Custom Connectors

​

Verify your Claude plan and permissions

While anyone can build and host connectors using remote MCP, only Owners can add them to Team and Enterprise plans. Once a connector has been added to a Team or Enterprise organization, users individually connect to and enable that connector. This ensures that Claude can only access tools and data that the individual user has access to.

​

Configure your custom connector

​

For Team and Enterprise plans

1. Go to Claude.
2. Go to Organization settings > Connectors.
3. Click Add.
4. Hover over Custom, then select Web.
5. Complete the form as follows:
   • Name: Conductor
   • Remote MCP server URL: https://mcp-universal.conductor.com/mcp/v4
6. Click Advanced settings and complete:
   • OAuth Client ID: 4fhi7qah4mg0fane9gp9s3i6i5
   • OAuth Client Secret: [leave blank]
7. Click Add. Anthropic will process your information, and you will be redirected to a Conductor authentication screen.
8. Authenticate using your Conductor credentials.

1. Go to Claude.
2. Go to Customize > Connectors.
3. Find the Conductor connector your Owner added in the list. It carries a Custom label.
4. Click Connect. You will be redirected to a Conductor authentication screen.
5. Authenticate using your Conductor credentials.

​

For Pro and Max plans

1. Go to Claude.
2. Go to Customize > Connectors.
3. In the top-right of the Connectors window, click the Add, and then select Add custom connector.
4. Complete the form as follows:
   • Name: Conductor
   • Remote MCP server URL: https://mcp-universal.conductor.com/mcp/v4
5. Click Continue.
6. In the OAuth client section, complete these fields:
   • OAuth Client ID: 4fhi7qah4mg0fane9gp9s3i6i5
   • OAuth Client Secret: [leave blank]
7. Click Add. Anthropic will process your information, and you will be redirected to a Conductor authentication screen.
8. Authenticate using your Conductor credentials.

​

Install Claude Code

​

Add Conductor’s MCP server

claude mcp add --transport http \
  --client-id 4fhi7qah4mg0fane9gp9s3i6i5 \
  --callback-port 8080 \
  --scope user \
  conductor https://mcp-universal.conductor.com/mcp/v4

• --client-id is Conductor’s OAuth client ID—the same one the custom connector uses. There’s no client secret to provide.
• --callback-port must be 8080 or 8081. Use 8081 if another program on your machine is already listening on 8080.
  Pin the OAuth callback port. Each time Claude Code authorizes a server, it opens a callback on your machine using a random port. Conductor matches that callback address exactly, but only ports 8080 and 8081 are registered—so an unpinned port fails with a redirect_mismatch error.
• --scope user registers Conductor once for every project on your machine. Omit it to register Conductor only for the directory you’re currently in.

​

Authorize Conductor

1. Start a session with claude.
2. Run /mcp and select conductor.
3. Claude Code opens Conductor’s authentication screen in your browser. Authenticate using your Conductor credentials.
4. Return to your terminal. Conductor’s tools are available in the session.

​

Troubleshoot the connection

claude mcp remove conductor

claude --version

• Create an API token in the Conductor platform. Learn how: Authenticating custom connections
• Add the custom MCP connection in your OpenAI account settings.

​

Verify your ChatGPT plan and permissions

• Any of ChatGPT’s paid plans: Pro, Plus, Business, Enterprise, and Education.
• Admin access.

​

Configure your custom connection

1. Go to ChatGPT.
2. If you are not already, sign into the paid account you want to use to configure this integration. Be sure to use the correct account (likely an account belonging to your organization and not your personal ChatGPT account).
3. From the navigation on the left, click your profile and select Settings.
4. On the left, click Security and login.
5. Scroll to the Developer mode section and enable Developer mode if not already enabled.
6. On the left, click Plugins, then click Browse plugins.
7. In the top-right, click the Plus (+) icon.
8. In the New Plugin form, complete the following:
   • Name: Conductor
   • Connection:
     • Toggle above field: Streamable HTTP
     • Field: https://mcp-universal.conductor.com/mcp/v4
   • Authentication: Access token / API key
   • Header scheme: Bearer
9. Select the I understand and want to continue checkbox.
10. Click Create. OpenAI will process your information.
11. In the authentication form that appears, enter the API token you generated above and click Connect.

