# How to integrate Salesforce service cloud MCP with LlamaIndex ```json { "title": "How to integrate Salesforce service cloud MCP with LlamaIndex", "toolkit": "Salesforce service cloud", "toolkit_slug": "salesforce_service_cloud", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/salesforce_service_cloud/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/salesforce_service_cloud/framework/llama-index.md", "updated_at": "2026-05-12T10:24:36.668Z" } ``` ## Introduction This guide walks you through connecting Salesforce service cloud to LlamaIndex using the Composio tool router. By the end, you'll have a working Salesforce service cloud agent that can list all open support cases for today, update case status to resolved for customer, fetch recent customer interactions for an account through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a Salesforce service cloud account through Composio's Salesforce service cloud MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Salesforce service cloud with - [ChatGPT](https://composio.dev/toolkits/salesforce_service_cloud/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/salesforce_service_cloud/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/salesforce_service_cloud/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/salesforce_service_cloud/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/salesforce_service_cloud/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/salesforce_service_cloud/framework/codex) - [Cursor](https://composio.dev/toolkits/salesforce_service_cloud/framework/cursor) - [VS Code](https://composio.dev/toolkits/salesforce_service_cloud/framework/vscode) - [OpenCode](https://composio.dev/toolkits/salesforce_service_cloud/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/salesforce_service_cloud/framework/openclaw) - [Hermes](https://composio.dev/toolkits/salesforce_service_cloud/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/salesforce_service_cloud/framework/cli) - [Google ADK](https://composio.dev/toolkits/salesforce_service_cloud/framework/google-adk) - [LangChain](https://composio.dev/toolkits/salesforce_service_cloud/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/salesforce_service_cloud/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/salesforce_service_cloud/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/salesforce_service_cloud/framework/crew-ai) ## TL;DR Here's what you'll learn: - Set your OpenAI and Composio API keys - Install LlamaIndex and Composio packages - Create a Composio Tool Router session for Salesforce service cloud - Connect LlamaIndex to the Salesforce service cloud MCP server - Build a Salesforce service cloud-powered agent using LlamaIndex - Interact with Salesforce service cloud through natural language ## What is LlamaIndex? LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools. Key features include: - ReAct Agent: Reasoning and acting pattern for tool-using agents - MCP Tools: Native support for Model Context Protocol - Context Management: Maintain conversation context across interactions - Async Support: Built for async/await patterns ## What is the Salesforce service cloud MCP server, and what's possible with it? The Salesforce service cloud MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Salesforce Service Cloud account. It provides structured and secure access to your customer service data, so your agent can perform actions like managing cases, retrieving knowledge articles, automating service processes, and tracking customer interactions on your behalf. - Case management and triage: Empower your agent to create, update, assign, or close customer service cases, ensuring timely resolution of inquiries and incidents. - Knowledge base retrieval: Let your agent search, read, and recommend relevant knowledge articles to assist with customer support and internal troubleshooting. - Customer interaction tracking: Have your agent log new interactions, fetch historical communication, and surface recent touchpoints for a full view of customer engagement. - Omnichannel support automation: Enable your agent to route cases, escalate issues, and manage service requests across chat, email, phone, and social channels all from one place. - Service workflow automation: Direct your agent to trigger macros, update case statuses, or launch automated actions to streamline repetitive tasks and boost support team productivity. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `SALESFORCE_SERVICE_CLOUD_CHASITOR_SNEAK_PEEK` | Chasitor Sneak Peek | Send real-time typing indicator (sneak peek) to Live Agent during active chat session. Allows agents to see what visitors are typing before the message is sent. Requires an active Live Agent chat session with valid session_key and affinity token. The sequence number must increment with each request. | | `SALESFORCE_SERVICE_CLOUD_COMPOSITE_BATCH` | Composite Batch | Tool to execute multiple independent REST subrequests in one batch call. Use when bundling up to 25 independent operations to minimize round trips. Subrequests cannot reference each other. | | `SALESFORCE_SERVICE_CLOUD_COMPOSITE_REQUEST` | Composite Request | Execute up to 25 dependent Salesforce REST subrequests in a single API call. Subrequests execute sequentially and can reference results from earlier requests using '@{referenceId.field}' syntax. Use this when operations depend on each other (e.g., create Account then create related Contact). For independent operations, use Composite Batch instead. | | `SALESFORCE_SERVICE_CLOUD_COMPOSITE_SOBJECT_TREE` | Composite SObject Tree | Create one or more nested sObject record trees in a single API call. Supports parent-child relationships up to 5 levels deep, with a maximum of 200 total records across all trees. Use this for bulk insertion of related records (e.g., Account with Contacts, or Orders with Line Items). Relationships must be Master-Detail or Lookup. Only supports INSERT operations, not upserts. | | `SALESFORCE_SERVICE_CLOUD_CREATE_CASE_RECORD` | Create Case Record | Tool to create or upsert a Salesforce Case record. Use when you need to add a new Case or update via external ID. | | `SALESFORCE_SERVICE_CLOUD_DELETE_CASE_RECORD` | Delete Case Record | Tool to delete a Salesforce Case record. Use when you need to remove a case by its record ID. | | `SALESFORCE_SERVICE_CLOUD_DESCRIBE_S_OBJECT` | Describe SObject | Tool to retrieve metadata of any sObject. Use when you need to inspect field definitions, relationships, and supported features for objects like Account, Contact, Case, etc. | | `SALESFORCE_SERVICE_CLOUD_GENERATE_REQUEST_ID` | Generate Request ID | Generate a UUIDv4 string to use as an Idempotency-Key header in Salesforce User Interface API requests. This prevents duplicate record creation when POST, PATCH, or DELETE requests are retried due to network failures or timeouts. The same key returns cached responses for 30 days, avoiding duplicate operations and saving server resources. Use this tool whenever you need to ensure idempotent behavior for Salesforce UI API operations. | | `SALESFORCE_SERVICE_CLOUD_GENERATE_SIGNED_JWT_ASSERTION` | Generate Signed JWT Assertion | Tool to generate a signed JWT assertion for Salesforce JWT bearer OAuth flow. Use when you need to perform server-to-server authentication using a connected app’s certificate. Use before exchanging the assertion for an access token. | | `SALESFORCE_SERVICE_CLOUD_GET_CASE_RECORD` | Get Case Record | Retrieve a Salesforce Case record by its ID. Returns Case details including status, priority, subject, description, owner, and timestamps. Useful for: - Looking up Case details by ID - Checking Case status and priority - Getting customer issue information - Retrieving Case metadata and relationships Requires a valid 15 or 18-character Salesforce Case ID. Optionally specify which fields to retrieve using the fields parameter; otherwise all accessible fields are returned. | | `SALESFORCE_SERVICE_CLOUD_GET_CHAT_MESSAGES` | Get Chat Messages | Tool to long-poll for chat messages/events. Use after CreateChatSession to retrieve incoming chat events. Returns empty messages list when no new messages (HTTP 204). Call with ack from prior response to maintain sequence. | | `SALESFORCE_SERVICE_CLOUD_GET_LIVE_AGENT_API_VERSION` | Get Live Agent API Version | Tool to retrieve current Live Agent API version. Use when initializing chat sessions to ensure subsequent calls target the correct REST API version. | | `SALESFORCE_SERVICE_CLOUD_LIST_EINSTEIN_BOTS` | List Einstein Bots | Lists all Einstein Bot definitions in the Salesforce organization. This action queries the BotDefinition object using the Salesforce Tooling API to retrieve metadata about all Einstein Bots, including their IDs, labels, developer names, and language settings. Use this action when you need to: - Get a list of available Einstein Bots in the org - Find valid bot IDs for use with other Einstein Bots API operations - Retrieve bot metadata such as names and language settings Returns an empty list if no bots exist or if Tooling API access is unavailable. | | `SALESFORCE_SERVICE_CLOUD_QUERY_ALL_SOQL` | Query All SOQL | Tool to execute a SOQL query including deleted and archived records. Use when you need to fetch all rows including soft-deleted data in Salesforce. | | `SALESFORCE_SERVICE_CLOUD_QUERY_SOQL` | Query SOQL | Tool to execute a SOQL query. Use when you need to retrieve records from Salesforce via SOQL. | | `SALESFORCE_SERVICE_CLOUD_RECONNECT_CHAT_SESSION` | Reconnect Chat Session | Tool to reconnect a Live Agent chat session after the affinity token changes. Use this when you receive a 503 (Service