Skip to main content
hc
Submit
mcpSource-backed

Auth0 MCP Server for Claude

Connect Claude to Auth0's official local MCP server for tenant administration, application setup, Actions, logs, forms, and scoped Management API workflows.

by Auth0 · submitted by MkDev11·added 2026-06-05·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/mcp/auth0-mcp-server
Source URLs
https://auth0.com/docs/get-started/auth0-mcp-server, https://github.com/auth0/auth0-mcp-server, https://auth0.com/
Safety notes
Auth0 documents the server as beta software. Treat command behavior, available tools, requested scopes, and client setup flows as subject to change until Auth0 publishes a stable release., Start with `--read-only` or a narrow `--tools` pattern such as `auth0_list_*,auth0_get_*`. Enable create, update, deploy, or publish tools only for a scoped task and an approved tenant., The server can expose tools for applications, APIs, client grants, Actions, logs, and forms. Some of those tools can change callback URLs, token settings, Actions code, branding, and other live authentication behavior., Review every mutating tool call before approving it. A mistaken tenant change can break sign-in, weaken security settings, deploy incorrect Actions, expose callback URLs, or affect production users., Keep token lifetime and Management API scopes as small as possible when using the client-credentials setup path. Revoke or rotate credentials that were created for temporary MCP work., Use `npx @auth0/auth0-mcp-server logout` when finished or when switching tenants so local authentication state is removed from the system keychain.
Privacy notes
The local MCP server can send selected tenant operations to the Auth0 Management API and return application metadata, API identifiers, Actions code, form configuration, log events, user identifiers, IP addresses, and authentication error details into the model conversation., Prompts, MCP client logs, Claude transcripts, terminal history, screenshots, and issue comments can retain Auth0 resource names, tenant domains, client IDs, redirect URLs, organization names, and troubleshooting details outside Auth0's normal audit and retention controls., Do not paste client secrets, access tokens, refresh tokens, private keys, production user records, password-reset links, session cookies, or full log payloads into the conversation., Auth0 says the server stores credentials in the system keychain and redacts sensitive response fields such as client secrets and tokens. Still review assistant output before copying it into tickets, commits, runbooks, or shared chats., The server collects anonymized analytics by default according to Auth0's README. Set `AUTH0_MCP_ANALYTICS=false` when analytics collection is not approved for the environment.
Author
Auth0
Submitted by
MkDev11
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

10 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

6 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    Listing has review metadata.

    Done

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

6 prerequisites to line up before setup. Have accounts and credentials ready first.

0/6 ready
Account & credentials3Install & runtime2Permissions & scopes110 minutes

Safety & privacy surface

Safety & privacy surface

6 safety and 5 privacy notes across 6 risk areas. Review closely: credentials & tokens, permissions & scopes.

6 areas
  • SafetyPermissions & scopesAuth0 documents the server as beta software. Treat command behavior, available tools, requested scopes, and client setup flows as subject to change until Auth0 publishes a stable release.
  • SafetyPermissions & scopesStart with `--read-only` or a narrow `--tools` pattern such as `auth0_list_*,auth0_get_*`. Enable create, update, deploy, or publish tools only for a scoped task and an approved tenant.
  • SafetyCredentials & tokensThe server can expose tools for applications, APIs, client grants, Actions, logs, and forms. Some of those tools can change callback URLs, token settings, Actions code, branding, and other live authentication behavior.
  • SafetyGeneralReview every mutating tool call before approving it. A mistaken tenant change can break sign-in, weaken security settings, deploy incorrect Actions, expose callback URLs, or affect production users.
  • SafetyCredentials & tokensKeep token lifetime and Management API scopes as small as possible when using the client-credentials setup path. Revoke or rotate credentials that were created for temporary MCP work.
  • SafetyData retentionUse `npx @auth0/auth0-mcp-server logout` when finished or when switching tenants so local authentication state is removed from the system keychain.
  • PrivacyData retentionThe local MCP server can send selected tenant operations to the Auth0 Management API and return application metadata, API identifiers, Actions code, form configuration, log events, user identifiers, IP addresses, and authentication error details into the model conversation.
  • PrivacyExecution & processesPrompts, MCP client logs, Claude transcripts, terminal history, screenshots, and issue comments can retain Auth0 resource names, tenant domains, client IDs, redirect URLs, organization names, and troubleshooting details outside Auth0's normal audit and retention controls.
  • PrivacyCredentials & tokensDo not paste client secrets, access tokens, refresh tokens, private keys, production user records, password-reset links, session cookies, or full log payloads into the conversation.
  • PrivacyCredentials & tokensAuth0 says the server stores credentials in the system keychain and redacts sensitive response fields such as client secrets and tokens. Still review assistant output before copying it into tickets, commits, runbooks, or shared chats.
  • PrivacyTelemetryThe server collects anonymized analytics by default according to Auth0's README. Set `AUTH0_MCP_ANALYTICS=false` when analytics collection is not approved for the environment.

