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.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.