Unavailable) response during chat operations, indicating the affinity token has changed and the session needs to be reestablished on a new server. After reconnecting, you must call ResyncChasitorState to restore the visitor's chat context. Note: Requires valid session_key and affinity tokens from an active Live Agent chat session. | | `SALESFORCE_SERVICE_CLOUD_RESYNC_CHASITOR_STATE` | Resync Chasitor State | Resynchronizes the chat visitor's state after a session reconnection. This action is part of the Salesforce Live Agent chat session recovery workflow: 1. First, call ReconnectChatSession with the session_key and affinity_token 2. Then, call this action to restore the visitor's chat state 3. Finally, resume normal chat operations (sending messages, getting messages, etc.) Prerequisites: - An active or recently disconnected Live Agent chat session - Valid session_key and affinity_token from the original session - Live Agent must be properly configured in the Salesforce org Note: The legacy Live Agent product is being phased out in favor of Messaging for In-App and Web. This action sends a POST request to /chat/rest/Chasitor/ChasitorResyncState with required Live Agent headers but no request body. | | `SALESFORCE_SERVICE_CLOUD_RETRIEVE_CONNECTED_APP_PRIVATE_KEY` | Retrieve Connected App Private Key | Tool to retrieve RSA private key PEM for a Salesforce Connected App. Use when signing JWT assertions for OAuth flows. Provide the app's Connected App ID and optional secret name or file path. Use before generating signed JWTs. | | `SALESFORCE_SERVICE_CLOUD_RETRIEVE_SALESFORCE_USERNAME` | Retrieve Salesforce Username | Tool to retrieve the Salesforce username. Use when you need the current authenticated user's username. Use after completing OAuth2 authentication. | | `SALESFORCE_SERVICE_CLOUD_SEND_CUSTOM_EVENT` | Send Custom Event | Send a custom event from a chat visitor to a Live Agent during an active chat session. Use this tool to trigger custom event handlers on the agent's side, enabling custom interactions beyond standard chat messages. Custom events can be used for actions like form submissions, button clicks, page navigation, or any application-specific events that need to be communicated to the agent. Prerequisites: - An active Live Agent chat session must be established - Live Agent REST API must be configured and enabled in your Salesforce org - Valid session_key and affinity_token from session initialization Note: This endpoint requires Live Agent to be properly configured. The API typically returns 204 No Content on success. | | `SALESFORCE_SERVICE_CLOUD_SET_BREADCRUMB` | Set Breadcrumb | Tool to set a breadcrumb URL for the visitor's current page. Use after a visitor navigates to a new page during an active chat session. | | `SALESFORCE_SERVICE_CLOUD_UPLOAD_FILE_TO_S3` | Upload File to S3 | Tool to upload a file to managed S3 storage. Use when you need to persist files externally. | | `SALESFORCE_SERVICE_CLOUD_VISITOR_SENSITIVE_DATA_RULE` | Visitor Sensitive Data Rule Triggered | Tool to trigger sensitive data rules for the chat visitor. Use after detecting sensitive content to apply visitor masking or handling rules. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Salesforce service cloud MCP server is an implementation of the Model Context Protocol that connects your AI agent to Salesforce service cloud. It provides structured and secure access so your agent can perform Salesforce service cloud operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before you begin, make sure you have: - Python 3.8/Node 16 or higher installed - A Composio account with the API key - An OpenAI API key - A Salesforce service cloud account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and Salesforce service cloud No description provided. ### 2. Installing dependencies No description provided. ```python pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv ``` ```typescript npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv ``` ### 3. Set environment variables Create a .env file in your project root: These credentials will be used to: - Authenticate with OpenAI's GPT-5 model - Connect to Composio's Tool Router - Identify your Composio user session for Salesforce service cloud access ```bash OPENAI_API_KEY=your-openai-api-key COMPOSIO_API_KEY=your-composio-api-key COMPOSIO_USER_ID=your-user-id ``` ### 4. Import modules No description provided. ```python import asyncio import os import dotenv from composio import Composio from composio_llamaindex import LlamaIndexProvider from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI from llama_index.tools.mcp import BasicMCPClient, McpToolSpec dotenv.load_dotenv() ``` ```typescript import "dotenv/config"; import readline from "node:readline/promises"; import { stdin as input, stdout as output } from "node:process"; import { Composio } from "@composio/core"; import { mcp } from "@llamaindex/tools"; import { agent as createAgent } from "@llamaindex/workflow"; import { openai } from "@llamaindex/openai"; dotenv.config(); ``` ### 5. Load environment variables and initialize Composio No description provided. ```python OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not OPENAI_API_KEY: raise ValueError("OPENAI_API_KEY is not set in the environment") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set in the environment") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set in the environment") ``` ```typescript const OPENAI_API_KEY = process.env.OPENAI_API_KEY; const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY; const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID; if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set"); if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set"); if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set"); ``` ### 6. Create a Tool Router session and build the agent function What's happening here: - We create a Composio client using your API key and configure it with the LlamaIndex provider - We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, salesforce service cloud) - The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools - LlamaIndex will connect to this endpoint to dynamically discover and use the available Salesforce service cloud tools. - The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent. ```python async def build_agent() -> ReActAgent: composio_client = Composio( api_key=COMPOSIO_API_KEY, provider=LlamaIndexProvider(), ) session = composio_client.create( user_id=COMPOSIO_USER_ID, toolkits=["salesforce_service_cloud"], ) mcp_url = session.mcp.url print(f"Composio MCP URL: {mcp_url}") mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY}) mcp_tool_spec = McpToolSpec(client=mcp_client) tools = await mcp_tool_spec.to_tool_list_async() llm = OpenAI(model="gpt-5") description = "An agent that uses Composio Tool Router MCP tools to perform Salesforce service cloud actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Salesforce service cloud actions. """ return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True) ``` ```typescript async function buildAgent() { console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`); console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`); const composio = new Composio({ apiKey: COMPOSIO_API_KEY, provider: new LlamaindexProvider(), }); const session = await composio.create( COMPOSIO_USER_ID!, { toolkits: ["salesforce_service_cloud"], }, ); const mcpUrl = session.mcp.url; console.log(`Composio Tool Router MCP URL: ${mcpUrl}`); const server = mcp({ url: mcpUrl, clientName: "composio_tool_router_with_llamaindex", requestInit: { headers: { "x-api-key": COMPOSIO_API_KEY!, }, }, // verbose: true, }); const tools = await server.tools(); const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" }); const agent = createAgent({ name: "composio_tool_router_with_llamaindex", description : "An agent that uses Composio Tool Router MCP tools to perform actions.", systemPrompt: "You are a helpful assistant connected to Composio Tool Router."+ "Use the available tools to answer user queries and perform Salesforce service cloud actions." , llm, tools, }); return agent; } ``` ### 7. Create an interactive chat loop No description provided. ```python async def chat_loop(agent: ReActAgent) -> None: ctx = Context(agent) print("Type 'quit', 'exit', or Ctrl+C to stop.") while True: try: user_input = input("\nYou: ").strip() except (KeyboardInterrupt, EOFError): print("\nBye!") break if not user_input or user_input.lower() in {"quit", "exit"}: print("Bye!") break try: print("Agent: ", end="", flush=True) handler = agent.run(user_input, ctx=ctx) async for event in handler.stream_events(): # Stream token-by-token from LLM responses if hasattr(event, "delta") and event.delta: print(event.delta, end="", flush=True) # Show tool calls as they happen elif hasattr(event, "tool_name"): print(f"\n[Using tool: {event.tool_name}]", flush=True) # Get final response response = await handler print() # Newline after streaming except KeyboardInterrupt: print("\n[Interrupted]") continue except Exception as e: print(f"\nError: {e}") ``` ```typescript async function chatLoop(agent: ReturnType) { const rl = readline.createInterface({ input, output }); console.log("Type 'quit' or 'exit' to stop."); while (true) { let userInput: string; try { userInput = (await rl.question("\nYou: ")).trim(); } catch { console.log("\nAgent: Bye!"); break; } if (!userInput) { continue; } const lower = userInput.toLowerCase(); if (lower === "quit" || lower === "exit") { console.log("Agent: Bye!"); break; } try { process.stdout.write("Agent: "); const stream = agent.runStream(userInput); let finalResult: any = null; for await (const event of stream) { // The event.data contains the streamed content const data: any = event.data; // Check for streaming delta content if (data?.delta) { process.stdout.write(data.delta); } // Store final result for fallback if (data?.result || data?.message) { finalResult = data; } } // If no streaming happened, show the final result if (finalResult) { const answer = finalResult.result ?? finalResult.message?.content ?? finalResult.message ?? ""; if (answer && typeof answer === "string" && !answer.includes("[object")) { process.stdout.write(answer); } } console.log(); // New line after streaming completes } catch (err: any) { console.error("\nAgent error:", err?.message ?? err); } } rl.close(); } ``` ### 8. Define the main entry point What's happening here: - We're orchestrating the entire application flow - The agent gets built with proper error handling - Then we kick off the interactive chat loop so you can start talking to Salesforce service cloud ```python async def main() -> None: agent = await build_agent() await chat_loop(agent) if __name__ == "__main__": # Handle Ctrl+C gracefully signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0))) try: asyncio.run(main()) except KeyboardInterrupt: print("\nBye!") ``` ```typescript async function main() { try { const agent = await buildAgent(); await chatLoop(agent); } catch (err) { console.error("Failed to start agent:", err); process.exit(1); } } main(); ``` ### 9. Run the agent When prompted, authenticate and authorise your agent with Salesforce service cloud, then start asking questions. ```bash python llamaindex_agent.py ``` ```typescript npx ts-node llamaindex-agent.ts ``` ## Complete Code ```python import asyncio import os import signal import dotenv from composio import Composio from composio_llamaindex import LlamaIndexProvider from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI from llama_index.tools.mcp import BasicMCPClient, McpToolSpec dotenv.load_dotenv() OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not OPENAI_API_KEY: raise ValueError("OPENAI_API_KEY is not set") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set") async def build_agent() -> ReActAgent: composio_client = Composio( api_key=COMPOSIO_API_KEY, provider=LlamaIndexProvider(), ) session = composio_client.create( user_id=COMPOSIO_USER_ID, toolkits=["salesforce_service_cloud"], ) mcp_url = session.mcp.url print(f"Composio MCP URL: {mcp_url}") mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY}) mcp_tool_spec = McpToolSpec(client=mcp_client) tools = await mcp_tool_spec.to_tool_list_async() llm = OpenAI(model="gpt-5") description = "An agent that uses Composio Tool Router MCP tools to perform Salesforce service cloud actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Salesforce service cloud actions. """ return ReActAgent( tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True, ); async def chat_loop(agent: ReActAgent) -> None: ctx = Context(agent) print("Type 'quit', 'exit', or Ctrl+C to stop.") while True: try: user_input = input("\nYou: ").strip() except (KeyboardInterrupt, EOFError): print("\nBye!") break if not user_input or user_input.lower() in {"quit", "exit"}: print("Bye!") break try: print("Agent: ", end="", flush=True) handler = agent.run(user_input, ctx=ctx) async for event in handler.stream_events(): # Stream token-by-token from LLM responses if hasattr(event, "delta") and event.delta: print(event.delta, end="", flush=True) # Show tool calls as they happen elif hasattr(event, "tool_name"): print(f"\n[Using tool: {event.tool_name}]", flush=True) # Get final response response = await handler print() # Newline after streaming except KeyboardInterrupt: print("\n[Interrupted]") continue except Exception as e: print(f"\nError: {e}") async def main() -> None: agent = await build_agent() await chat_loop(agent) if __name__ == "__main__": # Handle Ctrl+C gracefully signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0))) try: asyncio.run(main()) except KeyboardInterrupt: print("\nBye!") ``` ```typescript import "dotenv/config"; import readline from "node:readline/promises"; import { stdin as input, stdout as output } from "node:process"; import { Composio } from "@composio/core"; import { LlamaindexProvider } from "@composio/llamaindex"; import { mcp } from "@llamaindex/tools"; import { agent as createAgent } from "@llamaindex/workflow"; import { openai } from "@llamaindex/openai"; dotenv.config(); const OPENAI_API_KEY = process.env.OPENAI_API_KEY; const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY; const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID; if (!OPENAI_API_KEY) { throw new Error("OPENAI_API_KEY is not set in the environment"); } if (!COMPOSIO_API_KEY) { throw new Error("COMPOSIO_API_KEY is not set in the environment"); } if (!COMPOSIO_USER_ID) { throw