# How to integrate Vapi MCP with LlamaIndex ```json { "title": "How to integrate Vapi MCP with LlamaIndex", "toolkit": "Vapi", "toolkit_slug": "vapi", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/vapi/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/vapi/framework/llama-index.md", "updated_at": "2026-03-29T06:54:31.728Z" } ``` ## Introduction This guide walks you through connecting Vapi to LlamaIndex using the Composio tool router. By the end, you'll have a working Vapi agent that can start a new outbound call campaign, get transcript from the last agent call, pause all ongoing voice agent sessions through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a Vapi account through Composio's Vapi MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Vapi with - [OpenAI Agents SDK](https://composio.dev/toolkits/vapi/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/vapi/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/vapi/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/vapi/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/vapi/framework/codex) - [OpenClaw](https://composio.dev/toolkits/vapi/framework/openclaw) - [Hermes](https://composio.dev/toolkits/vapi/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/vapi/framework/cli) - [Google ADK](https://composio.dev/toolkits/vapi/framework/google-adk) - [LangChain](https://composio.dev/toolkits/vapi/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/vapi/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/vapi/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/vapi/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 Vapi - Connect LlamaIndex to the Vapi MCP server - Build a Vapi-powered agent using LlamaIndex - Interact with Vapi 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 Vapi MCP server, and what's possible with it? The Vapi MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Vapi account. It provides structured and secure access so your agent can perform Vapi operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `VAPI_ASSISTANT_CONTROLLER_UPDATE` | Update Assistant | Tool to update an existing Vapi assistant configuration. Use when you need to modify assistant properties such as name, voice settings, transcriber configuration, model settings, messages, or other behavior parameters. Only include fields you want to update. | | `VAPI_CALL_CONTROLLER_FIND_ALL` | List Calls | Tool to list calls from Vapi. Use when you need to retrieve multiple calls with optional filtering by id, assistantId, phoneNumberId, or date ranges. Returns an array of call objects with details including status, costs, messages, and artifacts. | | `VAPI_CHAT_CONTROLLER_DELETE_CHAT` | Delete Chat | Tool to delete a chat by its ID from Vapi. Use when you need to permanently remove a chat conversation. | | `VAPI_CHAT_CONTROLLER_GET_CHAT` | Get Chat | Tool to fetch chat details by ID. Use when you have a chat ID and need full chat information including messages, costs, and configuration. | | `VAPI_CREATE_ANALYTICS_QUERIES` | Create Analytics Queries | Tool to create and execute analytics queries on VAPI data. Use when you need to analyze call or subscription metrics with aggregations like count, sum, average, min, or max. Supports grouping by various dimensions and time-based analysis with custom time ranges. | | `VAPI_CREATE_ASSISTANT` | Create Assistant | Tool to create a new Vapi assistant with specified transcriber, voice, and AI model configurations. Use when setting up a conversational AI assistant for voice interactions. The assistant requires transcription (speech-to-text), voice (text-to-speech), and AI model (conversation logic) configurations at minimum. | | `VAPI_CREATE_EVAL` | Create Eval | Tool to create an eval for testing conversation flows. Use when you need to validate that an AI assistant responds correctly to specific conversation scenarios. | | `VAPI_CREATE_OPENAI_CHAT` | Create OpenAI Chat | Tool to create an OpenAI-compatible chat using the Vapi API. Use when you need to send a chat message to an assistant or squad and receive a response. Supports both streaming and non-streaming modes. | | `VAPI_CREATE_PHONE_NUMBER` | Create Phone Number | Tool to create a phone number with Vapi. Supports multiple providers including byo-phone-number, twilio, vonage, vapi, and telnyx. Use this to provision new phone numbers for handling voice calls. For vapi provider, only provider field is required; other fields are optional based on provider type. | | `VAPI_CREATE_MONITORING_POLICY` | Create Monitoring Policy | Tool to create a monitoring policy in VAPI. Use when you need to set up automated monitoring rules based on thresholds and time windows. Policies can trigger alerts based on event counts or percentages over a specified lookback window. | | `VAPI_CREATE_PROVIDER_RESOURCE` | Create Provider Resource | Tool to create an 11Labs pronunciation dictionary resource. Use when you need to define custom pronunciations for specific terms or acronyms in voice synthesis. | | `VAPI_CREATE_SCORECARD` | Create Scorecard | Tool to create a scorecard for observability and evaluation. Use when setting up metrics to evaluate assistant performance based on structured outputs. Scorecards contain metrics with conditions that calculate normalized