# How to integrate CrowTerminal MCP with LlamaIndex ```json { "title": "How to integrate CrowTerminal MCP with LlamaIndex", "toolkit": "CrowTerminal", "toolkit_slug": "crowterminal", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/crowterminal/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/crowterminal/framework/llama-index.md", "updated_at": "2026-06-18T09:22:23.948Z" } ``` ## Introduction This guide walks you through connecting CrowTerminal to LlamaIndex using the Composio tool router. By the end, you'll have a working CrowTerminal agent that can debug failing docker build command, automate repeated git cleanup commands, recall yesterday's terminal troubleshooting notes through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a CrowTerminal account through Composio's CrowTerminal MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate CrowTerminal with - [OpenAI Agents SDK](https://composio.dev/toolkits/crowterminal/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/crowterminal/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/crowterminal/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/crowterminal/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/crowterminal/framework/codex) - [OpenClaw](https://composio.dev/toolkits/crowterminal/framework/openclaw) - [Hermes](https://composio.dev/toolkits/crowterminal/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/crowterminal/framework/cli) - [Google ADK](https://composio.dev/toolkits/crowterminal/framework/google-adk) - [LangChain](https://composio.dev/toolkits/crowterminal/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/crowterminal/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/crowterminal/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/crowterminal/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 CrowTerminal - Connect LlamaIndex to the CrowTerminal MCP server - Build a CrowTerminal-powered agent using LlamaIndex - Interact with CrowTerminal 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 CrowTerminal MCP server, and what's possible with it? The CrowTerminal MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your CrowTerminal account. It provides structured and secure access so your agent can perform CrowTerminal operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `CROWTERMINAL_ANALYZE_ENGAGEMENT` | Analyze Agent Engagement | Tool to analyze engagement correlation for every field in your agent's markdown. Use when you need to understand which agent configuration fields drive engagement and get specific recommendations for improvement. Returns similarity to best/worst performing versions and field-by-field analysis. | | `CROWTERMINAL_COMPARE_MD` | Compare Agent Markdown | Tool to compare your agent's markdown directly with all stored versions. Returns field differences showing which values differ across versions, lists missing fields not present in your current data, and provides version counts. Use when you need to understand how your current agent configuration compares to historical versions. | | `CROWTERMINAL_CREATE_WEBHOOK` | Create Webhook | Tool to register a new webhook for receiving real-time event notifications from CrowTerminal. Use when you need to set up asynchronous notifications for events like skill updates, data ingestion, or validation blocks. | | `CROWTERMINAL_DELETE_WEBHOOK` | Delete Webhook | Tool to delete an existing webhook registration. Use when you need to remove a webhook that is no longer needed or should be replaced. | | `CROWTERMINAL_GET_BYOK_PLATFORM_INTEL` | Get BYOK Platform Intelligence | Tool to get algorithm insights for TikTok, Instagram, and YouTube without client-specific context. Use when you need platform intelligence data for BYOK (Bring Your Own Key) analysis workflows. This endpoint provides raw contextual algorithm data without triggering LLM inference charges. | | `CROWTERMINAL_GET_CLIENT_MEMORY_CHANGELOG` | Get Client Memory Changelog | Retrieve human-readable change history for a client's memory. Provides a narrative view of how the client's skill data has evolved over time. | | `CROWTERMINAL_GET_CLIENT_MEMORY_PATTERN` | Get Client Memory Pattern | Tool to track a specific field over time for trend analysis. Use when you need to understand how a particular metric evolved across versions or time periods. | | `CROWTERMINAL_GET_COMPONENTS_STATUS` | Get Components Status | Tool to get detailed status of each CrowTerminal service component. Returns current health status, latency, and summary statistics for all monitored components (database, cache, APIs, webhooks). Use when checking system health or diagnosing service issues. | | `CROWTERMINAL_GET_DATA_TYPES` | Get Data Types | Tool to retrieve valid data types for ingestion across platforms. Returns available data types for TikTok, Instagram, and YouTube that can be used for data ingestion operations. | | `CROWTERMINAL_GET_INCIDENTS` | Get Recent Incidents | Tool to retrieve list of recent incidents from CrowTerminal with duration and affected components. Use when you need to check system status, monitor service health, or investigate recent outages or degradations. | | `CROWTERMINAL_GET_PLATFORM_INTEL` | Get Platform Intelligence | Tool to retrieve algorithm insights for TikTok, Instagram, and YouTube. Returns platform-wide intelligence about content algorithm behavior and optimization strategies. Use when you need current platform algorithm trends and recommendations. | | `CROWTERMINAL_GET_SANDBOX_CLIENT` | Get Sandbox Client | Tool to get mock client data for testing in the sandbox environment. Use when you need to test client-related functionality without affecting real data. No authentication required for sandbox endpoints. | | `CROWTERMINAL_GET_SANDBOX_MEMORY` | Get Sandbox Memory | Tool to retrieve mock memory/skill data for testing purposes. Use when you need to test memory retrieval without affecting real data or requiring authentication. Part of the sandbox testing environment. | | `CROWTERMINAL_GET_STATUS` | Get Service Status | Retrieve CrowTerminal service status including overall health, component metrics, and uptime data. Use when you need to check the operational status of CrowTerminal services or monitor system health. No authentication required. | | `CROWTERMINAL_GET_STATUS_HISTORY` | Get Status History | Tool to get 7-day uptime data points ready for visualization and charting. Use when you need historical uptime metrics for monitoring dashboards or status displays. | | `CROWTERMINAL_GET_UPTIME` | Get Uptime Data | Tool to retrieve historical uptime data for CrowTerminal agents. Use when you need to check system reliability, view uptime percentages for 24h/7d periods, or review recent service incidents. | | `CROWTERMINAL_INGEST_BULK_DATA` | Bulk Ingest Analytics Data | Tool to bulk ingest up to 50 analytics data points at once to CrowTerminal. Use when you need to efficiently push large amounts of platform analytics data for content creators across social media platforms. Ideal for batch uploads of retention, engagement, views, and other