Salesforce Sales Cloud MCP server
An AI agent connected to Salesforce Sales Cloud can automate the entire sales process—capturing and scoring leads, converting qualified prospects to opportunities, moving deals through sales stages, and generating forecasts. Sales representatives, managers, and sales operations teams use this integration to reduce administrative tasks and focus on customer engagement.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers
- API credentials for the application you're connecting (see the relevant application page for what to collect)
Create an MCP server
Find the API in the catalog
- Sign in to AI Gateway and select MCP Servers from the left navigation.
- Select New MCP Server.
- Search for the application you want to connect, then select it from the catalog.
Configure the server
- Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
- Enter a Description so your team knows what the server is for.
- Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
- Toggle Production mode on if this server will be used in a live workflow.
- Select Next.
Configure authentication
Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.
Configure security
- Set any Rate limits appropriate for your use case and the API's own limits.
- Enable Logging if you want AI Gateway to record requests and responses for auditing.
- Select Next.
Deploy
Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
- You can edit a server's name, description, timeout, and security settings after deployment without redeploying.
Authentication
Salesforce Sales Cloud uses OAuth 2.0 via a Connected App for secure API authentication. The authorization endpoint is https://login.salesforce.com/services/oauth2/authorize (use https://test.salesforce.com for sandboxes), and the token endpoint is https://login.salesforce.com/services/oauth2/token. Your Connected App provides Client ID and Client Secret. Core scopes are api (read and write Salesforce data), refresh_token (maintain persistent access), and id (access user profile). Optional scopes like wave_api (Einstein Analytics) and custom_permissions unlock advanced features.
Available tools
The MCP server provides lead and opportunity management, account and contact operations, forecasting, and sales analytics capabilities.
Lead & opportunity management
| Tool | Description |
|---|---|
| createLead | Create new lead record with company, contact, and source data |
| getLead | Retrieve lead by ID with field selection |
| updateLead | Update lead qualification status, score, and assignment |
| convertLead | Convert qualified lead to Account, Contact, and Opportunity |
| createOpportunity | Create opportunity from lead or standalone |
| updateOpportunity | Update stage, probability, close date, and amount |
| getOpportunity | Retrieve opportunity details with product and forecast info |
Account & contact management
| Tool | Description |
|---|---|
| createAccount | Create account with billing/shipping addresses and hierarchy |
| getAccount | Retrieve account with relationships and custom fields |
| updateAccount | Update account revenue, employee count, and segment |
| createContact | Add contact to account with role and communication preferences |
| updateContact | Update contact information and association |
| getContact | Retrieve contact history and related records |
Forecasting & analytics
| Tool | Description |
|---|---|
| generateForecast | Execute forecast query for period or sales team |
| getReport | Run report and retrieve sales pipeline, activity, or performance data |
| listReports | Search available reports in Sales Cloud |
| queryActivities | Get tasks, events, and calls related to records |
Additional operations
| Tool | Description |
|---|---|
| executeQuery | Run SOQL queries on Lead, Opportunity, Account, Contact objects |
| executeComposite | Execute multiple operations (create, update, delete) in single call |
| executeBatch | Run up to 25 parallel operations for bulk updates |
Tips
Use api and refresh_token scopes as baseline — add wave_api if you need to pull Einstein Analytics data or reporting APIs.
Validate lead readiness with a convertLead query first to ensure company matching and required fields are complete, since lead conversion is irreversible.
Update Opportunity stage programmatically only if your sales process allows it, as some orgs lock stage changes to the UI for compliance or workflow control.
Batch lead creates and bulk imports with executeBatch when handling contact lists or trade show registrations to avoid hitting per-hour API rate limits.
Schedule forecast queries off-peak (early morning or evening) as they're resource-intensive and may consume more API calls than standard operations.
Cequence AI Gateway