new Error("COMPOSIO_USER_ID is not set in the environment"); } async function buildAgent() { console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`); console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`); const composio = new Composio({ apiKey: COMPOSIO_API_KEY, provider: new LlamaindexProvider(), }); const session = await composio.create( COMPOSIO_USER_ID!, { toolkits: ["salesforce_service_cloud"], }, ); const mcpUrl = session.mcp.url; console.log(`Composio Tool Router MCP URL: ${mcpUrl}`); const server = mcp({ url: mcpUrl, clientName: "composio_tool_router_with_llamaindex", requestInit: { headers: { "x-api-key": COMPOSIO_API_KEY!, }, }, // verbose: true, }); const tools = await server.tools(); const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" }); const agent = createAgent({ name: "composio_tool_router_with_llamaindex", description: "An agent that uses Composio Tool Router MCP tools to perform actions.", systemPrompt: "You are a helpful assistant connected to Composio Tool Router."+ "Use the available tools to answer user queries and perform Salesforce service cloud actions." , llm, tools, }); return agent; } async function chatLoop(agent: ReturnType) { const rl = readline.createInterface({ input, output }); console.log("Type 'quit' or 'exit' to stop."); while (true) { let userInput: string; try { userInput = (await rl.question("\nYou: ")).trim(); } catch { console.log("\nAgent: Bye!"); break; } if (!userInput) { continue; } const lower = userInput.toLowerCase(); if (lower === "quit" || lower === "exit") { console.log("Agent: Bye!"); break; } try { process.stdout.write("Agent: "); const stream = agent.runStream(userInput); let finalResult: any = null; for await (const event of stream) { // The event.data contains the streamed content const data: any = event.data; // Check for streaming delta content if (data?.delta) { process.stdout.write(data.delta); } // Store final result for fallback if (data?.result || data?.message) { finalResult = data; } } // If no streaming happened, show the final result if (finalResult) { const answer = finalResult.result ?? finalResult.message?.content ?? finalResult.message ?? ""; if (answer && typeof answer === "string" && !answer.includes("[object")) { process.stdout.write(answer); } } console.log(); // New line after streaming completes } catch (err: any) { console.error("\nAgent error:", err?.message ?? err); } } rl.close(); } async function main() { try { const agent = await buildAgent(); await chatLoop(agent); } catch (err: any) { console.error("Failed to start agent:", err?.message ?? err); process.exit(1); } } main(); ``` ## Conclusion You've successfully connected Salesforce service cloud to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes Salesforce service cloud tools through an MCP endpoint - LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations - The agent becomes more capable without increasing prompt size - Async Python provides clean, efficient execution of agent workflows You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter. ## How to build Salesforce service cloud MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/salesforce_service_cloud/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/salesforce_service_cloud/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/salesforce_service_cloud/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/salesforce_service_cloud/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/salesforce_service_cloud/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/salesforce_service_cloud/framework/codex) - [Cursor](https://composio.dev/toolkits/salesforce_service_cloud/framework/cursor) - [VS Code](https://composio.dev/toolkits/salesforce_service_cloud/framework/vscode) - [OpenCode](https://composio.dev/toolkits/salesforce_service_cloud/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/salesforce_service_cloud/framework/openclaw) - [Hermes](https://composio.dev/toolkits/salesforce_service_cloud/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/salesforce_service_cloud/framework/cli) - [Google ADK](https://composio.dev/toolkits/salesforce_service_cloud/framework/google-adk) - [LangChain](https://composio.dev/toolkits/salesforce_service_cloud/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/salesforce_service_cloud/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/salesforce_service_cloud/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/salesforce_service_cloud/framework/crew-ai) ## Related Toolkits - [Hubspot](https://composio.dev/toolkits/hubspot) - HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place. - [Pipedrive](https://composio.dev/toolkits/pipedrive) - Pipedrive is a sales management platform offering pipeline visualization, lead tracking, and workflow automation. It helps sales teams keep