scores on a 100-point scale. | | `VAPI_DELETE_CALL` | Delete Call | Tool to delete a call by its unique identifier. Use when you need to remove call data from the system. Returns the deleted call object with all its associated data. | | `VAPI_DELETE_EVAL` | Delete Eval | Tool to delete an eval by ID. Use when you need to permanently remove an eval from the system. | | `VAPI_DELETE_PHONE_NUMBER` | Delete Phone Number | Tool to delete a phone number from Vapi. Use when you need to remove a phone number from your Vapi organization. Returns the deleted phone number object. | | `VAPI_GET_EVAL` | Get Eval | Tool to retrieve an eval by its ID. Use when you need to fetch details about a specific eval including its mock conversation messages and metadata. | | `VAPI_DELETE_EVAL_RUN` | Delete Eval Run | Tool to delete an eval run by its ID from Vapi. Use when you need to permanently remove an evaluation run. | | `VAPI_UPDATE_EVAL` | Update Eval | Tool to update an existing eval in Vapi. Use when you need to modify eval properties like name, description, type, or mock conversation messages. | | `VAPI_GET_ASSISTANT` | Get Assistant | Tool to retrieve a specific assistant by ID from Vapi. Use when you need to fetch details about an existing assistant. | | `VAPI_GET_CALL` | Get Call | Tool to fetch call details by ID. Use when you have a call ID and need full call information including status, duration, costs, messages, and recordings. | | `VAPI_GET_FILE` | Get File | Tool to retrieve a file by its ID from Vapi. Use when you need to get details about a specific file including its status, metadata, storage location, and timestamps. | | `VAPI_GET_INSIGHTS` | Get Insights | Tool to retrieve insights from Vapi. Use when you need to fetch insight data with optional filtering by ID, timestamps, or pagination. Returns a paginated list of insights with metadata. | | `VAPI_LIST_MONITORING_POLICIES` | List Monitoring Policies | Tool to retrieve monitoring policies from Vapi. Use when you need to list, filter, or search for monitoring policies configured in the organization. Supports filtering by policy ID, severity level, monitor ID, and date ranges for creation/update timestamps. | | `VAPI_GET_OBSERVABILITY_SCORECARD` | Get Observability Scorecard | Tool to list observability scorecards with optional filtering and pagination. Use when you need to retrieve scorecards for monitoring or analysis. | | `VAPI_LIST_PROVIDER_RESOURCES` | List Provider Resources | Tool to list provider resources from Vapi. Use when you need to retrieve pronunciation dictionaries or other resources from providers like 11labs or Cartesia. | | `VAPI_LIST_STRUCTURED_OUTPUTS` | List Structured Outputs | Tool to list structured outputs with optional filtering. Use when you need to retrieve structured output configurations with pagination support. Supports filtering by ID, name, timestamps, and includes pagination controls. | | `VAPI_GET_INSIGHTS` | Get Insights | Tool to retrieve insights from VAPI. Use when you need to list insights with optional filtering by ID, creation date, or update date. Supports pagination and sorting. | | `VAPI_LIST_ASSISTANTS` | List Assistants | Tool to list all assistants in your VAPI organization. Use when you need to retrieve information about configured assistants. Supports filtering by creation and update timestamps. | | `VAPI_LIST_CHATS` | List Chats | Tool to retrieve a list of chat conversations from VAPI. Use when you need to view existing chats, optionally filtered by assistant, squad, session, or time range. Supports pagination and sorting for efficient retrieval of large chat histories. | | `VAPI_LIST_EVALS` | List Evals | Tool to retrieve a paginated list of evals from Vapi. Use when you need to list or search evals with optional filtering by creation/update timestamps. | | `VAPI_LIST_PROVIDER_RESOURCES` | List Provider Resources | Tool to retrieve provider resources from Vapi (e.g., 11labs pronunciation dictionaries). Use when you need to list or search provider-specific resources with optional filtering by timestamps. | | `VAPI_UPDATE_INSIGHT` | Update Insight | Tool to update an existing insight configuration in VAPI. Use when you need to modify insight properties like name, queries, time range, or visualization settings. Supports all four insight types (bar, pie, line, text) with type-specific configurations. | | `VAPI_CREATE_PHONE_NUMBER` | Create Phone Number | Tool to create a phone number with VAPI. Use when you need to provision a new phone number for voice AI applications. Supports multiple providers (VAPI, Twilio, Vonage, Telnyx, BYO). Required parameters vary by provider. | | `VAPI_LIST_SCORECARDS` | List Scorecards | Tool to retrieve a paginated list of scorecards from Vapi. Use when you need to list or search scorecards with optional filtering by creation/update timestamps. | | `VAPI_CREATE_SESSION` | Create Session | Tool to create a new session in Vapi. Use when you need to establish a persistent conversation context that can span multiple chats. Sessions automatically expire after 24 hours. | | `VAPI_LIST_SESSIONS` | List Sessions | Tool to retrieve a paginated list of sessions from VAPI. Use when you need to list sessions with optional filtering by session ID, name, assistant, squad, or workflow. Supports