# How to integrate Webex MCP with LlamaIndex ```json { "title": "How to integrate Webex MCP with LlamaIndex", "toolkit": "Webex", "toolkit_slug": "webex", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/webex/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/webex/framework/llama-index.md", "updated_at": "2026-05-12T10:30:09.836Z" } ``` ## Introduction This guide walks you through connecting Webex to LlamaIndex using the Composio tool router. By the end, you'll have a working Webex agent that can create a new project discussion room, list all teams i am part of, send a meeting summary to your team through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a Webex account through Composio's Webex MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Webex with - [ChatGPT](https://composio.dev/toolkits/webex/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/webex/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/webex/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/webex/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/webex/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/webex/framework/codex) - [Cursor](https://composio.dev/toolkits/webex/framework/cursor) - [VS Code](https://composio.dev/toolkits/webex/framework/vscode) - [OpenCode](https://composio.dev/toolkits/webex/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/webex/framework/openclaw) - [Hermes](https://composio.dev/toolkits/webex/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/webex/framework/cli) - [Google ADK](https://composio.dev/toolkits/webex/framework/google-adk) - [LangChain](https://composio.dev/toolkits/webex/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/webex/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/webex/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/webex/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 Webex - Connect LlamaIndex to the Webex MCP server - Build a Webex-powered agent using LlamaIndex - Interact with Webex 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 Webex MCP server, and what's possible with it? The Webex MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Webex account. It provides structured and secure access to your meetings, teams, rooms, and messaging, so your agent can perform actions like managing teams, creating rooms, posting messages, and handling memberships on your behalf. - Automated team and room management: Quickly create new teams or rooms, group conversations by topic, and keep collaboration spaces organized through your agent. - Seamless messaging and announcements: Direct your agent to post messages, send important files, or share updates with individuals or entire rooms instantly. - Membership and access control: Effortlessly add or remove members from teams and spaces, ensuring the right people have access at the right time. - Webhook and event integrations: List and manage Webex webhooks so your agent can react to events or changes as they happen in your workspace. - Content and message cleanup: Ask your agent to delete outdated or mistaken messages and memberships, keeping your workspace tidy and relevant. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `WEBEX_CREATE_TEAM` | Create Team | Creates a new Webex team and automatically adds the authenticated user as a member. Teams are used to organize and group multiple rooms (spaces) under a common umbrella. Use this when you need to create a collaborative workspace for a project, department, or any group that needs multiple related discussion spaces. Note: The creator is automatically added as a team member and can manage team memberships. Use the Team Memberships API to add additional members after creation. | | `WEBEX_GET_TEAM_DETAILS` | Get Team Details | Tool to retrieve details for a specific team by teamId. Use when you need full metadata of a team before performing team-related operations. | | `WEBEX_LIST_TEAMS` | List Teams | Lists all teams the authenticated user belongs to. Teams are groups of people with shared rooms visible to all members. Use this when you need to find available teams, get team IDs for other operations, or discover which teams a user has access to. Results are ordered by creation date (newest first) and can be paginated using the max parameter. | | `WEBEX_LIST_WEBHOOKS` | List Webhooks | Lists all webhooks registered for the authenticated user or organization. Supports optional filtering by maximum results and ownership type (creator vs org-wide). | | `WEBEX_MESSAGING_CREATE_MESSAGE` | Create Message | Tool to post a message to a Webex room or person. Use when you have a target roomId or private recipient and want to send text, markdown, files, or card attachments. | | `WEBEX_CREATE_ROOM` | Create Room | Creates a new Webex room for team collaboration. The authenticated user is automatically added as a member. Use this to create group rooms for team discussions or associate rooms with existing teams. To create a 1:1 room, use the Create Message action with toPersonId/toPersonEmail instead. Note: Team rooms cannot be moved after creation. Bots cannot simultaneously create and classify rooms. | | `WEBEX_MESSAGING_CREATE_TEAM_MEMBERSHIP` | Create Team Membership | Tool to add a person to a Webex team by personId or personEmail. Use when granting a user access to a team; requires teamId and one of personId or personEmail. | | `WEBEX_MESSAGING_DELETE_MEMBERSHIP` | Delete Membership | Tool to delete a Webex membership by its unique identifier. Use when you need to remove a member from a space after confirming the membership exists. Example: "Delete the membership with ID Y2lzY29zcGFjMDczNzA2Njg0ZDliY2YxNDE4NDQyYzQ5NDQzOTExYTk4". | | `WEBEX_MESSAGING_DELETE_MESSAGE` | Delete Message | Tool to delete a Webex message by its unique identifier. Use after confirming the messageId to remove unintended or obsolete messages. Example: "Delete the message with ID Y2lzY29zcGFyazovL21lc3NhZ2UvYWJjMTIzNDU2Nzg5". | | `WEBEX_MESSAGING_DELETE_ROOM` | Delete Room | Deletes a Webex room by its ID. Deleted rooms cannot be recovered. Note: Non-moderators will be removed from the room instead of deleting it (as a safety measure). Rooms that are part of a team will be archived instead of deleted. Use this when you need to permanently remove a room or leave a room. | | `WEBEX_MESSAGING_GET_MEMBERSHIP_DETAILS` | Get Membership Details | Tool to retrieve details for a specific membership. Use when you need metadata for a membership by its ID. | | `WEBEX_MESSAGING_GET_MESSAGE_DETAILS` | Get Message Details | Tool to retrieve details for a specific message. Use when you need full content and metadata by message ID. | | `WEBEX_MESSAGING_GET_TEAM_MEMBERSHIP_DETAILS` | Get Team Membership Details | Tool to retrieve details for a specific team membership. Use when you need metadata for a team membership by its ID. | | `WEBEX_MESSAGING_LIST_MEMBERSHIPS` | List Memberships | List memberships in Webex rooms. When called without parameters, returns memberships for all rooms the authenticated user belongs to. Use roomId to list all members of a specific room. Use personId or personEmail with roomId to check if a specific person is a member of a room. Supports filtering by teamId and limiting results with max parameter. | | `WEBEX_MESSAGING_LIST_MESSAGES` | List Messages | Tool to list messages in a room. Use when you need to retrieve chat history filtered by room, time window, or mentions. | | `WEBEX_MESSAGING_LIST_ROOMS` | List Rooms | Tool to list rooms the authenticated user belongs to. Use after authentication when needing to retrieve spaces filtered by team, type, or sorted. Example: "List my group rooms sorted by last activity." | | `WEBEX_MESSAGING_LIST_TEAM_MEMBERSHIPS` | List Team Memberships | Tool to list all memberships for a specific team. Use when you need to retrieve all members of a team, including their roles (moderator status). Requires a valid teamId. | | `WEBEX_PEOPLE_GET_PERSON` | Get Person Details | Retrieves detailed profile information for a specific person by their ID. Returns comprehensive user details including contact information, organizational data, presence status, and Webex Calling information. Use when you need full profile details for a known person ID. To find person IDs, use the List People action first. | | `WEBEX_PEOPLE_LIST_PEOPLE` | List People | Tool to list people in your organization. Use when you need to retrieve people filtered by email, display name, IDs, roles, or location. | | `WEBEX_ROOMS_GET_ROOM_DETAILS` | Get Room Details | Tool to retrieve details for a specific room. Use when you need full metadata of a room before posting messages or updating settings. | | `WEBEX_UPDATE_MEMBERSHIP` | Update Membership | Updates a Webex room membership by ID to change moderator or monitor status. Use this to grant or revoke moderator privileges, or to enable/disable room monitoring for a member. Note: Assigning moderator status requires special account permissions; operations may fail with 403 Forbidden if the authenticated user lacks the necessary entitlements. | | `WEBEX_UPDATE_ROOM` | Update Room | Update a room's title, lock status, or team association. The title parameter is always required by the Webex API - if you're only updating isLocked or teamId, you must still provide the current room title. | | `WEBEX_UPDATE_TEAM` | Update Team | Tool to update a team's name by teamId. Use when you need to rename a Webex team. Example: "Change team 12345 name to 'Project X Team'". | | `WEBEX_WEBHOOKS_CREATE_WEBHOOK` | Create Webhook | Creates a Webex webhook to receive real-time event notifications via HTTP POST requests to your specified URL. Use this tool to register for automated notifications when resources (messages, rooms, memberships, meetings, etc.) are created, updated, deleted, or undergo other state changes. Webhooks enable event-driven integrations without polling. Important: The webhook will be automatically disabled if your target URL fails to respond with HTTP 2xx status codes 100 times within five minutes. Requires 'read' scope for the monitored resource type. | | `WEBEX_WEBHOOKS_DELETE_WEBHOOK` | Delete Webhook | Tool to delete a specific webhook. Use when you need to remove an existing webhook by its ID after confirming the identifier. | | `WEBEX_WEBHOOKS_GET_WEBHOOK` | Get Webhook Details | Retrieves detailed information about a specific Webex webhook by its ID. Use this action to: - Inspect a webhook's configuration (target URL, resource, event type, filters) - Verify webhook status (active/inactive) - Check webhook ownership and security settings (secret, ownedBy) - Get webhook metadata (creation date, creator, organization) The webhook must exist and be accessible with your current credentials. Returns 404 error if the webhook ID is invalid or you don't have permission to view it. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Webex MCP server is an implementation of the Model Context Protocol that connects your AI agent to Webex. It provides structured and secure access so your agent can perform Webex 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 Webex account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and Webex 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 Webex 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, webex) - 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 Webex 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=["webex"], ) 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 Webex actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Webex 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: ["webex"], }, ); 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 Webex 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 Webex ```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 Webex, 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=["webex"], ) 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 Webex actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Webex 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: ["webex"], }, ); 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 Webex 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 