metrics. | | `CROWTERMINAL_INGEST_DATA` | Ingest Analytics Data | Tool to ingest platform analytics data from TikTok Studio, Instagram Insights, or YouTube Analytics. Use when you need to push retention curves, demographics, traffic sources, or other engagement metrics for analysis. Supports both video-specific and channel-level data ingestion. | | `CROWTERMINAL_LIST_WEBHOOKS` | List Webhooks | Tool to list all registered webhooks for the authenticated agent. Use when you need to view all webhook subscriptions and their configurations. | | `CROWTERMINAL_PING_CROWTERMINAL` | Ping CrowTerminal Service | Tool to check CrowTerminal service availability via a simple ping endpoint. Use when you need to verify the service is online and responding. Returns a pong confirmation with a timestamp. | | `CROWTERMINAL_READ_BULK_MEMORY` | Bulk Read Memory | Tool to read memory for multiple clients at once (up to 50). Use when you need to efficiently retrieve memory data for multiple creators in a single API call. | | `CROWTERMINAL_REGISTER_AGENT` | Register Agent | Tool to self-register a new agent and obtain an API key. Use when you need to create a new agent identity in CrowTerminal. No authentication required for this endpoint. Rate limited to 5 requests per hour per IP address. | | `CROWTERMINAL_RUN_SANDBOX_ENGAGEMENT_ANALYSIS` | Sandbox Engagement Analysis | Tool to run mock engagement analysis in the CrowTerminal sandbox environment. Use when you need to test the engagement analysis workflow without affecting real data or when developing and validating agent configurations. | | `CROWTERMINAL_TEST_WEBHOOK` | Test Webhook | Tool to test a webhook URL by sending a test payload. Use when you need to verify that a webhook endpoint is properly configured and can receive requests. | | `CROWTERMINAL_UPDATE_WEBHOOK` | Update Webhook | Tool to update an existing webhook configuration in CrowTerminal. Use when you need to modify webhook URL, change event subscriptions, or enable/disable a webhook. | | `CROWTERMINAL_VALIDATE_PROPOSED_CHANGES` | Validate Proposed Changes | Tool to validate proposed changes against historical data before updating memory. Use when you need to check if proposed changes contradict historical patterns and receive warnings or recommendations. | | `CROWTERMINAL_VALIDATE_SANDBOX` | Validate Sandbox | Tool to mock validation endpoint for testing in sandbox. Use when you need to test validation logic. Send 'tutorial' in proposedChanges to get a blocked response. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The CrowTerminal MCP server is an implementation of the Model Context Protocol that connects your AI agent to CrowTerminal. It provides structured and secure access so your agent can perform CrowTerminal 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 CrowTerminal account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and CrowTerminal 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 CrowTerminal 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, crowterminal) - 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 CrowTerminal 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=["crowterminal"], ) 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 CrowTerminal actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform CrowTerminal 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: ["crowterminal"], }, ); 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 CrowTerminal 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 CrowTerminal ```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 CrowTerminal, 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=["crowterminal"], ) 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 CrowTerminal actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform CrowTerminal 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: ["crowterminal"], }, ); 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 CrowTerminal 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 CrowTerminal to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes CrowTerminal 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 CrowTerminal MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/crowterminal/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/crowterminal/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/crowterminal/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/crowterminal/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/crowterminal/framework/codex) - [OpenClaw](https://composio.dev/toolkits/crowterminal/framework/openclaw) - [Hermes](https://composio.dev/toolkits/crowterminal/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/crowterminal/framework/cli) - [Google ADK](https://composio.dev/toolkits/crowterminal/framework/google-adk) - [LangChain](https://composio.dev/toolkits/crowterminal/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/crowterminal/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/crowterminal/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/crowterminal/framework/crew-ai) ## Related Toolkits - [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure. - [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms. - [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place. - [1password](https://composio.dev/toolkits/_1password) - 1Password is a password manager and digital vault for storing logins, secrets, notes, and secure documents. It helps individuals and teams protect credentials, share access safely, and reduce password risk. - [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences. - [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses. - [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure. - [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure. - [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction. - [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting. - [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache. - [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence. - [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place. - [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines. - [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure. - [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code. - [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows. - [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights. - [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews. - [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and CrowTerminal MCP? With a standalone CrowTerminal MCP server, the agents and LLMs can only access a fixed set of CrowTerminal tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from CrowTerminal 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 CrowTerminal tools. ### Can I manage the permissions and scopes for CrowTerminal while using Tool Router? Yes, absolutely. You can configure which CrowTerminal 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 CrowTerminal data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) ยท [Composio docs](https://docs.composio.dev/llms.txt)