Agentforce MCP Integration Server
Enables MCP clients to connect to LLM/API services using the Model Context Protocol, providing real-time interaction and tool access. Also offers RESTful API endpoints via FastAPI for programmatic integration with existing systems.
README
🧩 Agentforce MCP Integration Server
This repository provides a unified solution for integrating Model Context Protocol (MCP) clients and REST API applications with LLM using the Python SDK.
It includes two core components:
- MCP Server – Enables any MCP-compatible client to communicate directly with an LLM/API.
- FastAPI Server – Offers RESTful API endpoints for invoking the LLM/API programmatically.
Both servers are built to ensure seamless connectivity, secure authentication, and consistent performance across integration channels.
📘 Overview
The repository implements two key servers designed for different modes of communication:
-
MCP Server Enables MCP clients to connect to LLM/API using the standardized Model Context Protocol. This allows real-time interaction and dynamic tool access through supported MCP clients and inspectors.
-
FastAPI Server Provides RESTful access to LLM/API, making it easy to integrate into existing systems or applications using simple HTTP requests.
Both implementations utilize the Agentforce Python SDK to communicate with Salesforce and the Agentforce backend, ensuring reliability and consistency.
⚙️ Setup Instructions
1. Repository Setup
Clone the repository and configure the required environment variables:
git clone hhttps://github.com/rajpatidar35/custommcp
cd custommcp
⚠️ Note: Ensure these credentials correspond to a valid CRED to access LLM/API.
2. Dependency Installation
Install all required Python dependencies using:
pip install -r requirements.txt
This will install all necessary libraries for both MCP and FastAPI servers, including the Agentforce Python SDK.
🚀 Running the Servers
🧠 Start MCP Server
To start the MCP server (used for MCP clients and inspectors):
python ./src/serverllm.py
The MCP server will initialize and listen for incoming MCP client connections.
🌐 Start FastAPI Server
To run the FastAPI server for REST API access:
fastapi dev ./src/serverllm.py
This launches a development instance of the FastAPI application, exposing REST endpoints that interact with Agentforce Agents.
🔍 Inspector Server (Optional)
To test and debug the MCP server using the MCP Inspector tool:
-
Start the Inspector server:
npx @modelcontextprotocol/inspector -
Open the Inspector web interface (default port:
http://localhost:5173or as shown in the console). -
Connect to your running MCP server using the host URL:
https://localhost:8000/mcp -
Navigate to the Tools tab to explore and test the available MCP tools.
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。