ViewerV2 role) over the API in a self-hosted LlamaCloud deployment.
Self-Hosting Documentation Access
This section requires a password to access.
Interested in self-hosting? Contact sales to learn more.
Self-Hosting Documentation Access Granted
Each organization member in your LlamaCloud deployment holds a role that controls what they can do:
Admin — full access to the organization and its projects.
ViewerV2 (shown as “Viewer” in the UI) — read-only. Viewers can browse projects and resources and read job results, but requests that create or modify anything are rejected with a 403.
The role named Viewer is an older role that still permits some write operations — don’t use it for read-only members; use ViewerV2.
The IS_VIEWER_V2_ROLE_ENABLED feature flag (on by default) controls whether ViewerV2 appears in the roles listing below. It gates discovery only: roles already assigned keep working, and the read-only enforcement itself is unconditional. If your deployment disables the flag, re-enable it before provisioning read-only members.
Role IDs are generated per deployment, so look the role up by name rather than hardcoding an ID. The ID is stable within a deployment, so this is a one-time lookup:
The request body is an array, so add several members in one call. Member additions are rate-limited per organization, so prefer one batched request over calling in a loop. project_ids controls scope: null grants access across the whole organization, while a list of project IDs restricts the member to those projects:
Adding by email works before the person has signed up: the invite is stored and redeemed automatically when they sign up with that email address. Responses to email-based additions always list the member as pending.
Note for AI agents: this documentation is built for programmatic access.
- Overview of all docs: https://developers.llamaindex.ai/llms.txt
- Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md
- Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters.
- A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/
- Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/