> ## Documentation Index
> Fetch the complete documentation index at: https://conductorone-docs-cxh-1986.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Set up the LinkedIn MCP server

> Connect LinkedIn to C1 with per-user OAuth, then register the LinkedIn MCP server and govern its tools.

<Note>
  **Activation required.** AI access management must be enabled for your tenant before you can use it. To get started, [contact the C1 support team](mailto:support@c1.ai) for a walkthrough.
</Note>

The LinkedIn MCP server lets you govern access to LinkedIn — member profiles, organization pages, social posts, and ads data — as tools your AI clients can call through C1.

LinkedIn authenticates with per-user OAuth. Each person authorizes with their own LinkedIn account, so every tool call runs under that user's LinkedIn identity and permissions. For a deeper comparison of shared versus per-user credentials, see [Configure authentication](/product/admin/mcp-servers#configure-authentication).

## How C1 connects to LinkedIn

C1 hosts the LinkedIn MCP server, so your users' AI clients only ever see MCP tools — they never call LinkedIn directly. When an AI client calls one of these tools, C1 makes the matching request to the LinkedIn API using the credentials you configure here, then returns the result to the AI client.

The credentials you set up below are what C1 uses to call LinkedIn on your users' behalf.

## Before you begin

* AI access management must be enabled for your tenant. See [Enable AI access management](/product/admin/enable-ai-access-management).
* A LinkedIn account with permission to create an app in the LinkedIn Developer Portal, linked to a LinkedIn Page you administer.

<Note>
  If you don't see **LinkedIn** in your MCP server catalog, [contact the C1 support team](mailto:support@c1.ai) to enable it for your tenant.
</Note>

## Create a LinkedIn app

Create an app in the LinkedIn Developer Portal to generate the OAuth credentials C1 uses to connect.

<Steps>
  <Step>
    In the LinkedIn Developer Portal, select **Create app**. For details, see LinkedIn's [Authenticating with OAuth 2.0](https://learn.microsoft.com/en-us/linkedin/shared/authentication/authentication) documentation.
  </Step>

  <Step>
    Give the app a recognizable name such as `C1` and associate it with a LinkedIn Page you administer.
  </Step>

  <Step>
    On the **Auth** tab, set the **authorized redirect URL** exactly to `https://accounts.conductor.one/auth/callback`.
  </Step>

  <Step>
    On the **Products** tab, request the products that grant the scopes you need, such as profile, email, and organization access.
  </Step>

  <Step>
    Copy the **client ID** and **client secret** from the **Auth** tab.
  </Step>
</Steps>

## How LinkedIn credentials are shared

Each user authorizes with their own LinkedIn account, so tool calls run under that user's LinkedIn identity and inherit only the access they already have. LinkedIn attributes each action to the individual user.

For how shared and per-user credentials work across MCP servers, see [Configure authentication](/product/admin/mcp-servers#configure-authentication).

## Register the LinkedIn MCP server in C1

With your app ready, register the server and provide your credentials.

<Steps>
  <Step>
    Follow [Register an MCP server](/product/admin/mcp-servers#register-an-mcp-server) and select **LinkedIn** from the catalog.
  </Step>

  <Step>
    When you [configure authentication](/product/admin/mcp-servers#configure-authentication), choose per-user OAuth and enter your app's **client ID** and **client secret**.
  </Step>

  <Step>
    Save your changes. The first time a user calls a LinkedIn tool from their AI client, they're prompted to connect their LinkedIn account.
  </Step>
</Steps>

## Discover and govern tools

After you register the server, C1 runs tool discovery against LinkedIn. Discovered tools appear on the server's **Tools** tab.

Each tool starts as either **Pending review** or automatically **Approved**, depending on the option chosen when the server was set up or your tenant's default tool settings in **Settings** > **AI Connections**. See [Require tool approval](/product/admin/enable-ai-access-management#require-tool-approval) and [Default tool classification](/product/admin/enable-ai-access-management#default-tool-classification).

Before anyone can call a LinkedIn tool, it must be approved, added to a toolset, and bound to an access profile. Continue to [Govern tools and toolsets](/product/admin/tools-and-toolsets) to set this up.

<Note>
  Tool discovery runs even if your credentials are incorrect, so seeing discovered tools doesn't confirm that authentication is working. You confirm your LinkedIn credentials when an approved user successfully calls a LinkedIn tool from their AI client.
</Note>

## Manage your LinkedIn credentials

* **Rotate the client secret** in your LinkedIn app under the **Auth** tab, then update the secret on the server's authentication settings in C1.
* **Adjust access** by requesting or removing products on the app's **Products** tab in LinkedIn.