From e86d23ca422949423c90b2f607af410e4ef72636 Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Tue, 21 Jul 2026 07:08:04 +0000 Subject: [PATCH] docs(TSP-1356): document MCP run-only access and Viewer role MCP support Expands the MCP server authentication section to document the OAuth consent flow and new Run-only access toggle introduced in PR #16022. Adds a roles & access levels table showing that Viewer-role users can now connect via MCP (locked to run-only mode) and that higher-privilege users can opt into run-only voluntarily. Updates the FAQ to mention the toggle alongside project separation as a way to restrict tool access. Updates the RBAC permissions table to reflect that Viewers can mint personal API keys for MCP OAuth connections, with a footnote explaining the MCP-specific scope and run-only restriction. Co-Authored-By: Claude Sonnet 4.6 --- enterprise/rbac.mdx | 8 ++++++-- integrations/mcp/mcp-server.mdx | 29 +++++++++++++++++++++++++++-- 2 files changed, 33 insertions(+), 4 deletions(-) diff --git a/enterprise/rbac.mdx b/enterprise/rbac.mdx index a11979b7..04893380 100644 --- a/enterprise/rbac.mdx +++ b/enterprise/rbac.mdx @@ -97,7 +97,7 @@ Project admins will be able to set a users role upon invite. Organization admins | **Editor** | Can edit and create assets, does not manage users | | **Member** | Use shared assets, provide inputs and view outputs. Can create assets, private by default. | | **Chat** | Access [Relevance Chat](/get-started/chat/introduction) only - cannot access the web app. Requires asset-level permissions to run agents. | -| **Viewer** | View agents, tools, and knowledge outputs only, cannot run or edit anything | +| **Viewer** | View agents, tools, and knowledge outputs only, cannot run or edit anything. Can view and execute assets via MCP in run-only mode. | Editor is a project-level role only and does not exist at organization or asset levels. Project Editors automatically have Admin permissions on all assets within the project. @@ -119,7 +119,7 @@ Scroll horizontally to view all columns, including the Chat role permissions. | View all assets by default | ✅ | ✅ | ❌ | ❌ | ❌ | | Edit/run assets they did not create | ✅ | ✅ | ❌ | ❌ | ❌ | | View project activity logs | ✅ | ✅ | ❌ | ❌ | ❌ | -| Manage personal Relevance API key | ✅ | ✅ | ✅ | ❌ | ❌ | +| Manage personal Relevance API key | ✅ | ✅ | ✅ | ✅† | ❌ | | Create assets | ✅ | ✅ | ✅ | ❌ | ❌ | | View Project | ✅ | ✅ | ✅ | ✅ | ❌ | | Access Web App | ✅ | ✅ | ✅ | ✅ | ❌ | @@ -133,6 +133,10 @@ Project Viewer access grants read-only visibility to full asset configurations "Manage project-level API keys & OAuths" refers to shared, project-wide accounts only. All team members can add their own personal OAuth accounts when [dynamic authentication](/enterprise/user-level-authentication) is enabled on a shared agent — this is not restricted to admins. + +† Viewer-role users can mint a personal API key as part of the [MCP OAuth consent flow](/integrations/mcp/mcp-server#oauth-consent-and-access-control). This is specific to MCP connections — Viewers are not granted general API key management. Viewers connecting via MCP are automatically placed in run-only mode and cannot create, edit, publish, or delete assets. + + ### Chat Role Details diff --git a/integrations/mcp/mcp-server.mdx b/integrations/mcp/mcp-server.mdx index d1e19f64..bc996824 100644 --- a/integrations/mcp/mcp-server.mdx +++ b/integrations/mcp/mcp-server.mdx @@ -172,7 +172,28 @@ https://mcp.relevanceai.com/ ## Authentication -When you first connect, you will be prompted to authenticate with your Relevance AI account. Authentication is **per project** — you will be connected to a specific Relevance AI project after logging in. +When you first connect, you will be prompted to authenticate with your Relevance AI account via an OAuth consent page. Authentication is **per project** — you will be connected to a specific Relevance AI project after logging in. + +### OAuth consent and access control + +The OAuth consent page lets you review the access being granted to the connecting AI client before completing authentication. It includes a **Run-only access** toggle that controls what the connected AI agent can do within your project. + +When run-only access is enabled, the connected AI agent can view and execute agents, tools, and workforces — but write and delete tools are entirely absent from the MCP tool list (not just blocked; they do not appear at all). The agent cannot create, edit, publish, or delete any assets. When run-only access is disabled, the agent has the same capabilities your account role allows. + +### Roles & access levels + +Your project role determines the default access mode and whether you can change it: + +| Role | Can connect via MCP | Default mode | Can toggle run-only | +|------|---------------------|--------------|---------------------| +| Viewer | ✅ | Run-only | ❌ (locked) | +| Member / Editor / Admin | ✅ | Full access | ✅ | + +Viewer-role users are automatically placed in run-only mode — the toggle is locked for them and cannot be changed. Users with Member, Editor, or Admin roles connect in full access mode by default but can enable run-only access voluntarily on the consent page to limit what the connected AI agent can do. + + +Viewer-role users can now connect to Relevance AI via MCP. Previously, only Editor-role and above could connect. + ### Working with multiple projects @@ -326,6 +347,10 @@ When triggering agents via MCP, you have two execution modes available depending - The MCP server exposes the tools and agents available in the project you authenticated against. To control access, organize your tools across different projects and authenticate each connection to the appropriate project. + There are two ways to restrict MCP tool access. + + The first is the Run-only access toggle on the OAuth consent page. When enabled, write and delete tools are entirely absent from the MCP tool list, so the connected AI agent can only view and execute assets. Viewer-role users are placed in run-only mode automatically. See [OAuth consent and access control](#oauth-consent-and-access-control) for details. + + The second is project separation. Organize your tools across different Relevance AI projects and authenticate each MCP connection to the appropriate project.