Salesforce MCP
Enables AI agents to query, mutate, and analyze Salesforce CRM data natively through the Model Context Protocol, without requiring API glue code.
README
☁️ Salesforce CRM Model Context Protocol (MCP)
Turn your AI into a fully autonomous sales operations manager. This server provides a native Model Context Protocol bridge directly into Salesforce CRM, allowing large language models (LLMs) to natively query, mutate, and analyze your enterprise data pipeline without writing a single line of API glue code.
Why use this integration?
Connecting ChatGPT, Claude, or any custom agent to your CRM usually involves brittle Zapier flows or custom middleware. This MCP exposes a structured, intent-driven interface. Whether you need to run complex SOQL aggregates or execute routine CRUD operations on custom objects, the agent handles it safely.
Built for the Vinkius Edge Platform
We designed this connector specifically to be hosted on the Vinkius Edge. When you deploy your agentic infrastructure on Vinkius, you benefit from:
- Zero-Trust Security: Vinkius securely stores your Salesforce OAuth tokens. The AI never sees your underlying credentials.
- Edge Performance: Running on V8 isolates via Vinkius guarantees ultra-low latency, crucial when AI agents execute multi-step SOQL chain reasoning.
- Instant Scale: Stop managing Node.js PM2 servers. Vinkius handles the infrastructure seamlessly.
Available Agentic Capabilities
The server registers 12 distinct tools designed for semantic consumption:
- Data Retrieval: Execute raw
soql_queryor use optimizedlist_accounts,list_contacts, andlist_opportunitiesfetchers. - Deep Exploration: The
global_searchtool leverages SOSL to find entities across the entire Salesforce org instantly. - Full Lifecycle: Complete
get_record,create_record,update_record, anddelete_recordsupport for standard and custom SObjects. - Analytics: Expose your existing pipeline dashboards directly to the LLM via
list_reportsandrun_report.
🚀 Deployment Guide
To get this running on the Vinkius Edge Marketplace:
- Pull the repository to your environment.
- Initialize the deployment to Vinkius:
npx mcpfusion deploy
Within seconds, your MCP will be globally distributed and available for connection.
🔗 Claim your free edge hosting for the Salesforce MCP on Vinkius
Testing Locally
For engineers modifying the core engine using @mcpfusion/core:
npm install && npm run dev
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。