Webex to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes Webex 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 Webex MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/webex/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/webex/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/webex/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/webex/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/webex/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/webex/framework/codex) - [Cursor](https://composio.dev/toolkits/webex/framework/cursor) - [VS Code](https://composio.dev/toolkits/webex/framework/vscode) - [OpenCode](https://composio.dev/toolkits/webex/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/webex/framework/openclaw) - [Hermes](https://composio.dev/toolkits/webex/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/webex/framework/cli) - [Google ADK](https://composio.dev/toolkits/webex/framework/google-adk) - [LangChain](https://composio.dev/toolkits/webex/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/webex/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/webex/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/webex/framework/crew-ai) ## Related Toolkits - [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable. - [Outlook](https://composio.dev/toolkits/outlook) - Outlook is Microsoft's email and calendaring platform for unified communications and scheduling. It helps users stay organized with powerful email, contacts, and calendar management. - [Slack](https://composio.dev/toolkits/slack) - Slack is a channel-based messaging platform for teams and organizations. It helps people collaborate in real time, share files, and connect all their tools in one place. - [Gong](https://composio.dev/toolkits/gong) - Gong is a platform for video meetings, call recording, and team collaboration. It helps teams capture conversations, analyze calls, and turn insights into action. - [Microsoft teams](https://composio.dev/toolkits/microsoft_teams) - Microsoft Teams is a collaboration platform that combines chat, meetings, and file sharing within Microsoft 365. It keeps distributed teams connected and productive through seamless virtual communication. - [Slackbot](https://composio.dev/toolkits/slackbot) - Slackbot is a conversational automation tool for Slack that handles reminders, notifications, and automated responses. It boosts team productivity by streamlining onboarding, answering FAQs, and managing timely alerts—all right inside Slack. - [2chat](https://composio.dev/toolkits/_2chat) - 2chat is an API platform for WhatsApp and multichannel text messaging. It streamlines chat automation, group management, and real-time messaging for developers. - [Agent mail](https://composio.dev/toolkits/agent_mail) - Agent mail provides AI agents with dedicated email inboxes for sending, receiving, and managing emails. It empowers agents to communicate autonomously with people, services, and other agents—no human intervention needed. - [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place. - [Chatwork](https://composio.dev/toolkits/chatwork) - Chatwork is a team communication platform with group chats, file sharing, and task management. It helps businesses boost collaboration and streamline productivity. - [Clickmeeting](https://composio.dev/toolkits/clickmeeting) - ClickMeeting is a cloud-based platform for running online meetings and webinars. It helps businesses and individuals host, manage, and engage virtual audiences with ease. - [Confluence](https://composio.dev/toolkits/confluence) - Confluence is Atlassian's team collaboration and knowledge management platform. It helps your team organize, share, and update documents and project content in one secure workspace. - [Dailybot](https://composio.dev/toolkits/dailybot) - DailyBot streamlines team collaboration with chat-based standups, reminders, and polls. It keeps work flowing smoothly in your favorite messaging platforms. - [Dialmycalls](https://composio.dev/toolkits/dialmycalls) - Dialmycalls is a mass notification service for sending voice and text messages to contacts. It helps teams and organizations quickly broadcast urgent alerts and updates. - [Dialpad](https://composio.dev/toolkits/dialpad) - Dialpad is a cloud-based business phone and contact center system for teams. It unifies voice, video, messaging, and meetings across your devices. - [Discord](https://composio.dev/toolkits/discord) - Discord is a real-time messaging and VoIP platform for communities and teams. It lets users chat, share media, and collaborate across public and private channels. - [Discordbot](https://composio.dev/toolkits/discordbot) - Discordbot is an automation tool for Discord servers that handles moderation, messaging, and user engagement. It helps communities run smoothly by automating routine and complex tasks. - [Echtpost](https://composio.dev/toolkits/echtpost) - Echtpost is a secure digital communication platform for encrypted document and message exchange. It ensures confidential data stays private and protected during transmission. - [Egnyte](https://composio.dev/toolkits/egnyte) - Egnyte is a cloud-based platform for secure file sharing, storage, and governance. It helps teams collaborate efficiently while maintaining data compliance and security. - [Google Meet](https://composio.dev/toolkits/googlemeet) - Google Meet is a secure video conferencing platform for virtual meetings, chat, and screen sharing. It helps teams connect, collaborate, and communicate seamlessly from anywhere. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Webex MCP? With a standalone Webex MCP server, the agents and LLMs can only access a fixed set of Webex tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Webex 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 Webex tools. ### Can I manage the permissions and scopes for Webex while using Tool Router? Yes, absolutely. You can configure which Webex 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 Webex data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)