Safety notes

  • Auth0 documents the server as beta software. Treat command behavior, available tools, requested scopes, and client setup flows as subject to change until Auth0 publishes a stable release.
  • Start with `--read-only` or a narrow `--tools` pattern such as `auth0_list_*,auth0_get_*`. Enable create, update, deploy, or publish tools only for a scoped task and an approved tenant.
  • The server can expose tools for applications, APIs, client grants, Actions, logs, and forms. Some of those tools can change callback URLs, token settings, Actions code, branding, and other live authentication behavior.
  • Review every mutating tool call before approving it. A mistaken tenant change can break sign-in, weaken security settings, deploy incorrect Actions, expose callback URLs, or affect production users.
  • Keep token lifetime and Management API scopes as small as possible when using the client-credentials setup path. Revoke or rotate credentials that were created for temporary MCP work.
  • Use `npx @auth0/auth0-mcp-server logout` when finished or when switching tenants so local authentication state is removed from the system keychain.

Privacy notes

  • The local MCP server can send selected tenant operations to the Auth0 Management API and return application metadata, API identifiers, Actions code, form configuration, log events, user identifiers, IP addresses, and authentication error details into the model conversation.
  • Prompts, MCP client logs, Claude transcripts, terminal history, screenshots, and issue comments can retain Auth0 resource names, tenant domains, client IDs, redirect URLs, organization names, and troubleshooting details outside Auth0's normal audit and retention controls.
  • Do not paste client secrets, access tokens, refresh tokens, private keys, production user records, password-reset links, session cookies, or full log payloads into the conversation.
  • Auth0 says the server stores credentials in the system keychain and redacts sensitive response fields such as client secrets and tokens. Still review assistant output before copying it into tickets, commits, runbooks, or shared chats.
  • The server collects anonymized analytics by default according to Auth0's README. Set `AUTH0_MCP_ANALYTICS=false` when analytics collection is not approved for the environment.

Prerequisites

  • Auth0 account and approval to connect an MCP client to the selected tenant.
  • Node.js 18 or newer with `npx` available to the MCP client.
  • MCP-capable client such as Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, or another stdio-compatible client.
  • Interactive browser access for the OAuth 2.0 device authorization setup flow, unless using the documented client-credentials path for private cloud tenants.
  • Auth0 Management API scopes that match the intended work, starting with read-only scopes whenever possible.
  • A non-production or development tenant for first-time setup and testing of mutating tools.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
10 minutes
Difficulty
intermediate
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "auth0": {
      "command": "npx",
      "args": ["-y", "@auth0/auth0-mcp-server", "run", "--read-only"],
      "capabilities": ["tools"],
      "env": {
        "AUTH0_MCP_ANALYTICS": "false"
      }
    }
  }
}

About this resource

Content

Auth0 MCP Server is Auth0's official local Model Context Protocol server for connecting Claude and other MCP-capable clients to Auth0 tenant administration workflows. It runs through the @auth0/auth0-mcp-server npm package, uses Auth0 authentication, and exposes Management API tools according to the scopes and tool filters you grant during setup.

The best first use is read-only tenant inspection: list applications, inspect API resource servers, retrieve Actions, and review authentication logs before drafting a change. After you have reviewed the exact tools and scopes, the same server can assist with controlled create, update, deploy, and publish workflows for Auth0 resources.

