MCP-Salesforce
MCP Salesforce connector Python-based implementation.
Documentation
MCP Salesforce Connector
A Model Context Protocol (MCP) server implementation for Salesforce integration, allowing LLMs to interact with Salesforce data through SOQL queries and SOSL searches.
Features
- Execute SOQL (Salesforce Object Query Language) queries
- Perform SOSL (Salesforce Object Search Language) searches
- Retrieve metadata for Salesforce objects, including field names, labels, and types
- List all available SObjects - Discover standard and custom objects
- Retrieve, create, update, and delete records
- Execute Tooling API requests
- Execute Apex REST requests
- Make direct REST API calls to Salesforce
Configuration
Model Context Protocol
To use this server with the Model Context Protocol, you need to configure it in your `claude_desktop_config.json` file. Add the following entry to the `mcpServers` section:
{
"mcpServers": {
"salesforce": {
"command": "uvx",
"args": [
"--from",
"mcp-salesforce-connector",
"salesforce"
],
"env": {
"SALESFORCE_ACCESS_TOKEN": "SALESFORCE_ACCESS_TOKEN",
"SALESFORCE_INSTANCE_URL": "SALESFORCE_INSTANCE_URL",
"SALESFORCE_DOMAIN": "SALESFORCE_DOMAIN"
}
}
}
}
Available Tools
Query and Search Tools
- `run_soql_query` - Execute SOQL queries against Salesforce
- `run_sosl_search` - Perform SOSL searches across objects
Metadata Tools
- `get_object_fields` - Retrieve field metadata for specific objects
- `list_sobjects` - List all available SObjects (standard and custom)
Single Record Operations
- `get_record` - Retrieve a specific record by ID
- `create_record` - Create a new record
- `update_record` - Update an existing record
- `delete_record` - Delete a record
Bulk Operations
- `bulk_create_records` - Create multiple records in a single operation
- `bulk_update_records` - Update multiple records (must include Id field)
- `bulk_delete_records` - Delete multiple records using record IDs
Advanced API Tools
- `tooling_execute` - Execute Tooling API requests
- `apex_execute` - Execute Apex REST requests
- `restful` - Make direct REST API calls to Salesforce
Note on Salesforce Authentication Methods
This server supports four authentication methods:
- OAuth (Recommended): Set `SALESFORCE_ACCESS_TOKEN` and `SALESFORCE_INSTANCE_URL` as environment variables.
- Client Credentials: Set `SALESFORCE_CLIENT_ID` and `SALESFORCE_CLIENT_SECRET` for OAuth 2.0 Client Credentials flow. This is useful for server-to-server integrations.
- Salesforce CLI (Default Org): If no OAuth env vars are set, the server will try to use the active Salesforce CLI default org from the current workspace (via `sf org display --json` or `sfdx force:org:display --json`). Optionally set `SALESFORCE_CLI_TARGET_ORG` to target a specific org.
- Username/Password (Legacy): If `SALESFORCE_ACCESS_TOKEN` and `SALESFORCE_INSTANCE_URL` are not set, the server will fall back to using `SALESFORCE_USERNAME`, `SALESFORCE_PASSWORD`, and `SALESFORCE_SECURITY_TOKEN`.
Environment Configuration
- `SALESFORCE_DOMAIN` (Optional): Set to `test` to connect to a Salesforce sandbox environment. If not set or left empty, the server will connect to the production environment.
- `SALESFORCE_CLI_TARGET_ORG` (Optional): When using the Salesforce CLI authentication method, set this to target a specific org alias or username instead of the default org.
Frequently asked questions
What is MCP-Salesforce?
MCP-Salesforce is MCP Salesforce connector Python-based implementation.
How do I install MCP-Salesforce?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is MCP-Salesforce open source?
Yes — it is hosted on GitHub at https://github.com/smn2gnt/MCP-Salesforce and has 142 stars.
Related MCP tools
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! Python-based implementation. Trusted by 11000+ developers.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP. Python-based implementation. Trusted by 4100+ developers.
Constrain, log and scan your MCP connections for security vulnerabilities. Python-based implementation. Trusted by 1200+ developers.
An MCP server that autonomously evaluates web applications. Python-based implementation. Trusted by 1100+ developers. Trusted by 1100+ developers.
Connect AI models like Claude & GPT with robots using MCP and ROS. Python-based implementation. Trusted by 800+ developers.
This MCP server allows Claude and other AI assistants to access your LinkedIn. Scrape LinkedIn profiles and companies, get your recommended jobs, and perform...
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP