Model Context Protocol server for the Microsoft Entra SCIM 2.0 Provisioning API (GA April 2026). Exposes user and group lifecycle operations against https://graph.microsoft.com/rp/scim as MCP tools for AI agents
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
claude mcp add entra-scim-mcp -- npx -y --package{
"mcpServers": {
"entra-scim-mcp": {
"command": "npx",
"args": ["-y", "--package"]
}
}
}MCP Servers overview
# entra-scim-mcp
Model Context Protocol server for the Microsoft Entra SCIM 2.0 Provisioning API (GA April 2026). Exposes user and group lifecycle operations against `https://graph.microsoft.com/rp/scim` as MCP tools for agents like Claude.
## What you can do with it
- Discover the tenant's SCIM capabilities (`get_service_provider_config`, `list_resource_types`, `list_schemas`)
- Provision, read, update, and deprovision users — including Custom Security Attributes and lifecycle attrs
- Create, update, and delete groups, and manage membership with the API's strict PATCH rules respected automatically
## Prerequisites
Before this server can talk to your tenant, complete the one-time setup in the [Microsoft docs](https://learn.microsoft.com/entra/identity/app-provisioning/enable-scim-api):
1. Entra ID P1 (or any SKU containing P1) and an Azure subscription to link for billing.
2. Enable the **SCIM Provisioning API** in **ID Governance → Dashboard** and link a billing resource group.
3. Register an application with the Microsoft Graph **application** permissions you need:
- `User.ReadWrite.All`, `Group.ReadWrite.All` (core lifecycle)
- `CustomSecAttributeAssignment.ReadWrite.All`, `CustomSecAttributeDefinition.Read.All` (CSA tools)
- `User-LifeCycleInfo.ReadWrite.All` (lifecycle tools)
- `User-Mail.ReadWrite.All`, `User-Phone.ReadWrite.All`, `User.EnableDisableAccount.All` (least-privilege alternatives)
Grant admin consent.
4. Create **either** a client secret **or** upload a PEM client certificate.
Every SCIM API call is billed — this server does not batch beyond what the API requires.
## Try it without an Entra tenant
The package ships a local mock of the Entra SCIM API (`entra-scim-mock-server`) so you can drive every tool with zero Azure setup and zero API billing:
```bash
# shell 1 — start the mock (seeds a small demo tenant)
npx -y --package entra-scim-mcp entra-scim-mock-server
```
Then point the MCP server at it:
```json
{
"mcpServers": {
"entra-scim-mock": {
"command": "npx",
"args": ["-y", "entra-scim-mcp"],
"env": {
"ENTRA_SCIM_BASE_URL": "http://127.0.0.1:8990",
"ENTRA_SCIM_STATIC_TOKEN": "dev-token"
}
}
}
}
```
Mock flags: `--port`, `--token`, `--seed <file.json>`, `--no-seed`, `--capture <file.jsonl>` (log every request/response), `--validator-compat` (RFC-standard behavior for the [Microsoft SCIM Validator](https://scimvalidator.microsoft.com) — see [docs/scim-validator.md](node/docs/scim-validator.md)).
## Install / run
The server is a stdio MCP server, designed to be launched by your MCP client (Claude Desktop, Claude Code, etc.).
```bash
npx -y entra-scim-mcp
```
Required environment:
| Var | Required | Description |
| --- | --- | --- |
| `ENTRA_TENANT_ID` | yes | Directory (tenant) GUID |
| `ENTRA_CLIENT_ID` | yes | App registration (client) GUID |
| `ENTRA_CLIENT_SECRET` | one of | Client secret value (dev) |
| `ENTRA_CLIENT_CERT_PATH` | one of | Path to a PEM containing the certificate **and** private key |
| `ENTRA_CLIENT_CERT_PASSWORD` | optional | Password if the PEM is encrypted |
Set exactly one of `ENTRA_CLIENT_SECRET` or `ENTRA_CLIENT_CERT_PATH`.