Features

  • Official Auth0 documentation page for setup, authentication, client support, tool access controls, and troubleshooting.
  • Public auth0/auth0-mcp-server source repository with an MIT license.
  • Published npm package at @auth0/auth0-mcp-server.
  • Local stdio MCP server that can be configured for Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI, and other compatible clients.
  • OAuth 2.0 device authorization setup for standard Auth0 tenants.
  • Client-credentials setup path for private cloud tenants and other non-interactive cases.
  • Read-only mode through --read-only or AUTH0_MCP_READ_ONLY=true.
  • Tool filtering with glob patterns through --tools or AUTH0_MCP_TOOLS.
  • Documented Management API scope selection during initialization.
  • System keychain credential storage, logout command, and redaction of sensitive fields in tool responses.
  • Optional analytics opt-out with AUTH0_MCP_ANALYTICS=false.

Tool Surface

Auth0 documents tools for these resource groups:

  • Applications: list, inspect, create, and update Auth0 applications.
  • Resource servers: list, inspect, create, and update APIs and scopes.
  • Application grants: create grants between applications and APIs.
  • Actions: list, inspect, create, update, and deploy Actions.
  • Logs: list recent tenant logs and retrieve a specific log event.
  • Forms: list, inspect, create, update, and publish forms.

Use read-only mode when your task is investigation, support triage, onboarding, or documentation. Move to mutating tools only when the tenant, scope set, and approval path are explicit.

Installation

Auth0 Initialization

Configure the Auth0 MCP Server with the safest starter mode:

npx @auth0/auth0-mcp-server init --read-only

For a narrower read-only tool set, use Auth0's documented tool filters:

npx @auth0/auth0-mcp-server init --tools 'auth0_list_*,auth0_get_*'

The initialization flow opens a browser for Auth0 authorization and lets you select the tenant and scopes. Restart your MCP client after setup.

MCP Client Config

Use this stdio configuration when manually configuring a compatible client:

{
  "mcpServers": {
    "auth0": {
      "command": "npx",
      "args": ["-y", "@auth0/auth0-mcp-server", "run", "--read-only"],
      "capabilities": ["tools"],
      "env": {
        "AUTH0_MCP_ANALYTICS": "false"
      }
    }
  }
}

To enable a limited non-read-only surface, replace --read-only with a specific tool pattern and matching scopes. For example, a development-tenant workflow for applications might use --tools 'auth0_*_application*' only after the selected tenant and permissions are approved.

Use Cases

  • Ask Claude to list Auth0 applications and summarize callback URL drift before changing a web app configuration.
  • Review recent failed login logs, blocked attempts, or tenant errors while debugging an authentication incident.
  • Inspect resource server scopes before drafting an API authorization update.
  • Retrieve an Action's current code and ask Claude to explain what it changes in the login or token flow.
  • Create or update a development tenant application after confirming redirect URLs, allowed origins, token settings, and ownership.
  • Draft a new Action in a non-production tenant, review the code manually, then approve deployment only after tests pass.
  • Compare form configuration or branding across tenants before publishing a change.

Safety Checklist

  • Use a development tenant for first-time setup and mutating workflows.
  • Prefer --read-only until the task genuinely requires create, update, deploy, or publish tools.
  • Grant only the Auth0 Management API scopes required for the current task.
  • Confirm the selected tenant before approving tool calls.
  • Keep MCP client approval prompts enabled for every mutating operation.
  • Do not expose Auth0 secrets or production user records in prompts.
  • Run npx @auth0/auth0-mcp-server session to check the active tenant and authentication state when unsure.
  • Run npx @auth0/auth0-mcp-server logout after temporary administration work.

Source Links

#auth0#authentication#identity#security#mcp

Source citations

Add this badge to your README

Show that Auth0 MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/auth0-mcp-server.svg)](https://heyclau.de/entry/mcp/auth0-mcp-server)

How it compares

Auth0 MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field
Auth0 MCP Server for Claude

Connect Claude to Auth0's official local MCP server for tenant administration, application setup, Actions, logs, forms, and scoped Management API workflows.

Open dossier
Okta MCP Server for Claude

Connect Claude to Okta's official self-hosted MCP server for scoped identity administration, users, groups, applications, policies, logs, brands, and tenant management workflows.

Open dossier
AWS Labs logoAWS IAM MCP Server

Official AWS Labs MCP server for AWS Identity and Access Management that lets AI assistants inspect and manage IAM users, roles, groups, policies, and access keys, with policy simulation and an opt-in read-only mode.

