
Salesforce MCP Integration
A Model Context Protocol server that allows execution of SOQL queries and interaction with Salesforce data through a standardized interface.
README
Salesforce MCP Integration
This project provides a Model Context Protocol (MCP) server for Salesforce integration, allowing you to execute SOQL queries and interact with Salesforce data through a standardized interface.
Features
- Connect to Salesforce orgs using environment variables
- Execute SOQL queries against Salesforce data
- Retrieve and process Salesforce records
- Secure credential management using environment variables
Prerequisites
- Node.js (v14 or higher)
- npm (Node Package Manager)
- Salesforce org with API access
- Salesforce credentials (username, password, and security token)
Installation
-
Clone this repository:
git clone <repository-url> cd <repository-directory>
-
Install dependencies:
npm install
-
Create a
.env
file in the root directory with your Salesforce credentials:SF_LOGIN_URL=https://your-instance.salesforce.com/ SF_USERNAME=your_username SF_PASSWORD=your_password SF_SECURITY_TOKEN=your_security_token PORT=3000
Note: For sandbox environments, use
https://test.salesforce.com/
as the login URL.
Usage
Starting the MCP Server
Run the server using Node.js:
node server.js
The server will connect to Salesforce using the credentials in your .env
file and start listening for MCP requests.
Executing SOQL Queries
Once the server is running, you can execute SOQL queries through the MCP interface. The server provides a soqlQuery
tool that accepts SOQL queries and returns the results.
Example SOQL query:
SELECT Id, Name, Status FROM Account LIMIT 5
Project Structure
server.js
- Main MCP server implementation.env
- Environment variables for Salesforce credentialspackage.json
- Project dependencies and scripts
Security Considerations
- Never commit your
.env
file to version control - Add
.env
to your.gitignore
file - Use environment variables for all sensitive information
- Consider using a more secure authentication method for production environments
Troubleshooting
Connection Issues
If you encounter connection issues:
- Verify your Salesforce credentials in the
.env
file - Check that your Salesforce org is accessible
- Ensure your IP address is whitelisted in Salesforce (if required)
- Verify that your Salesforce user has API access
Query Errors
If your SOQL queries fail:
- Check the SOQL syntax
- Verify that the objects and fields exist in your org
- Ensure your user has permission to access the objects and fields
License
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。