Auth0 Mcp ServerCAUTION
Connect LLMs and AI agents to Auth0 Management APIs via an MCP server. Use natural-language commands to create apps, deploy Actions, and query logs—runs locally and supports interactive tenant authentication for secure Auth0 administration from AI tools/CLIs.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://opensource.org/licenses/MIT) [](https://nodejs.org/) [](https://www.npmjs.com/package/@auth0/auth0-mcp-server) [](https://www.npmjs.com/package/@auth0/auth0-mcp-server) [](https://deepwiki.com/auth0/auth0-mcp-server)
📚 Documentation • 🚀 Getting Started • 💻 Supported Tools • 💬 Feedback
MCP (Model Context Protocol) is an open protocol introduced by Anthropic that standardizes how large language models communicate with external tools, resources or remote services.
Connect Claude, Cursor, or Windsurf to your Auth0 tenant to create apps, deploy Actions, debug logs, and manage users — all without touching the dashboard.
[!CAUTION] Beta Software Notice: This software is currently in beta and is provided AS IS without any warranties. - Features, APIs, and functionality may change at any time without notice - Not recommended for production use or critical workloads - Support during the beta period is limited - Issues and feedback can be reported through the GitHub issue tracker By using this beta software, you acknowledge and accept these conditions.
The Auth0 MCP Server integrates with LLMs and AI agents, allowing you to perform various Auth0 management operations
d75fcdd02832OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add auth0-mcp-server -- npx -y @auth0/[email protected] run
Exposed tools (24)
14 read · 10 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
auth0_create_action | write | Create a new Auth0 action |
auth0_create_application | write | Create application |
auth0_create_form | write | Create a new Auth0 form |
auth0_create_resource_server | write | Create a new Auth0 resource server (API). Use RS256 for the signing_alg unless otherwise specified. |
auth0_deploy_action | write | Deploy an Auth0 action to make it live. |
auth0_get_action | read | Get details about a specific Auth0 action |
auth0_get_application | read | Get details about a specific Auth0 application |
auth0_get_form | read | Get details about a specific Auth0 form |
auth0_get_log | read | Get a specific log entry by ID |
auth0_get_quickstart_guide | read | Fetch and return the Auth0 quickstart implementation prompt for a specific framework. |
auth0_get_resource_server | read | Get details about a specific Auth0 resource server |
auth0_list_actions | read | List all actions in the Auth0 tenant |
auth0_list_applications | read | List all applications in the Auth0 tenant or search by name |
auth0_list_forms | read | List all forms in the Auth0 tenant |
auth0_list_logs | read | List logs from the Auth0 tenant |
auth0_list_resource_servers | read | List all resource servers (APIs) in the Auth0 tenant |
auth0_onboarding | read | Onboard a project with Auth0. Creates an Auth0 application with the correct |
auth0_save_credentials_to_file | write | Save Auth0 application credentials to the project |
auth0_update_action | write | Update an existing Auth0 action |
auth0_update_application | write | Update an existing Auth0 application. After updating, always inform the user about any automatically applied settings (such as skip_non_verifiable_callback_uri_confirmation_prompt). |
auth0_update_form | write | Update an existing Auth0 form |
auth0_update_resource_server | write | Update an existing Auth0 resource server |
schema_tool | read | Tool with a declared input schema |
test_tool | read | Test tool |
Trust audit
CAUTIONgrade B · trust 84/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (11 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (22)
callback_url: {callback_url: callbackUrl,
callback_url: callbackUrl,
callback_url?: string;
callback_url: callbackUrl,
.mcpbignore
.prettierignore
.shiprc
.version
const packageJson = require('../../package.json');const packageJson = require('../../package.json');import { requestClientCredentialsAuthorization } from '../../src/auth/client-credentials-flow';import { keychain } from '../../src/utils/keychain';vi.mock('../../src/utils/logger', () => ({expect(hasNonVerifiableCallbacks(['http://127.0.0.1:3000/callback'])).toBe(true);
expect(hasNonVerifiableCallbacks(['http://127.0.0.2:8080/callback'])).toBe(true);
expect(hasNonVerifiableCallbacks(['http://127.255.255.255/callback'])).toBe(true);
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. If you have not received a response for our team (apologies f
@github/keytar, @modelcontextprotocol/sdk, auth0, chalk, commander, debug, dotenv, jwt-decode
3. **Resource-Based Access Control**: You can configure different instances of the MCP server with different tool sets based on specific needs - development environments might need full access, while
assets/auth0-mcp-example-demo.gif
assets/mcp-banner-light.png
Gates applied: no_behavioural_pass.
d75fcdd02832full audit observations/trust-audit/mcp-server/auth0__auth0-mcp-server.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | d75fcdd02832 | CAUTION | B | 84 | first audit |
Questions
What is the @auth0/auth0-mcp-server MCP server?
Connect LLMs and AI agents to Auth0 Management APIs via an MCP server. Use natural-language commands to create apps, deploy Actions, and query logs—runs locally and supports interactive tenant authentication for secure Auth0 administration from AI tools/CLIs.
What tools does @auth0/auth0-mcp-server expose?
24 in total: 14 read-only, 10 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @auth0/auth0-mcp-server safe to connect to an agent?
With care. The audit graded it B (84/100) and found 22 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does @auth0/auth0-mcp-server need?
It reads AUTH0_CLIENT_ID, AUTH0_DOMAIN, AUTH0_MCP_ANALYTICS, AUTH0_MCP_DEBUG, AUTH0_MCP_READ_ONLY, AUTH0_MCP_TOOLS, AUTH0_TENANT_NAME, AUTH0_TOKEN and SMITHERY_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does @auth0/auth0-mcp-server run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @auth0/auth0-mcp-server at 0.1.0-beta.19.
How current is this page?
The grade is for one exact copy of the source (d75fcdd02832), read on 2026-10-12. The repository is watched and re-audited when it changes.