pagination, sorting, and timestamp-based filtering. | | `VAPI_LIST_STRUCTURED_OUTPUTS` | List Structured Outputs | Tool to list structured outputs with optional filtering and pagination. Use when you need to retrieve structured output configurations from Vapi. | | `VAPI_GET_TOOL` | Get Tool | Tool to fetch tool details by ID. Use when you have a tool ID and need full tool configuration including type, messages, function definitions, and server settings. | | `VAPI_TEST_CODE_TOOL_EXECUTION` | Test Code Tool Execution | Tool to test TypeScript code execution in Vapi's code tool environment. Use when validating code before deploying it as a tool. | | `VAPI_UPDATE_TOOL` | Update Tool | Tool to update an existing Vapi tool configuration. Use when you need to modify tool properties such as function definitions, server settings, messages, or other tool-specific parameters. | | `VAPI_UPDATE_PHONE_NUMBER` | Update Phone Number | Tool to update an existing phone number configuration in VAPI. Use when you need to modify phone number settings such as name, associated assistant/workflow, or provider-specific configurations. | | `VAPI_UPLOAD_FILE` | Upload File | Tool to upload a file to Vapi Knowledge Base. Use when you need to add files for AI assistants to reference. Returns file metadata including ID, storage URLs, and processing status. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Vapi MCP server is an implementation of the Model Context Protocol that connects your AI agent to Vapi. It provides structured and secure access so your agent can perform Vapi 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 Vapi account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and Vapi 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 Vapi 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, vapi) - 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 Vapi 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=["vapi"], ) 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 Vapi actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Vapi 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: ["vapi"], }, ); 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 Vapi 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 Vapi ```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 Vapi, 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=["vapi"], ) 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 Vapi actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Vapi 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: ["vapi"], }, ); 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 Vapi 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 Vapi to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes Vapi 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 Vapi MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/vapi/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/vapi/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/vapi/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/vapi/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/vapi/framework/codex) - [OpenClaw](https://composio.dev/toolkits/vapi/framework/openclaw) - [Hermes](https://composio.dev/toolkits/vapi/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/vapi/framework/cli) - [Google ADK](https://composio.dev/toolkits/vapi/framework/google-adk) - [LangChain](https://composio.dev/toolkits/vapi/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/vapi/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/vapi/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/vapi/framework/crew-ai) ## Related Toolkits - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service. - [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows. - [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow. - [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows. - [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application. - [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities. - [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization. - [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications. - [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations. - [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key. - [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient. - [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions. - [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences. - [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement. - [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team. - [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs. - [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code. - [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets. - [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Vapi MCP? With a standalone Vapi MCP server, the agents and LLMs can only access a fixed set of Vapi tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Vapi 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 Vapi tools. ### Can I manage the permissions and scopes for Vapi while using Tool Router? Yes, absolutely. You can configure which Vapi 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 Vapi data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)