Open dossier
Descope MCP Server for Claude

Manage your Descope identity project from Claude — search users, configure auth flows, inspect audit logs, manage tenants, and search Descope documentation — with the official Descope remote MCP server hosted at mcp.descope.com.

Open dossier
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersMkDev11MkDev11jaso0n0818—
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Brand——AWS Labs logoAWS Labs—
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorAuth0OktaAWS LabsDescope
Added2026-06-052026-06-052026-06-212026-06-18
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Harness
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓Auth0 documents the server as beta software. Treat command behavior, available tools, requested scopes, and client setup flows as subject to change until Auth0 publishes a stable release. Start with `--read-only` or a narrow `--tools` pattern such as `auth0_list_*,auth0_get_*`. Enable create, update, deploy, or publish tools only for a scoped task and an approved tenant. The server can expose tools for applications, APIs, client grants, Actions, logs, and forms. Some of those tools can change callback URLs, token settings, Actions code, branding, and other live authentication behavior. Review every mutating tool call before approving it. A mistaken tenant change can break sign-in, weaken security settings, deploy incorrect Actions, expose callback URLs, or affect production users. Keep token lifetime and Management API scopes as small as possible when using the client-credentials setup path. Revoke or rotate credentials that were created for temporary MCP work. Use `npx @auth0/auth0-mcp-server logout` when finished or when switching tenants so local authentication state is removed from the system keychain.✓Okta MCP Server connects to Okta Admin Management APIs. Even ordinary natural-language prompts can translate into identity administration actions, so use a dedicated app integration and the smallest useful API scope set. The server uses scope-based tool loading. Tools whose required OAuth scope is not present in `OKTA_SCOPES` are removed from the tool list, and runtime scope guards provide another permission check before API calls. Prefer read scopes such as `okta.users.read`, `okta.groups.read`, and `okta.logs.read` for investigation. Add `okta.<resource>.manage` scopes only for an approved change window and an explicit task. Manage scopes can create, update, activate, deactivate, delete, assign, or otherwise change users, groups, applications, policies, brands, templates, custom domains, email domains, and device assurance policies. Destructive operations use MCP elicitation when the client supports it and return a fallback confirmation payload for clients that do not. Keep MCP client approval prompts enabled and manually review every mutating action. Private Key JWT is intended for browserless automation, but it introduces a long-lived private key. Store the key outside source control, rotate it on schedule, and restrict the app's admin role and scopes. Device Authorization Grant is convenient for interactive use, but Docker setups may persist tokens in a mounted keyring volume. Treat that volume as sensitive and remove it when the temporary workflow ends. MCP usage consumes Okta Management API rate limits. Avoid broad loops, unbounded list operations, or repeated audit-report prompts against a production org.✓Run with the `--readonly` flag (shown above) to block all mutating operations. Without it the server can create and delete IAM users, roles, groups, policies, and access keys — high-impact identity changes — so enable write access only deliberately and with scoped permissions. IAM controls account-wide access; a misused write operation can grant or revoke permissions broadly. Prefer non-production accounts while evaluating, and use policy simulation to test changes before applying them. This server acts on real IAM with your AWS credentials; scope the profile tightly and run it only on a trusted host.✓Sessions start in read-only mode. Write operations require explicit elevation and out-of-band one-time passcode confirmation — preventing accidental changes to production auth infrastructure. The server has access to your Descope project including user PII, tenant config, and auth secrets; scope usage to least-privilege workflows.
Privacy notes✓The local MCP server can send selected tenant operations to the Auth0 Management API and return application metadata, API identifiers, Actions code, form configuration, log events, user identifiers, IP addresses, and authentication error details into the model conversation. Prompts, MCP client logs, Claude transcripts, terminal history, screenshots, and issue comments can retain Auth0 resource names, tenant domains, client IDs, redirect URLs, organization names, and troubleshooting details outside Auth0's normal audit and retention controls. Do not paste client secrets, access tokens, refresh tokens, private keys, production user records, password-reset links, session cookies, or full log payloads into the conversation. Auth0 says the server stores credentials in the system keychain and redacts sensitive response fields such as client secrets and tokens. Still review assistant output before copying it into tickets, commits, runbooks, or shared chats. The server collects anonymized analytics by default according to Auth0's README. Set `AUTH0_MCP_ANALYTICS=false` when analytics collection is not approved for the environment.