Salesforce TypeScript Connector

Interact with Salesforce data using SOQL queries, SOSL searches, and CRUD operations via a TypeScript MCP server.

A TypeScript implementation of a Model Context Protocol (MCP) server for Salesforce integration, allowing LLMs to interact with Salesforce data through SOQL queries, SOSL searches, and CRUD operations.

- 🔐 Simplified Password Authentication: Secure OAuth 2.0 Resource Owner Password Credentials Flow
- 📊 SOQL & SOSL: Execute queries and searches against Salesforce
- 🔍 Metadata Access: Retrieve object fields, labels, and types
- ✏️ CRUD Operations: Create, read, update, and delete records
- 🛠️ Tooling API: Execute Tooling API requests
- ⚡ Apex REST: Execute Apex REST requests
- 🌐 REST API: Make direct REST API calls to Salesforce
- 🐳 Docker Ready: No hardcoded values, fully configurable via environment variables
- 🔄 Token Refresh: Automatic token refresh for long-running sessions

- authenticate_password- Authenticate using username/password with OAuth
- run_soql_query- Execute SOQL queries
- run_sosl_search- Execute SOSL searches
- get_object_fields- Get metadata for Salesforce objects
- get_record- Retrieve specific records by ID
- create_record- Create new records
- update_record- Update existing records
- delete_record- Delete records
- tooling_execute- Execute Tooling API requests
- apex_execute- Execute Apex REST requests
- restful- Make direct REST API calls

- Go to Setup → Apps → App Manager → New Connected App
- Fill in basic information (App Name, API Name, Contact Email)
- Enable OAuth Settings
- Set callback URL:http://localhost:8080/callback(required but not used)
- Select OAuth Scopes:

- Access your basic information (id, profile, email, address, phone)
- Perform requests on your behalf at any time (refresh_token, offline_access)
- Access and manage your data (api)

- Go to Setup → My Personal Information → Reset Security Token
- Check your email for the new security token

# Pull the image docker pull steffensbola/salesforce-mcp-ts:latest # Run with your credentials docker run -p 3000:3000 \ -e SALESFORCE_CLIENT_ID=your_consumer_key \ -e SALESFORCE_CLIENT_SECRET=your_consumer_secret \ -e SALESFORCE_USERNAME=your_username@domain.com \ -e SALESFORCE_PASSWORD=your_password \ -e SALESFORCE_SECURITY_TOKEN=your_security_token \ -e SALESFORCE_SANDBOX=true \ steffensbola/salesforce-mcp-ts:latest

{ "servers": { "salesforce": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "SALESFORCE_CLIENT_ID=your_consumer_key", "-e", "SALESFORCE_CLIENT_SECRET=your_consumer_secret", "-e", "SALESFORCE_USERNAME=your_username@domain.com", "-e", "SALESFORCE_PASSWORD=your_password", "-e", "SALESFORCE_SECURITY_TOKEN=your_token", "-e", "SALESFORCE_SANDBOX=true", "steffensbola/salesforce-mcp-ts:latest" ] } } }

You can also use volumes to mount a config file instead of passing environment variables:

{ "servers": { "salesforce": { "command": "docker", "args": [ "run", "--rm", "-i", "-v", "${workspaceFolder}/.env:/app/.env", "steffensbola/salesforce-mcp-ts:latest" ] } } }

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "salesforce": { "command": "docker", "args": [ "run", "--rm", "-i", "-e", "SALESFORCE_CLIENT_ID=your_consumer_key", "-e", "SALESFORCE_CLIENT_SECRET=your_consumer_secret", "-e", "SALESFORCE_USERNAME=your_username@domain.com", "-e", "SALESFORCE_PASSWORD=your_password", "-e", "SALESFORCE_SECURITY_TOKEN=your_token", "-e", "SALESFORCE_SANDBOX=true", "steffensbola/salesforce-mcp-ts:latest" ] } } }

The server requires the following environment variables:

- SALESFORCE_CLIENT_ID- Consumer Key from your Connected App
- SALESFORCE_CLIENT_SECRET- Consumer Secret from your Connected App
- SALESFORCE_USERNAME- Your Salesforce username
- SALESFORCE_PASSWORD- Your Salesforce password
- SALESFORCE_SECURITY_TOKEN- Your Salesforce security token

- SALESFORCE_SANDBOX- Set to"true"for sandbox,"false"for production (default:"false")

Alternative (Direct Token Authentication)

Instead of username/password, you can use:

- SALESFORCE_ACCESS_TOKEN- Direct access token
- SALESFORCE_INSTANCE_URL- Salesforce instance URL (e.g.,https://your-instance.my.salesforce.com)

The server also supports alternative variable names:

- SF_CONSUMER_KEY/SF_CONSUMER_SECRET
- SF_USERNAME/SF_PASSWORD/SF_SECURITY_TOKEN
- Create a.envfile with your environment variables:

SALESFORCE_CLIENT_ID=your_consumer_key SALESFORCE_CLIENT_SECRET=your_consumer_secret SALESFORCE_USERNAME=your_username@domain.com SALESFORCE_PASSWORD=your_password SALESFORCE_SECURITY_TOKEN=your_token SALESFORCE_SANDBOX=true DOCKER_HUB_USERNAME=steffensbola

Once connected, you can use the tools through your MCP client:

Please authenticate with Salesforce using my credentials

Run this SOQL query: SELECT Id, Name, Industry FROM Account WHERE Industry = 'Technology' LIMIT 10

Search for contacts named "John" using SOSL

Get all the fields for the Contact object

Create a new Account with Name "Test Company" and Industry "Technology"

- Verify credentials are correct
- Check Connected App OAuth scopes include "Access and manage your data (api)"
- Ensure security token is current (reset if needed)
- Verify sandbox setting matches your org type

- Ensure both CLIENT_ID and CLIENT_SECRET are provided
- Check that all required environment variables are set
- Verify Docker has access to pull the image

- Check internet connection
- Verify Salesforce service status
- Check firewall settings allow outbound HTTPS connections

For verbose logging, add the debug environment variable:

docker run -e DEBUG=true \ -e SALESFORCE_CLIENT_ID=... \ # ... other variables steffensbola/salesforce-mcp-ts:latest

SeeCONTRIBUTING.mdfor information about:

MIT License - seeLICENSEfile for details.

- Salesforce Documentation
- Model Context Protocol
- Docker Hub Repository

Interact with the Appwrite API to manage databases, users, storage, and more. Requires configuration via environment variables.