Salesforce MCP Server
Enables interaction with Salesforce orgs to perform operations like querying data with SOQL, managing records, and executing Apex code. It provides configurable access levels and support for both standard and Tooling APIs via natural language interfaces.
README
Salesforce MCP Server
Setup
uv venv .venv
uv pip install --python .venv/bin/python -e .
Configuration
Set environment variables for authentication:
Username/Password (default):
SALESFORCE_USERNAME=your-username
SALESFORCE_PASSWORD=your-password
SALESFORCE_SECURITY_TOKEN=your-token
SALESFORCE_DOMAIN=login # or "test" for sandbox
Note: SOAP API login is disabled by default in newer Salesforce orgs. To enable it:
- Go to Setup → Quick Find → User Interface
- Under API Settings, enable Enable SOAP API login()
- Click Save
OAuth (alternative, recommended for enterprise):
SALESFORCE_ACCESS_TOKEN=your-token
SALESFORCE_INSTANCE_URL=https://your-instance.salesforce.com
Access Mode
Control which tools are available by setting SALESFORCE_ACCESS_MODE:
| Value | Tools Available | Use Case |
|---|---|---|
read |
list_objects, describe_object, run_soql_query, run_sosl_search, get_record | Safe exploration, reporting, read-only integrations |
read_write |
All read tools + create_record, update_record | Day-to-day CRM operations |
all (default) |
All tools including delete_record, tooling_execute, apex_execute, restful | Full API access |
Recommended Security Levels
| Environment | Recommended Mode | Rationale |
|---|---|---|
| Production (end users) | read |
Prevents accidental data modification |
| Production (trusted ops) | read_write |
Allows CRM data entry, blocks deletes and raw API |
| Sandbox / Development | all |
Full access for testing and development |
| Demo / Exploration | read |
Safe for exploring org structure and data |
Set it in your environment or MCP server config:
SALESFORCE_ACCESS_MODE=read
Tip: When using this server with MintMCP, you can configure fine-grained per-tool permissions directly in MintMCP instead of using the env var. This gives you more granular control (e.g., allow create but not update) without needing to restart the server.
Tool Permissions by Access Mode
MCP tool annotations (readOnlyHint, destructiveHint) are set on each tool so MCP clients can enforce additional policies:
| Tool | Access Mode | readOnlyHint | destructiveHint | openWorldHint |
|---|---|---|---|---|
list_objects |
read | true | — | — |
describe_object |
read | true | — | — |
run_soql_query |
read | true | — | — |
run_sosl_search |
read | true | — | — |
get_record |
read | true | — | — |
create_record |
read_write | false | — | — |
update_record |
read_write | false | — | — |
delete_record |
all | false | true | — |
tooling_execute |
all | false | — | true |
apex_execute |
all | false | — | true |
restful |
all | false | — | true |
Run
.venv/bin/python -m salesforce_mcp
Tools
| Tool | Description |
|---|---|
list_objects |
List all Salesforce objects in the org (with optional search filter) |
describe_object |
Get fields, relationships, picklist values, and record types for an object |
run_soql_query |
Execute a SOQL query |
run_sosl_search |
Cross-object full-text search via SOSL |
get_record |
Get a single record by ID |
create_record |
Create a new record |
update_record |
Update fields on an existing record |
delete_record |
Permanently delete a record |
tooling_execute |
Salesforce Tooling API (metadata, Apex classes, custom fields) |
apex_execute |
Call custom Apex REST endpoints |
restful |
Generic Salesforce REST API call |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.