### Development / testing environment variables
| Var | Description |
| --- | --- |
| `ENTRA_SCIM_BASE_URL` | Override the SCIM base URL (default `https://graph.microsoft.com/rp/scim`). Point it at the local mock. |
| `ENTRA_SCIM_STATIC_TOKEN` | Use a fixed bearer token instead of Azure AD. **Guardrails:** requires `ENTRA_SCIM_BASE_URL`, refuses any `*.microsoft.com` / `*.microsoft.us` host, warns on non-loopback hosts, and cannot be combined with a real credential. Tenant/client IDs are not required in this mode. |
| `ENTRA_SCIM_DRY_RUN` | Set to `1`: tools run all client-side validation, then return the exact request that would have been sent instead of sending it. No token is acquired — works with zero credential config. |
Dry-run results come back as a successful payload:
```json
{
"dryRun": true,
"request": {
"method": "DELETE",
"url": "https://graph.microsoft.com/rp/scim/users/u-1",
"headers": {}
}
}
```
(DELETE carries no `Accept` header — the API rejects a specific JSON media type there. Every other method sends `Accept: application/json`.)
Multi-request tools (e.g. `add_group_members` beyond 20 ids) surface only their first chunked request in dry-run.
### Claude Desktop config
`~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
```json
{
"mcpServers": {
"entra-scim": {
"command": "npx",
"args": ["-y", "entra-scim-mcp"],
"env": {
"ENTRA_TENANT_ID": "00000000-0000-0000-0000-000000000000",
"ENTRA_CLIENT_ID": "11111111-1111-1111-1111-111111111111",
"ENTRA_CLIENT_SECRET": "..."
}
}
}
}
```
For production, swap the secret for a certificate:
```json
{
"env": {
"ENTRA_TENANT_ID": "...",
"ENTRA_CLIENT_ID": "...",
"ENTRA_CLIENT_CERT_PATH": "/secure/path/entra-scim-mcp.pem"
}
}
```
## Tools
The **Kind** column is the tool's MCP annotations, which is what a client reads
when it decides whether a call needs your approval: *read* is `readOnlyHint`,
*add* is a write that only creates (`destructiveHint: false`), *overwrite* is a
write that discards or replaces state with no undo through this API
(`destructiveHint: true`).
| Tool | Kind | Purpose |
| --- | --- | --- |
| `get_service_provider_config` | read | One-shot capability discovery. Static per API version — fetch once and reuse. |
| `list_resource_types` | read | Enumerate SCIM resource types (User, Group). |
| `list_schemas` | read | Enumerate SCIM schemas and Entra extensions, with each attribute's type, mutability and default-return. Check a patch path here before building it. |
| `list_users` | read | List users; supports the API's restricted filter (eq/ew, and-only) and cursor pagination. Also how you resolve a `userName` to the object id every other user tool wants. |
| `get_user` | read | Read a single user by id with optional attribute projection. Neither CSAs nor group membership are ever included. |
| `provision_user` | add | Create a user with the required attribute set enforced (userName, password, displayName, name.givenName, name.familyName, mailNickname). |
| `update_user` | overwrite | PATCH a user; blocks `remove` of mailNickname and enforces `[type eq "work"]` on address paths. |
| `deprovision_user` | overwrite | DELETE a user. Soft-deleted for 30 days, restorable only via Graph; also strips every group membership. |
| `update_user_lifecycle` | overwrite | Set lifecycle attrs (e.g. `employeeLeaveDateTime`) — which Lifecycle Workflows can fire off. Requires `User-LifeCycleInfo.ReadWrite.All`. |
| `get_user_custom_security_attributes` | read | Read a user's CSAs, projected by attribute set. `attributeSets` is **required** — the API rejects the bare extension URN, and CSAs never come back from a plain `get_user`. |
| `update_user_custom_security_attributes` | overwrite | PATCH CSAs on a user. `remove`, or `replace` with an empty array, deletes an assignment. |
| `list_groups` | read | List groups with the API's restricted filter set. A `members.value` filter is the only way to read membership. |
| `get_group` | read | Read a single group (members are NOT returned — use `list_groups` with a `members.value` filter). |
| `create_group` | add | POST a group. Sets `mailEnabled`, `securityEnabled`, `mailNickname`, `description` via the Entra extension. `displayName` is not unique. |
| `update_group` | overwrite | PATCH group attributes only (membership ops are rejected here; type flags are fixed at creation). |
| `add_group_members` | add | Add ≥1 users to a group — auto-chunks at 20 ids per PATCH (API cap), one Operation per PATCH. Idempotent. On a mid-sequence failure it reports `addedMemberIds` / `failedMemberIds` / `notAttemptedMemberIds` so partial writes are never silent. |
| `remove_group_member` | overwrite | Remove a single user from a group (the API allows only one removal per PATCH, with no other ops). A 404 here usually means *not a member*, not *no such group*. |
| `delete_group` | overwrite | DELETE a group. Unified groups are recoverable for 30 days via Graph; security groups are not. |
### What the agent is told, and where
A model never reads this file, so everything it needs has to travel in the
protocol. Three places carry it, and the split is deliberate:
- **Server instructions**, sent once in the handshake, hold what is true of
every tool: ids rather than names, membership being readable in one direction
only, CSAs being invisible to ordinary reads, the narrow filter grammar, and
that every call is a billed Graph request. Repeating that in eighteen
descriptions would cost more context than it bought.
- **Tool descriptions** hold what is specific to one tool, including the
failure modes worth pre-empting — the 404 that names the group when the user
simply is not a member, the mailNickname that cannot be removed once set, the
second `provision_user` that conflicts rather than merges.
- **Input descriptions** hold per-argument syntax. The three PATCH tools each
carry their own `path` example, because path syntax is the one thing here
that cannot be guessed: the API accepts a narrow subset of RFC 7644, and the
subset differs between ordinary attributes and CSAs.
With `ENTRA_SCIM_DRY_RUN=1` the instructions gain a paragraph saying so, since
a dry-run result is shaped like a success and would otherwise be reported as a
change that landed.
`test/tool-metadata.test.ts` enforces all of this: every tool carries
annotations, read-only and write sets are pinned by name, every input has a
description, and the PATCH tools must show a URN. A new tool that defaults to
looking read-only fails the suite.
## What this server enforces for you
The Entra SCIM API has constraints that areWhat people ask about entra-scim-mcp
What is darrenjrobinson/entra-scim-mcp?
+
darrenjrobinson/entra-scim-mcp is mcp servers for the Claude AI ecosystem. Model Context Protocol server for the Microsoft Entra SCIM 2.0 Provisioning API (GA April 2026). Exposes user and group lifecycle operations against https://graph.microsoft.com/rp/scim as MCP tools for AI agents It has 0 GitHub stars and its last recorded update is dated 2026-08-25.
How do I install entra-scim-mcp?
+
You can install entra-scim-mcp by cloning the repository (https://github.com/darrenjrobinson/entra-scim-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is darrenjrobinson/entra-scim-mcp safe to use?
+
Our security agent has analyzed darrenjrobinson/entra-scim-mcp and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains darrenjrobinson/entra-scim-mcp?
+
darrenjrobinson/entra-scim-mcp is maintained by darrenjrobinson. The last recorded GitHub activity is dated 2026-08-25, with 0 open issues.
Are there alternatives to entra-scim-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy entra-scim-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/darrenjrobinson-entra-scim-mcp)<a href="https://claudewave.com/repo/darrenjrobinson-entra-scim-mcp"><img src="https://claudewave.com/api/badge/darrenjrobinson-entra-scim-mcp" alt="Featured on ClaudeWave: darrenjrobinson/entra-scim-mcp" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!