deals moving forward efficiently and never miss a follow-up. - [Salesforce](https://composio.dev/toolkits/salesforce) - Salesforce is a leading CRM platform that helps businesses manage sales, service, and marketing. It centralizes customer data, enabling teams to drive growth and build strong relationships. - [Apollo](https://composio.dev/toolkits/apollo) - Apollo is a CRM and lead generation platform that helps businesses discover contacts and manage sales pipelines. Use it to streamline customer outreach and track your deals from one place. - [Attio](https://composio.dev/toolkits/attio) - Attio is a customizable CRM and workspace for managing your team's relationships and workflows. It helps teams organize contacts, automate tasks, and collaborate more efficiently. - [Acculynx](https://composio.dev/toolkits/acculynx) - AccuLynx is a cloud-based roofing business management software for contractors. It streamlines project tracking, lead management, and document sharing. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Affinity](https://composio.dev/toolkits/affinity) - Affinity is a relationship intelligence CRM that helps private capital investors find, manage, and close more deals. It streamlines deal flow and surfaces key connections to help you win opportunities. - [Agencyzoom](https://composio.dev/toolkits/agencyzoom) - AgencyZoom is a sales and performance platform built for P&C insurance agencies. It helps agents boost sales, retain clients, and analyze producer results in one place. - [Bettercontact](https://composio.dev/toolkits/bettercontact) - Bettercontact is a smart contact enrichment tool for finding emails and phone numbers. It helps boost lead generation with automated, waterfall search across multiple sources. - [Blackbaud](https://composio.dev/toolkits/blackbaud) - Blackbaud provides cloud-based software for nonprofits, schools, and healthcare institutions. It streamlines fundraising, donor management, and mission-driven operations. - [Brilliant directories](https://composio.dev/toolkits/brilliant_directories) - Brilliant Directories is an all-in-one platform for building and managing online membership communities and business directories. It streamlines listings, member management, and engagement tools into a single, easy interface. - [Capsule crm](https://composio.dev/toolkits/capsule_crm) - Capsule CRM is a user-friendly CRM platform for managing contacts and sales pipelines. It helps businesses organize relationships and streamline their sales process efficiently. - [Centralstationcrm](https://composio.dev/toolkits/centralstationcrm) - CentralStationCRM is an easy-to-use CRM software focused on collaboration and long-term customer relationships. It helps teams manage contacts, deals, and communications all in one place. - [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time. - [Close](https://composio.dev/toolkits/close) - Close is a CRM platform built for sales teams, combining calling, email automation, and predictive dialers. It streamlines sales workflows and boosts productivity with all-in-one communication tools. - [Dropcontact](https://composio.dev/toolkits/dropcontact) - Dropcontact is a B2B email finder and data enrichment service for professionals. It delivers verified email addresses and enriches contact info with up-to-date data. - [Dynamics365](https://composio.dev/toolkits/dynamics365) - Dynamics 365 is Microsoft's platform combining CRM, ERP, and productivity apps. It streamlines sales, marketing, service, and operations in one place. - [Espocrm](https://composio.dev/toolkits/espocrm) - EspoCRM is an open-source web application for managing customer relationships. It helps businesses organize contacts, track leads, and streamline their sales process. - [Fireberry](https://composio.dev/toolkits/fireberry) - Fireberry is a CRM platform that streamlines customer and sales management. It helps businesses organize contacts, automate sales, and integrate with other business tools. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Salesforce service cloud MCP? With a standalone Salesforce service cloud MCP server, the agents and LLMs can only access a fixed set of Salesforce service cloud tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Salesforce service cloud and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with LlamaIndex? Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Salesforce service cloud tools. ### Can I manage the permissions and scopes for Salesforce service cloud while using Tool Router? Yes, absolutely. You can configure which Salesforce service cloud scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do. ### How safe is my data with Composio Tool Router? All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Salesforce service cloud data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)