Provides tools for Salesforce lead and permission set management, including creating leads, creating new permission sets, and assigning permission sets to users.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Salesforce MCP Server create a lead for Jane Doe at Acme Inc with jane@acme.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A FastAPI-based MCP (Model Context Protocol) server for Salesforce Agentforce Registry (Beta).
MCP Protocol Support: Implements initialize, tools/list, and tools/call endpoints
Streamable HTTP: Uses standard HTTP POST requests (not SSE)
Salesforce Integration: Provides tools for lead management and permission sets
Production Ready: Includes proper logging, error handling, and JSON responses
Related MCP server: Salesforce MCP Server
createLead: Create a new Salesforce Lead
Parameters: first_name, last_name, email, company
assignPermissionSet: Assign a permission set to a user
Parameters: username, permission_set_name
createPermissionSet: Create a new permission set
Parameters: ps_name, ps_label
Install dependencies:
pip install -r requirements.txtConfigure environment variables in .env:
SALESFORCE_CLIENT_ID=your_client_id
SALESFORCE_CLIENT_SECRET=your_client_secret
SALESFORCE_USERNAME=your_username
SALESFORCE_PASSWORD=your_password
SALESFORCE_TOKEN_URL=https://login.salesforce.com/services/oauth2/tokenRun the server:
uvicorn main:app --host 0.0.0.0 --port 8000 --reloadGET /: Health check
POST /mcp: MCP protocol endpoint
The server strictly follows the MCP protocol with JSON responses containing:
id: Request ID
type: Response type ("result" or "error")
result: Response data for successful operations
All incoming requests and operations are logged for debugging purposes.
This server cannot be deployed
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
Give AI agents the LinkedIn tools to find, qualify, engage, and follow up with prospects.
Search, summarize, and update your RevOrbit CRM (leads, deals, contacts, tasks) in plain language.
Manage authorized Rafi leads, reminders, DNC status, and AI voice playbooks.