✓Okta MCP can return user profiles, group memberships, application metadata, assignments, policy settings, sign-in failures, System Log events, IP addresses, device context, brand assets, email templates, custom domains, and other tenant administration data into the model conversation. Prompts, tool results, MCP client logs, screenshots, debug files, and generated reports can retain Okta identifiers and security event details outside the Okta System Log and normal tenant retention controls. Do not paste API tokens, private keys, client secrets, session cookies, recovery links, full user exports, raw System Log dumps, customer identifiers, or production incident data into prompts, issue comments, or PR descriptions. If you enable `OKTA_LOG_LEVEL=DEBUG` or `OKTA_LOG_FILE`, store logs in an approved location and scrub them before sharing because troubleshooting output can include tenant URLs, resource identifiers, request context, and authentication details.✓IAM user/role/group names, ARNs, policy documents, and account metadata can be returned through tool calls and exposed to the model. Access key IDs and other identity material may appear in responses; never expose secret access keys, and keep account identifiers and policy contents out of public prompts, issues, and screenshots.✓User profiles, tenant configurations, auth flow definitions, audit log entries, and API key metadata from your Descope project are surfaced in Claude's context. Authenticated via your Descope account — no API keys stored in the MCP configuration.
Prerequisites
  • Auth0 account and approval to connect an MCP client to the selected tenant.
  • Node.js 18 or newer with `npx` available to the MCP client.
  • MCP-capable client such as Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, or another stdio-compatible client.
  • Interactive browser access for the OAuth 2.0 device authorization setup flow, unless using the documented client-credentials path for private cloud tenants.
  • Okta org, such as an Okta Integrator Free Plan org, with admin permissions for the resources Claude should access.
  • Okta admin role assignment that matches the intended workflow, not a broad super-admin grant by default.
  • Okta app integration created for the MCP server with either Device Authorization Grant for interactive use or Private Key JWT for browserless automation.
  • Okta API scopes granted to the app and repeated in `OKTA_SCOPES`, starting with read-only scopes such as `okta.users.read`, `okta.groups.read`, and `okta.logs.read`.
  • An AWS account with IAM access and permissions for the IAM read (and, if write is enabled, manage) operations you intend to use.
  • Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package.
  • AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) scoped least-privilege; read-only IAM permissions are enough for the recommended `--readonly` mode.
  • An MCP client that supports stdio servers; the server runs locally on the same host as the client.
  • A Descope account — authenticate via your Descope account when prompted on first tool use.
  • An MCP client such as Claude Code or Claude Desktop.
Install
npx @auth0/auth0-mcp-server init --read-only
git clone https://github.com/okta/okta-mcp-server.git
uvx awslabs.iam-mcp-server@latest --readonly
claude mcp add --transport http descope https://mcp.descope.com
Config
{
  "mcpServers": {
    "auth0": {
      "command": "npx",
      "args": ["-y", "@auth0/auth0-mcp-server", "run", "--read-only"],
      "capabilities": ["tools"],
      "env": {
        "AUTH0_MCP_ANALYTICS": "false"
      }
    }
  }
}
{
  "mcpServers": {
    "okta-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/okta-mcp-server",
        "okta-mcp-server"
      ],
      "env": {
        "OKTA_ORG_URL": "https://your-org.okta.com",
        "OKTA_CLIENT_ID": "your-client-id",
        "OKTA_SCOPES": "okta.users.read okta.groups.read okta.logs.read"
      }
    }
  }
}
{
  "mcpServers": {
    "awslabs.iam-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.iam-mcp-server@latest", "--readonly"],
      "env": {
        "AWS_PROFILE": "${AWS_PROFILE}",
        "AWS_REGION": "us-east-1",
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "descope": {
      "type": "http",
      "url": "https://mcp.descope.com"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Source-backed guides for putting this to work.

OAuth Patterns For MCP Server Authentication

Configure MCP OAuth with scopes, callbacks, and secure token storage patterns.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Auditing MCP Client Configuration Before Team Rollout

Audit MCP client configuration before sharing it with a team.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by YB0y

MCP OAuth Token Audience Checklist

Review remote MCP OAuth and token-audience handling before connecting clients.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by JSONbored

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.