Agent 与自动化 4.0 · 优秀 2026-07-29 · 文章

WorkOS MCP: Manage your WorkOS account from any AI agent

WorkOS 用远程 MCP 暴露管理面,并刻意用 discover-then-execute 四工具设计和权限/密钥剥离MCP 经 OAuth 继承操作者仪表盘角色,覆盖组织SSODirectory Sync用户会话审计日志等上百操作;不暴露铸钥模拟登录计费与账号级管理,密钥类字段在进模型上下文前剥离

打开原文回到归档

WorkOS MCP: Manage your WorkOS account from any AI agent

中文导读

WorkOS 用远程 MCP 暴露管理面,并刻意用 discover-then-execute 四工具设计和权限/密钥剥离。MCP 经 OAuth 继承操作者仪表盘角色,覆盖组织、SSO、Directory Sync、用户会话、审计日志等上百操作;不暴露铸钥、模拟登录、计费与账号级管理,密钥类字段在进模型上下文前剥离。

为什么值得关注

Agent 能管 SSO/用户/审计,但铸钥、模拟登录、密钥字段默认不准进上下文

原文摘录

WorkOS MCP: Manage your WorkOS account from any AI agent

原文链接: https://workos.com/blog/management-mcp-server

In this article

  • [

Introduction

](#introduction)

  • [

What is the WorkOS Management MCP Server

](#what-is-the-workos-management-mcp-server)

  • [

How agents interact with it

](#how-agents-interact-with-it)

  • [

Getting connected

](#getting-connected)

  • [

Managing Team Access to the MCP Server

](#managing-team-access-to-the-mcp-server)

  • [

How it fits with the WorkOS CLI

](#how-it-fits-with-the-workos-cli)

  • [

What to try first

](#what-to-try-first)

  • [

Available now

](#available-now)

July 1, 2026

July 1, 2026

WorkOS MCP: Manage your WorkOS account from any AI agent

We are launching a remote MCP server that gives AI agents the same access to WorkOS as your dashboard login.

Jeff Fiddler

July 1, 2026

Explore with AI

[

Open in ChatGPT

](https://chatgpt.com/?q=Read%20this%20article%3A%20https%3A%2F%2Fworkos.com%2Fblog%2Fmanagement-mcp-server.%20In%20a%20short%20paragraph%2C%20tell%20me%20what%20it%27s%20about%2C%20what%27s%20new%20or%20interesting%20about%20it%2C%20and%20whether%20it%27s%20worth%20reading%20in%20full.)[

Open in Claude

](https://claude.ai/new?q=Read%20this%20article%3A%20https%3A%2F%2Fworkos.com%2Fblog%2Fmanagement-mcp-server.%20In%20a%20short%20paragraph%2C%20tell%20me%20what%20it%27s%20about%2C%20what%27s%20new%20or%20interesting%20about%20it%2C%20and%20whether%20it%27s%20worth%20reading%20in%20full.)[

Open in Perplexity

](https://www.perplexity.ai/?q=Read%20this%20article%3A%20https%3A%2F%2Fworkos.com%2Fblog%2Fmanagement-mcp-server.%20In%20a%20short%20paragraph%2C%20tell%20me%20what%20it%27s%20about%2C%20what%27s%20new%20or%20interesting%20about%20it%2C%20and%20whether%20it%27s%20worth%20reading%20in%20full.)

Most configuration tasks in WorkOS have always required a trip to the dashboard. Setting up a domain, adjusting auth policies, managing users and roles, debugging a sign-in issue for a customer: all of it has lived behind a UI that only a human can drive.

Dashboards were built with a human on the other end. Someone with a mouse, a browser tab, and the patience to click through nested menus. That assumption made sense for a long time. It makes less sense now that agents are increasingly the ones doing the setup work, wiring up integrations, configuring services, debugging issues. An agent can write code at the speed of thought, but when it hits a dashboard, it stops.

Today that changes. The WorkOS MCP server exposes the full management surface of your WorkOS account as tools your agent can use, and it works from anywhere you can run an agent.

What is the WorkOS Management MCP Server

The WorkOS MCP server is a remote, hosted server your agent connects to over OAuth. Once connected, it authenticates as you and inherits exactly the roles and permissions your dashboard login has. If your account is read-only in production, the agent is too. If you have full admin access, the agent does. There is nothing extra to configure and no separate permission model to maintain.

This is not a narrow slice of the API. The server exposes hundreds of operations across the full WorkOS product surface: organizations, SSO connections, Directory Sync, AuthKit users and sessions, roles and permissions, audit logs, webhooks, API keys, feature flags, environments, branding, and more.

What the server does not expose is equally deliberate. Credential-minting operations, user impersonation, billing flows, and account-level administration are excluded entirely. Secret fields like API keys, client secrets, and webhook signing secrets are stripped from responses before they reach the agent's context. Nine irreversible deletes require a two-call confirmation before they execute. The agent can do everything you would do in the dashboard for day-to-day management, and nothing you would not.

How agents interact with it

Rather than exposing one tool per endpoint, the server uses a discover-then-execute design with four tools: whoami, list_operations, query, and mutate. This matters because every tool gets loaded into the LLM's context window, so exposing hundreds of operations as individual tools would consume the context budget before the agent even starts working. Instead, an agent uses list_operations to find what it needs, then calls query or mutate by operation name with the relevant variables.

Here is what that looks like in practice. A support engineer gets a report that a customer cannot sign in:

You: A user at Acme Corp is reporting they cannot sign in. Can you check if their SSO connection is set up correctly and whether they have an active session?
Agent: I found Acme Corp in your Production environment. They have one active SAML connection. The certificate is valid and not expiring soon, but the connection is pointed at a metadata URL that returned a 404 the last time it was fetched. That is most likely what is breaking sign-in.
You: Can you pull their recent SSO sessions to see when the issue started?
Agent: Their last successful sign-in was three days ago. Sessions since then show a consistent failure at the IdP redirect step, which lines up with the metadata URL issue.
You: Generate a setup link so their IT admin can reconfigure it.
Agent: Done. Here is an Admin Portal setup link for Acme Corp valid for 7 days: [link]. You can send this directly to their IT admin to complete the SAML reconfiguration.

**Gettin

[... 原文已截断,完整内容见链接 ...]