​

Verify your Perplexity plan and permissions

Organization members can add custom remote connectors if admins enable them for the organization. How you add a remote connector depends on whether an admin adds it for the entire organization or a user (including admins) adds it for their own account. In both cases, the steps are largely the same. The main difference is that only admins can share connectors with the entire organization.

​

Configure your custom connector

​

For Enterprise plans

1. Go to Perplexity.
2. In your Enterprise settings, click Connectors.
3. Click the toggle to Allow members to add custom connectors.
4. In the Access section, click + Custom connector.
5. Complete the Add custom remote connector form as follows (you’ll need to click the drop-down to see Advanced settings):
   • Name: Conductor
   • MCP server URL: https://mcp-universal.conductor.com/mcp/v4
   • Authentication: OAuth
   • Client ID: 5pa2l8d0uckl8ddqmr0dhnit0u
   • Client Secret: [Conductor will provide this value separately]
6. Select the I understand custom connectors can introduce risks check box.
7. Click Add. The connector appears on the Connectors screen in your Account settings.
8. In the Access section below, find the Conductor connector and enable the toggle to allow users to add the connector.

1. Open your Account settings, click Connectors.
2. Find and click the Conductor custom connector your admin added under the Custom section. You will be redirected to a Conductor authentication screen.
3. Authenticate using your Conductor credentials.

​

For individual Pro plans

1. Go to Perplexity.
2. Go to your Account settings and select All settings.
3. Click + Custom connector in the top-right corner.
4. Select Remote.
5. Complete the Add custom remote connector form as follows (you’ll need to click the drop-down to see Advanced settings):
   • Name: Conductor
   • MCP server URL: https://mcp-universal.conductor.com/mcp/v4
   • Authentication: OAuth
   • Client ID: 5pa2l8d0uckl8ddqmr0dhnit0u
   • Client Secret: [Conductor will provide this value separately]
6. Click Add. The connector appears on the Connectors screen in your Account settings.
7. Click the connector card. Perplexity will process your information, and you will be redirected to a Conductor authentication screen.
8. Authenticate using your Conductor credentials.

​

Query your data

1. Click the + icon.
2. In the Connectors and sources menu, confirm that the check box for the Conductor connector is selected. If not, select it.
3. Enter a query.

1. In Abacus.AI, open Agent Settings and select MCP Server Config from the sidebar.
2. Add a JSON entry for Conductor that includes the server URL and an Authorization header carrying your API token:
   {
     "conductor": {
       "url": "https://mcp-universal.conductor.com/mcp/v4",
       "headers": {
         "Authorization": "Bearer YOUR_CONDUCTOR_API_TOKEN"
       }
     }
   }
   
3. Save the configuration. Abacus queries the server and lists Conductor’s available tools.

​

Get your client secret from Conductor

​

Prerequisites

• Set the Disable custom MCP server connector for Gemini Enterprise organization policy constraint to Off (Not enforced). This requires an Organization Policy Administrator.
• Add all three of Conductor’s hosts to the allowedEgressFqdns parameter in your egress domain policy: mcp-universal.conductor.com, auth.conductor.com, and prod-conductor.auth.us-east-1.amazoncognito.com. Miss either of the last two and the OAuth exchange fails even though the MCP server itself is reachable.
• Add custom_mcp to the allowed data sources, if project enforcement is enabled or the project is protected by VPC Service Controls.
• Grant the Discovery Engine Editor (roles/discoveryengine.editor) role to whoever creates the data store.

​

Create the data store

1. In the Google Cloud console, go to Gemini Enterprise.
2. In the navigation menu, click Data stores, then click Create data store.
3. On the Select a data source page, enter Custom MCP Server in the Search sources field, then click Add MCP server on the card that appears.
4. In the Authentication settings section, select OAuth 2.0 and complete the form:
   • MCP Server URL: https://mcp-universal.conductor.com/mcp/v4
   • Authorization URL: https://auth.conductor.com/oauth2/authorize
   • Authorization URL Parameters: leave empty. Gemini Enterprise appends the standard OAuth parameters itself.
   • Token URL: https://prod-conductor.auth.us-east-1.amazoncognito.com/oauth2/token
   • Client ID: 2ff2jkrpif0dmb7meqc4tc0o4d
   • Enable PKCE Support: on. Conductor’s authorization server supports PKCE with the S256 challenge method—turn this off only if the token exchange errors.
   • Client Secret: [Enter the client secret you received from Conductor]
   • Scopes: openid profile email
5. Click Verify Auth, then click Continue.
6. Select Multi-region as the location, enter a name in Your data connector name (for example, Conductor), and click Create.

​

Enable Conductor’s tools

1. Open your new Custom MCP data store.
2. Click Actions > Reload custom actions to fetch the list of available tools.
3. Select the tools you want, then click Enable actions. You can enable up to 100 at a time.
4. Connect the data store to the app or agent that should use it. See Google’s guide to connecting a data store to an app for the steps.
5. Authorize the connection: open the app, select Manage your data, click Enable actions next to the Conductor data store, and sign in with your Conductor credentials.

1. Open your librechat.yaml configuration file.
2. Add Conductor as a streamable-http server, passing your API token in the Authorization header. Set requiresOAuth: false so LibreChat uses your header instead of attempting an OAuth flow:
   mcpServers:
     conductor:
       type: streamable-http
       url: https://mcp-universal.conductor.com/mcp/v4
       requiresOAuth: false
       headers:
         Authorization: "Bearer YOUR_CONDUCTOR_API_TOKEN"
   
3. Restart LibreChat so it picks up the new server, then select Conductor in the MCP menu.

1. In Lovable, open Connectors and go to Chat connectors.
2. Click New MCP server.
3. Enter a Server name (for example, Conductor) and set the Server URL to https://mcp-universal.conductor.com/mcp/v4.
4. Under Authentication, choose Bearer token or API key and paste your Conductor API token.
5. Click Add server. Conductor now appears in your list of chat connectors.

1. Add an MCP Client Tool node to your workflow and connect it to your AI Agent node.
2. Set the SSE Endpoint (server URL) to https://mcp-universal.conductor.com/mcp/v4.
3. Set Authentication to Bearer Auth, then create a credential whose token is your Conductor API token. If you prefer to send the token yourself, choose Header Auth and add an Authorization header with the value Bearer YOUR_CONDUCTOR_API_TOKEN.
4. Save and execute the workflow. The agent can now call Conductor’s tools.

1. A workspace admin enables custom connections in Settings > Notion AI > AI connectors > Enable Custom MCP servers.
2. Open your Custom Agent’s Settings and go to Tools & Access.
3. Click Add connection > Custom MCP server.
4. Enter the MCP server URL https://mcp-universal.conductor.com/mcp/v4 and a display name (for example, Conductor).
5. When prompted for authentication, choose header-based auth and add an Authorization header with the value Bearer YOUR_CONDUCTOR_API_TOKEN.
6. Click Save. Conductor’s tools become available to the agent.

1. In Replit, open the MCP Servers settings pane and click Add MCP server.
2. Paste the server URL https://mcp-universal.conductor.com/mcp/v4.
3. Open Advanced settings and add a custom header:
   • Key: Authorization
   • Value: Bearer YOUR_CONDUCTOR_API_TOKEN
4. Click Test & save. Once the connection succeeds, Conductor appears under MCP Servers and its tools are available to Agent.

1. In Writer’s AI Studio, open Connectors & Tools and select Create custom connector.
2. Choose MCP server as the connector type.
3. Enter the MCP server URL https://mcp-universal.conductor.com/mcp/v4, give the connector a name (for example, Conductor), and describe it under About this connector. Click Next.
4. Keep the default Profile name or update it, then choose whether the connector is available to all teams or to specific teams.
5. For the authentication method, select API key and enter your Conductor API token. Conductor supports this connection as Bearer token auth, so use Authorization as the key name and Bearer as the key prefix. Don’t choose No auth or OAuth—neither is supported for this connection.
6. Complete the connection flow. Conductor appears in your connected integrations, and its tools become available to authorized users in Writer Agent.