# How to integrate Stormboard MCP with LangChain ```json { "title": "How to integrate Stormboard MCP with LangChain", "toolkit": "Stormboard", "toolkit_slug": "stormboard", "framework": "LangChain", "framework_slug": "langchain", "url": "https://composio.dev/toolkits/stormboard/framework/langchain", "markdown_url": "https://composio.dev/toolkits/stormboard/framework/langchain.md", "updated_at": "2026-03-29T06:51:47.900Z" } ``` ## Introduction This guide walks you through connecting Stormboard to LangChain using the Composio tool router. By the end, you'll have a working Stormboard agent that can summarize all sticky notes on a board, add action items to a stormboard project, list team members assigned to a board through natural language commands. This guide will help you understand how to give your LangChain agent real control over a Stormboard account through Composio's Stormboard MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Stormboard with - [OpenAI Agents SDK](https://composio.dev/toolkits/stormboard/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/stormboard/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/stormboard/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/stormboard/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/stormboard/framework/codex) - [OpenClaw](https://composio.dev/toolkits/stormboard/framework/openclaw) - [Hermes](https://composio.dev/toolkits/stormboard/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/stormboard/framework/cli) - [Google ADK](https://composio.dev/toolkits/stormboard/framework/google-adk) - [Vercel AI SDK](https://composio.dev/toolkits/stormboard/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/stormboard/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/stormboard/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/stormboard/framework/crew-ai) ## TL;DR Here's what you'll learn: - Get and set up your OpenAI and Composio API keys - Connect your Stormboard project to Composio - Create a Tool Router MCP session for Stormboard - Initialize an MCP client and retrieve Stormboard tools - Build a LangChain agent that can interact with Stormboard - Set up an interactive chat interface for testing ## What is LangChain? LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context. Key features include: - Agent Framework: Build agents that can use tools and make decisions - MCP Integration: Connect to external services through Model Context Protocol adapters - Memory Management: Maintain conversation history across interactions - Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers ## What is the Stormboard MCP server, and what's possible with it? The Stormboard MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Stormboard account. It provides structured and secure access so your agent can perform Stormboard operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `STORMBOARD_ACCEPT_A_STORM_INVITE` | Accept a Storm Invite | Tool to accept a Storm invitation and join the Storm. Use when a user wants to accept an invitation to join a Storm. | | `STORMBOARD_ADD_A_FAVORITE_STAR` | Add a Favorite Star | Tool to add a favorite star to a Storm on the Dashboard. Use when you need to mark a Storm as a favorite. | | `STORMBOARD_CHECK_AUTHENTICATION` | Check Authentication | Tool to verify API key authentication validity. Use when you need to test if the API credentials are valid and properly configured. | | `STORMBOARD_CLOSE_A_STORM` | Close a Storm | Tool to close an open Storm, making it read-only. Use when you need to prevent further changes to a Storm. Only the Storm creator or a Storm administrator can close a storm. | | `STORMBOARD_CREATE_A_LINE_CONNECTOR` | Create a Line Connector | Tool to create a line connector between two ideas. Use when you need to establish a connection between a pair of ideas on the Storm board. | | `STORMBOARD_CREATE_A_NEW_CHAT_MESSAGE` | Create a new chat message | Tool to create a new chat message in a Stormboard storm. Use when you need to post a message to a specific storm's chat. | | `STORMBOARD_CREATE_A_NEW_STORM` | Create a New Storm | Tool to create a new Storm in Stormboard for interactive planning and collaboration. Use when you need to create a digital workspace for brainstorming, planning, or team collaboration. | | `STORMBOARD_CREATE_A_NEW_TAG` | Create a New Tag | Tool to create a new tag in a Storm without any data related to Ideas. Use when you need to add a new tag to a Storm's tag collection. | | `STORMBOARD_CREATE_A_NEW_USER` | Create a New User | Tool to create a new user account in Stormboard. An email will be sent to the newly created user asking them to verify their account. Use when you need to add a new user to the