# How to integrate Forcemanager MCP with LlamaIndex ```json { "title": "How to integrate Forcemanager MCP with LlamaIndex", "toolkit": "Forcemanager", "toolkit_slug": "forcemanager", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/forcemanager/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/forcemanager/framework/llama-index.md", "updated_at": "2026-05-12T10:12:04.404Z" } ``` ## Introduction This guide walks you through connecting Forcemanager to LlamaIndex using the Composio tool router. By the end, you'll have a working Forcemanager agent that can delete a contact by their id, get details for a specific sales order, retrieve company info using company id through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a Forcemanager account through Composio's Forcemanager MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Forcemanager with - [OpenAI Agents SDK](https://composio.dev/toolkits/forcemanager/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/forcemanager/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/forcemanager/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/forcemanager/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/forcemanager/framework/codex) - [OpenClaw](https://composio.dev/toolkits/forcemanager/framework/openclaw) - [Hermes](https://composio.dev/toolkits/forcemanager/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/forcemanager/framework/cli) - [Google ADK](https://composio.dev/toolkits/forcemanager/framework/google-adk) - [LangChain](https://composio.dev/toolkits/forcemanager/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/forcemanager/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/forcemanager/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/forcemanager/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 Forcemanager - Connect LlamaIndex to the Forcemanager MCP server - Build a Forcemanager-powered agent using LlamaIndex - Interact with Forcemanager 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 Forcemanager MCP server, and what's possible with it? The Forcemanager MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Forcemanager account. It provides structured and secure access to your CRM data, so your agent can perform actions like retrieving activity details, managing companies and contacts, and organizing sales orders on your behalf. - Activity management and retrieval: Instantly fetch specific sales activities or remove outdated ones, helping you keep your team's daily records up to date. - Company and contact administration: Easily get detailed company or contact information, or delete records when they're no longer needed—all with your agent's help. - Sales order and line control: Let your agent delete sales orders or individual order lines, streamlining your sales workflow and keeping data clean. - Master data maintenance: Empower your agent to manage master-data values, ensuring your CRM stays accurate and relevant as your business evolves. - Saved view organization: Ask your agent to delete saved views you no longer use, keeping your workspace focused and clutter-free. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `FORCEMANAGER_DELETE_ACTIVITY` | Delete Activity | Delete an existing activity by ID. Tries multiple base hosts and path variants to maximize compatibility across environments and gateways. | | `FORCEMANAGER_DELETE_COMPANY` | Delete Company | Tool to delete a company by its ForceManager ID. Use when you need to remove an existing company from the system. | | `FORCEMANAGER_DELETE_CONTACT` | Delete Contact | Permanently deletes a contact from ForceManager by its unique ID. This action removes the specified contact and all associated data. The operation is irreversible. The action automatically tries multiple API endpoint combinations to ensure compatibility across different ForceManager deployments and configurations. Returns the HTTP status code and any response message from the API. A successful deletion typically returns a 200 status code. | | `FORCEMANAGER_DELETE_SALES_ORDER` | Delete Sales Order | Delete a sales order by ID using ForceManager REST API. Tries multiple base hosts and path variants to maximize compatibility across environments. Accepts successful HTTP status codes (< 300) even when the response is non-JSON, capturing response text. | | `FORCEMANAGER_DELETE_SALES_ORDER_LINE` | Delete Sales Order Line | Delete a sales order line by ID. Attempts deletion across multiple ForceManager API hosts and path variations to ensure compatibility. Returns detailed information about the deletion result, including any messages or status codes from the API. Use this when you need to remove a specific sales order line item from the system. | | `FORCEMANAGER_DELETE_VALUE` | Delete Master Data Value | Delete a master-data value (Z_ table) by ID using ForceManager REST API. Tries multiple base hosts and path variants to maximize compatibility across environments. Accepts successful HTTP status codes (< 300) even when the response is HTML instead of JSON, capturing the response text as a message. Also retries sending authentication headers as query parameters on HTTP 401 as some gateways expect them in query string. | | `FORCEMANAGER_DELETE_VIEW` | Delete View | Delete a saved view (custom filter) by its ID. Views in ForceManager are saved filter configurations that users create to quickly access filtered lists of entities (accounts, activities, opportunities, etc.). This action permanently removes a view that the authenticated user has permission to delete. **Use Cases:** - Remove outdated or unused custom filters - Clean up views after organizational changes - Programmatically manage view lifecycle **Requirements:** - Valid view ID that exists in the system - Appropriate permissions to delete the view - The view must be owned by or shared with the authenticated user **Note:** This action tries multiple ForceManager API endpoints to maximize compatibility across different deployment environments and API versions. | | `FORCEMANAGER_GET_ACTIVITY` | Get Activity | Retrieves a single activity by its ID from ForceManager CRM. Use this tool when you need to: - Fetch details of a specific activity by its ID - Check if an activity exists - Retrieve activity data including comments, dates, linked contacts/accounts, and location info The action attempts multiple ForceManager API endpoints to ensure compatibility across different API versions and deployment configurations. Returns found=False if the activity does not exist or cannot be retrieved. Authentication is handled automatically via headers from the connected account. | | `FORCEMANAGER_GET_COMPANY` | Get Company | Retrieve a single company by its ID from ForceManager. Returns company details when