Salesforce CRM MCP server
An AI agent connected to Salesforce CRM can automate customer relationship management tasks—creating and updating leads, opportunities, and accounts; executing SOQL queries; and managing bulk data operations. Sales teams, administrators, and operations professionals use this integration to streamline data management and workflow automation without manual portal access.
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 uses OAuth 2.0 via a Connected App for secure API access. You'll authenticate with the instance URL pattern https://{instance}.salesforce.com/services/oauth2/authorize. Your Connected App provides a Client ID and Client Secret to exchange for access tokens. Scopes determine what data the MCP server can read or write—common scopes include api (standard API access), refresh_token (persistent access), and id (user profile access). You can optionally use JWT Bearer Flow for server-to-server authentication with a digital certificate instead of user interaction.
Available tools
The MCP server exposes operations for complete CRM data lifecycle management. You can create, read, update, and delete records across all Salesforce objects; execute SOQL queries with filtering, sorting, and aggregates; run bulk operations for high-volume updates; and access analytics reports and dashboards.
Core operations
| Tool | Description |
|---|---|
| createRecord | Create new record for any object type (Lead, Account, Opportunity, Contact, etc.) |
| getRecord | Retrieve specific record by ID with selectable fields |
| updateRecord | Update existing record with partial or full data |
| deleteRecord | Delete record by ID |
Query & search
| Tool | Description |
|---|---|
| executeQuery | Run SOQL queries with WHERE, ORDER BY, LIMIT, and aggregates |
| executeQueryAll | Query including deleted and archived records for historical analysis |
| executeSearch | Full-text SOSL search across multiple objects simultaneously |
Bulk operations
| Tool | Description |
|---|---|
| executeComposite | Execute multiple operations in single request with dependent references |
| executeBatch | Run up to 25 independent operations in parallel |
| createBulkJob | Process millions of records asynchronously for INSERT, UPDATE, UPSERT, DELETE |
Metadata & reporting
| Tool | Description |
|---|---|
| listApiVersions | Discover available REST API versions |
| listAllObjects | Retrieve all standard and custom objects in your org |
| describeObject | Get field definitions, picklist values, and relationships for any object |
| getReport | Execute reports and retrieve data with filtering |
| getOrganizationLimits | Monitor API usage and org limits (storage, API calls, etc.) |
Tips
Use api and refresh_token scopes as a starting minimum for most integrations — add full only if you need admin-level operations like deploying metadata.
Use specific field lists and WHERE clauses in SOQL queries rather than broad SELECT * statements to reduce payload size and improve performance.
Use the Bulk API 2.0 endpoints (createBulkJob) instead of individual create/update calls for bulk data operations exceeding 10,000 records to avoid hitting daily API limits.
Respect field-level security and record sharing rules — the Salesforce API enforces your org's permission model, so users see only data they have access to.
Implement token refresh logic to maintain persistent authentication for background workflows, since refresh tokens expire after long periods of inactivity.