Salesforce Lite

Simple and lightweight Salesforce MCP server for connecting AI assistants to Salesforce data. Ideal for prototyping and small projects.

📦 Install from PyPI:pip install mcp-salesforce-lite

🔗 PyPI Package:https://pypi.org/project/mcp-salesforce-lite/

📚 GitHub Repository:https://github.com/luvl/mcp-salesforce-lite

# Install the package pip install mcp-salesforce-lite # Use with Claude Desktop (recommended) uvx --from mcp-salesforce-lite mcp-salesforce-lite # Or run directly mcp-salesforce-lite

{ "mcpServers": { "salesforce-lite": { "command": "uvx", "args": [ "--from", "mcp-salesforce-lite", "mcp-salesforce-lite" ], "env": { "SALESFORCE_ACCESS_TOKEN": "your_access_token", "SALESFORCE_INSTANCE_URL": "your_instance_url" } } } }

Replace the environment variables in the configuration:

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

After saving the configuration, restart Claude Desktop. You should see a hammer icon indicating that tools are available.

- "List available Salesforce objects"
- "Describe the Account object"
- "Execute a SOQL query to get recent leads"

- Python 3.10 or higher
- Salesforce Developer/Production org
- Connected App configured in Salesforce

If you want to modify or contribute to this MCP server, follow these development setup instructions.

Option 1: Using uv (Recommended for development)

# Install uv if you haven't already brew install uv # macOS # or curl -LsSf https://astral.sh/uv/install.sh | sh # Linux/macOS # Clone and install the server git clone https://github.com/luvl/mcp-salesforce-lite.git cd mcp-salesforce-lite uv sync

git clone https://github.com/luvl/mcp-salesforce-lite.git cd mcp-salesforce-lite poetry install

SALESFORCE_ACCESS_TOKEN=your_access_token SALESFORCE_INSTANCE_URL=your_instance_url

First, make sure you have your Salesforce credentials configured in your.envfile.

# Run the server directly python src/mcp_salesforce_lite/server.py

# Run with Poetry poetry run python src/mcp_salesforce_lite/server.py

# Run with UV uv run python src/mcp_salesforce_lite/server.py

If you have the MCP CLI installed, you can test your server:

# Test with MCP Inspector mcp inspector # Or run in development mode mcp dev src/mcp_salesforce_lite/server.py

How to Release the Server as a Pip Package

The server can be packaged and distributed via PyPI using the includedpyproject.tomlconfiguration.

The server provides the following tools that AI assistants can use:

- soql_query: Execute SOQL queries (schema must be defined to carefully ask for confirmation of UPDATE and DELETE operations)
- search_records: Search records across multiple objects with limit and pagination
- get_record: Retrieve a specific record by ID with limit and pagination

- create_record: Create new records (make sure to describe_object first, and find the reference fields of the objects)
- update_record: Update existing records
- delete_record: Delete records

- describe_object_definition: Get object metadata and field information with pagination
- list_avail_objects: List available Salesforce objects with limit and pagination

If you're developing or running the server from source, you can use these alternative configurations:

💡 Tip:Example configuration files are provided in theexamples/directory:

- examples/claude_config_direct.json- Direct Python execution
- examples/claude_config_poetry.json- Poetry execution
- examples/claude_config_uv.json- UV execution (recommended)

{ "mcpServers": { "salesforce-lite": { "command": "python", "args": ["/ABSOLUTE/PATH/TO/mcp-salesforce-lite/src/mcp_salesforce_lite/server.py"], "env": { "SALESFORCE_ACCESS_TOKEN": "your_access_token", "SALESFORCE_INSTANCE_URL": "your_instance_url" } } } }

{ "mcpServers": { "salesforce-lite": { "command": "poetry", "args": [ "--directory", "/ABSOLUTE/PATH/TO/mcp-salesforce-lite", "run", "python", "src/mcp_salesforce_lite/server.py" ], "env": { "SALESFORCE_ACCESS_TOKEN": "your_access_token", "SALESFORCE_INSTANCE_URL": "your_instance_url" } } } }

Option 3: UV Execution (Recommended for Development)

{ "mcpServers": { "salesforce-lite": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/mcp-salesforce-lite", "run", "python", "src/mcp_salesforce_lite/server.py" ], "env": { "SALESFORCE_ACCESS_TOKEN": "your_access_token", "SALESFORCE_INSTANCE_URL": "your_instance_url" } } } }

mcp-salesforce-lite/ ├── src/ │ └── mcp_salesforce_lite/ │ ├── __init__.py │ ├── server.py # Main MCP server │ ├── client.py # Salesforce client wrapper │ ├── config.py # Configuration management │ └── tools/ │ ├── __init__.py │ ├── query.py # SOQL query tools │ ├── crud.py # Create, Read, Update, Delete tools │ └── metadata.py # Object metadata tools ├── examples/ │ ├── basic_usage.py │ └── claude_config.json ├── assets/ │ └── sf-demo.gif # Demo GIF showing usage ├── .env.example ├── pyproject.toml ├── poetry.lock └── uv.lock

- Register for PyPI Production: Go tohttps://pypi.org/account/register/
- Enable 2FA: Set up two-factor authentication in your account settings
- Create API Token: Go tohttps://pypi.org/manage/account/token/and create a token
- Update .pypirc: Replacepypi-YOUR_PRODUCTION_TOKEN_FROM_PYPI_ORG_HEREwith your actual token

# Build the package uv build # or: poetry build # Upload to TestPyPI twine upload --repository testpypi --config-file .pypirc dist/ # Test install from TestPyPI pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ mcp-salesforce-lite

# Upload to production PyPI twine upload --repository pypi --config-file .pypirc dist/ # Test install from production PyPI pip install mcp-salesforce-lite

A read-only MCP server for querying live Salesforce Einstein data using a CData JDBC driver.