Salesforce Platform MCP server

An AI agent connected to Salesforce Platform can manage the complete customer lifecycle—creating and qualifying leads, updating opportunities through sales stages, executing complex SOQL queries to find accounts by criteria, and automating bulk data operations across your org. Sales operations teams, customer success managers, and system administrators use this integration to drive data consistency and eliminate manual CRM updates.

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

1. Sign in to AI Gateway and select MCP Servers from the left navigation.
2. Select New MCP Server.
3. Search for the application you want to connect, then select it from the catalog.

Configure the server

1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
2. Enter a Description so your team knows what the server is for.
3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
4. Toggle Production mode on if this server will be used in a live workflow.
5. 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

1. Set any Rate limits appropriate for your use case and the API's own limits.
2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
3. 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:

• Claude Desktop
• Claude Code
• Cursor
• VS Code
• Windsurf

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 Platform uses OAuth 2.0 through a Connected App for API access. The authorization endpoint is https://login.salesforce.com/services/oauth2/authorize (or https://test.salesforce.com for sandboxes), and tokens are exchanged at https://login.salesforce.com/services/oauth2/token. Your Connected App provides Client ID and Client Secret credentials. Essential scopes include api (core data access), refresh_token (obtain long-lived refresh tokens), and id (access user identity). Optional scopes like full (complete org access) and custom_permissions (custom security models) extend capabilities based on your use case.

Available tools

The MCP server provides comprehensive object and data management, SOQL query execution, bulk operations, and reporting capabilities for complete CRM automation.

Record operations

Tool	Description
createRecord	Create new record for any standard or custom object
getRecord	Retrieve record by ID with specific field selection
updateRecord	Update record with partial data (upsert capability)
deleteRecord	Delete record by ID

Query & retrieval

Tool	Description
executeQuery	Run SOQL queries with filtering, relationships, and aggregates
executeQueryAll	Include deleted and archived records in query results
executeSearch	Full-text SOSL search across multiple objects

Bulk operations

Tool	Description
executeComposite	Execute multiple operations in single request with dependencies
executeBatch	Run up to 25 independent operations in parallel batch
createBulkJob	Process large-scale data asynchronously (INSERT, UPDATE, UPSERT, DELETE)

Metadata & analytics

Tool	Description
listAllObjects	Get all available standard and custom objects
describeObject	Retrieve metadata, field definitions, and relationships
listReports	Search for and list available reports
getReport	Execute report and retrieve data
getOrganizationLimits	Check API usage, storage, and org limits

Tips

Start with api and refresh_token scopes — request full only when you need metadata operations or admin functions beyond basic CRUD.

Use field-specific SOQL queries (e.g., SELECT Name, Phone FROM Account WHERE Industry = 'Technology') rather than broad queries to reduce data transfer and improve query performance.

Batch related operations together using executeComposite or executeBatch to make efficient use of your daily API call quota, especially for high-volume updates.

Respect your org's field-level security and sharing rules automatically — the Salesforce API ensures records returned reflect what the authenticated user can access.

Store refresh tokens securely and implement token refresh logic before expiration to maintain seamless automation in long-running processes.