outline-rbac-mcp
MCP server that provides role-based access control for Outline workspaces, allowing users to interact with docs, users, and admin tools according to their assigned role.
README
outline-rbac-mcp
Role-based access plugin for Outline, built as a standalone MCP server over the Outline REST API. No changes to the Outline server required.
Each person connects with their own Outline API key. The plugin resolves who the key belongs to and their workspace role, then only exposes the operations that role is entitled to.
How access is decided — the role graph
Roles are nodes in a directed graph; each role inherits every capability of the roles below it:
admin ──▶ member ──▶ viewer ──▶ guest
| Role | Adds capabilities |
|---|---|
| guest | view own account, read shared docs |
| viewer | read/search docs, list users, read comments |
| member | update own account, create/update/delete docs, write comments |
| admin | invite/remove/suspend/activate users, change roles, update any account, read audit log |
Effective permissions are resolved by walking the inheritance edges (BFS) and unioning capabilities.
The workflow pipeline
Every tool call flows through a staged workflow — a failure at any node short-circuits the call:
authenticate ─▶ resolve_role ─▶ authorize ─▶ execute ─▶ audit
- authenticate — verifies the API key against
auth.info - resolve_role — reads the caller's role, resolves capabilities from the graph
- authorize — rejects the call if the role lacks the tool's required capability
- execute — proxies to the Outline REST API
- audit — records actor, role, tool, outcome, and per-stage timing (admins can read it via
audit_log)
Tools
| Tool | Requires |
|---|---|
whoami, access_graph |
account.view_self (all roles) |
search_docs, read_doc, list_users |
viewer+ |
update_my_account, create_doc, update_doc, delete_doc |
member+ |
invite_user, remove_user, suspend_user, activate_user, change_user_role, audit_log |
admin |
Denied calls return DENIED: role "<role>" lacks capability "<capability>".
Install (per user)
- Create your API key in Outline: Settings → API & Apps → New API key
- Install from the packaged tarball (or from npm once published):
npm install -g ./outline-rbac-mcp-1.0.0.tgz # or: npm install -g outline-rbac-mcp
claude mcp add outline-rbac \
--env OUTLINE_URL=https://outline.knowaiclub.com \
--env OUTLINE_API_KEY=<your-personal-api-key> \
-- outline-rbac-mcp
The package also ships a Claude Code plugin manifest (.claude-plugin/plugin.json + .mcp.json), so the repo can be installed as a Claude Code plugin from a marketplace; set OUTLINE_URL and OUTLINE_API_KEY in your shell environment and the plugin's MCP server picks them up.
From source
cd outline_test && npm install
claude mcp add outline-rbac \
--env OUTLINE_URL=https://outline.knowaiclub.com \
--env OUTLINE_API_KEY=<your-personal-api-key> \
-- node /path/to/outline_test/src/server.js
Works the same in Claude Desktop / Cursor as a stdio MCP server:
{
"mcpServers": {
"outline-rbac": {
"command": "node",
"args": ["/path/to/outline_test/src/server.js"],
"env": {
"OUTLINE_URL": "https://outline.knowaiclub.com",
"OUTLINE_API_KEY": "<your-personal-api-key>"
}
}
}
}
Smoke test
TEST_KEY=<api-key> node test/smoke.js whoami access_graph 'list_users={}'
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.