Salesforce MCP Server for Heroku
Enables AI agents to interact with Salesforce CRM data by executing SOQL queries and managing records. It provides tools for object metadata discovery and record operations, specifically optimized for Heroku deployment.
README
Salesforce MCP Server for Heroku
A Model Context Protocol (MCP) server that enables AI agents to interact with Salesforce CRM data.
Features
- SOQL Queries - Execute any SOQL query against your Salesforce org
- Object Metadata - Discover fields and relationships for any object
- Record Management - Create, update, and delete records
- Heroku Native - Designed for Heroku deployment with MCP process support
Available Tools
| Tool | Description |
|---|---|
query |
Execute SOQL queries |
describe_object |
Get object metadata (fields, types, relationships) |
create |
Create new records |
update |
Update existing records |
delete |
Delete records |
Deployment
One-Click Deploy
Click the "Deploy to Heroku" button above, then configure your Salesforce credentials.
Manual Deploy
git clone https://github.com/dsouza-anush/mcp-salesforce
cd mcp-salesforce
heroku create my-salesforce-mcp
git push heroku main
Configure Credentials
heroku config:set SF_USERNAME=your-username@example.com
heroku config:set SF_PASSWORD=your-password
heroku config:set SF_SECURITY_TOKEN=your-security-token
heroku config:set SF_LOGIN_URL=https://login.salesforce.com
For sandbox orgs, use https://test.salesforce.com as the login URL.
Register with Heroku AI
After deployment, attach your Heroku AI model:
heroku addons:attach your-main-app::INFERENCE -a my-salesforce-mcp
The mcp-salesforce process is now available via /v1/agents/heroku.
Usage Example
from openai import OpenAI
client = OpenAI(
base_url=os.getenv("INFERENCE_URL") + "/v1",
api_key=os.getenv("INFERENCE_KEY")
)
response = client.chat.completions.create(
model=os.getenv("INFERENCE_MODEL_ID"),
messages=[
{"role": "user", "content": "Find all opportunities closing this quarter"}
],
extra_body={
"heroku": {
"mcp_servers": ["mcp-salesforce"]
}
}
)
Environment Variables
| Variable | Description | Required |
|---|---|---|
SF_LOGIN_URL |
Salesforce login URL | No (defaults to production) |
SF_USERNAME |
Salesforce username | Yes |
SF_PASSWORD |
Salesforce password | Yes |
SF_SECURITY_TOKEN |
Security token (if required) | No |
API_KEY |
API key for web endpoint | No |
License
MIT
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.
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.
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.
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.