found, or an empty entity with found=False when the company doesn't exist or the API returns non-JSON content. The action automatically tries multiple ForceManager API endpoints for maximum compatibility. Use this to fetch company information including name, address, contact details, and custom fields. Check the 'found' field to determine if the company exists. | | `FORCEMANAGER_GET_INTERNAL_ID` | Get Internal ID | Tool to retrieve ForceManager internal IDs mapping for a given externalId and entity type. This action calls the documented endpoint /api/internalid with required authentication headers and optional pagination/version headers. It tries multiple base hosts to avoid HTML app shell responses and gracefully handles non-JSON responses and error codes by returning empty results instead of failing the execution. | | `FORCEMANAGER_GET_PRODUCT` | Get Product | Retrieve a single product by its ID from ForceManager/Sage Sales Management. This action tries multiple known ForceManager API endpoints in sequence until one succeeds. If a product is not found or the API returns non-JSON content, it returns found=False with an empty entity dict. This graceful handling allows agents to check for product existence without encountering errors. Use this when you need to fetch product details such as name, price, cost, category, or custom fields by product ID. | | `FORCEMANAGER_GET_SALES_ORDER_LINE` | Get Sales Order Line | Retrieves a single sales order line by ID from ForceManager. A sales order line represents a product item within a sales order, including quantity, pricing, and discount information. Use this when you need to fetch details about a specific line item in a sales order, such as product information, quantities, prices, or applied discounts. | | `FORCEMANAGER_GET_USER` | Get User | Retrieves a single ForceManager user by their ID, returning comprehensive user information including name, email, phone, active status, permission level, manager, branches, and more. Returns the complete user object if found, or an empty entity with found=False if the user doesn't exist, was deleted, or the API returns an error. Automatically tries multiple ForceManager API endpoints and versions to ensure compatibility. Use this when you need to: fetch user profile details, verify user existence, check user permissions/status, or retrieve user contact information. | | `FORCEMANAGER_GET_VIEW` | Get View | Tool to get a single view by ID. Returns a list with zero or one view object. | | `FORCEMANAGER_LIST_VIEWS` | List Views | Tool to list saved view filters. Use when you need to retrieve saved views for a specific entity (e.g., list views for entity 'account'). | | `FORCEMANAGER_UPDATE_ACTIVITY` | Update Activity | Tool to update an existing activity by ID. Use when you need to change fields such as comment, date/time, linked entities, or geocode. | | `FORCEMANAGER_UPDATE_COMPANY` | Update Company | Update Company | | `FORCEMANAGER_UPDATE_PRODUCT` | Update Product | Updates an existing product by ID in ForceManager. Use this tool to modify product details such as name, price, cost, description, availability status, category, family, discount limits, and custom fields. The product must already exist - this action does not create new products. At least one field besides 'id' must be provided to update. | | `FORCEMANAGER_UPDATE_SALES_ORDER` | Update Sales Order | Update Sales Order | | `FORCEMANAGER_UPDATE_SALES_ORDER_LINE` | Update Sales Order Line | Tool to update sales order line by ID. Use when modifying details of an existing sales order line. Retries with query auth on 401 for proxy-pro host. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Forcemanager MCP server is an implementation of the Model Context Protocol that connects your AI agent to Forcemanager. It provides structured and secure access so your agent can perform Forcemanager 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 Forcemanager account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and Forcemanager 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 Forcemanager 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, forcemanager) - 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 Forcemanager 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=["forcemanager"], ) 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 Forcemanager actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Forcemanager 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: ["forcemanager"], }, ); 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 Forcemanager 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 Forcemanager ```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 Forcemanager, 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=["forcemanager"], ) 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 Forcemanager actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Forcemanager 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: ["forcemanager"], }, ); 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 Forcemanager 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 Forcemanager to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes Forcemanager 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 Forcemanager MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/forcemanager/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/forcemanager/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/forcemanager/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/forcemanager/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/forcemanager/framework/codex) - [OpenClaw](https://composio.dev/toolkits/forcemanager/framework/openclaw) - [Hermes](https://composio.dev/toolkits/forcemanager/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/forcemanager/framework/cli) - [Google ADK](https://composio.dev/toolkits/forcemanager/framework/google-adk) - [LangChain](https://composio.dev/toolkits/forcemanager/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/forcemanager/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/forcemanager/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/forcemanager/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 Forcemanager MCP? With a standalone Forcemanager MCP server, the agents and LLMs can only access a fixed set of Forcemanager tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Forcemanager 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 Forcemanager tools. ### Can I manage the permissions and scopes for Forcemanager while using Tool Router? Yes, absolutely. You can configure which Forcemanager 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 Forcemanager data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)