system. | | `STORMBOARD_CREATE_AN_IDEA_IN_STORMBOARD` | Create an idea in Stormboard | Tool to create a new idea in an existing Stormboard storm. Use when you need to add ideas, notes, or items to a storm with specific content and details. | | `STORMBOARD_CREATE_TAG_DATA_FOR_AN_IDEA` | Create Tag Data for an Idea | Tool to update tag data for an idea. Any tag not in the change list remains unchanged. Tags not found in the Storm are created automatically with the provided tag data applied. | | `STORMBOARD_DECLINE_A_STORM_INVITE` | Decline a Storm Invite | Tool to decline a Storm invitation and remove it from your list. Use when a user wants to reject an invitation to join a Storm. | | `STORMBOARD_DELETE_A_CONNECTOR_BETWEEN_IDEAS` | Delete a Connector Between Ideas | Tool to delete a line connector between two ideas. Use when you need to remove a connection between a pair of ideas on the Storm board. | | `STORMBOARD_DELETE_A_SPECIFIC_CONNECTOR` | Delete a Specific Connector | Tool to delete a line connector using the connector ID. Use when you need to remove a specific connector from the Storm board. | | `STORMBOARD_GET_STORM_DETAILS` | Get Storm Details | Tool to retrieve detailed information about a specific Storm. Use when you need to get complete Storm details including metadata, settings, and configuration. | | `STORMBOARD_DUPLICATE_A_STORM` | Duplicate a Storm | Tool to duplicate an existing Storm. Use when you need to create a copy of a Storm with all its content. | | `STORMBOARD_GET_A_LIST_OF_CONNECTORS_IN_A_STORM` | Get a list of connectors in a Storm | Tool to retrieve a list of connectors within a specific Storm. Use when you need to access relationship data between ideas or elements in a Storm. | | `STORMBOARD_GET_A_LIST_OF_IDEAS` | Get a List of Ideas | Tool to retrieve all ideas from a Storm. Returns a list of ideas, but Files, Images, and Whiteboards do not contain their corresponding data at this time. Use when you need to get an overview of all ideas in a Storm. | | `STORMBOARD_GET_A_LIST_OF_PARTICIPANTS` | Get A List Of Participants | Tool to retrieve a list of all participants in a Storm. Use when you need to see who has access to a specific Storm and their roles. | | `STORMBOARD_GET_A_LIST_OF_STORMS_INVITES` | Get A List Of Storms Invites | Tool to retrieve a list of storms that you have been invited to. Use when you need to see pending storm invitations for the authenticated user. | | `STORMBOARD_GET_LIST_OF_TAGS_IN_STORM` | Get List of Tags in Storm | Tool to retrieve the list of tags that have been created in a Storm. Use when you need to view all tags available in a specific Storm. Note that tag data for individual ideas is not available through this endpoint. | | `STORMBOARD_GET_A_LIST_OF_YOUR_STORMS` | Get A List Of Your Storms | Tool to retrieve a list of storms from Stormboard. Use when you need to browse or access available storms in the user's account. | | `STORMBOARD_GET_AUTHENTICATION_INFO` | Get Authentication Info | Tool to retrieve authentication information and API token for the authenticated user. Use when you need to get authentication details or verify API access credentials. | | `STORMBOARD_GET_CHAT_MESSAGES` | Get Chat Messages | Tool to retrieve a list of chat messages from a Stormboard storm. Use when you need to view the chat history for a specific storm. | | `STORMBOARD_GET_IDEA_DATA` | Get Idea Data | Tool to retrieve detailed data and metadata for a specific idea. Use when you need to fetch information about an idea including its content, position, creator, votes, comments, and associated task details. | | `STORMBOARD_GET_INFO_ABOUT_YOUR_USER` | Get Info About Your User | Tool to retrieve authenticated user profile information. Use when you need to get the current user's details like name, email, or account metadata. | | `STORMBOARD_GET_MY_STORM_ACCESS` | Get My Storm Access | Tool to check if the authenticated user has access to a Storm and retrieve their permission level. Use when verifying user permissions for a specific Storm. Returns 401 error if user lacks access. | | `STORMBOARD_GET_STORM_TEMPLATE` | Get Storm Template | Tool to retrieve template data for a Storm including all sections and subsections. Use when you need to get the organizational structure and template configuration of a Storm. | | `STORMBOARD_GET_TAG_DATA_FOR_AN_IDEA` | Get Tag Data For An Idea | Tool to retrieve tag data for a specific idea in Stormboard. Use when you need to view all tags associated with a particular idea. | | `STORMBOARD_GET_UNREAD_CHAT_MESSAGES` | Get Unread Chat Messages | Tool to retrieve unread chat messages from a specific Storm. Use when you need to check for new messages in a Storm's chat. | | `STORMBOARD_INVITE_PARTICIPANTS_TO_STORM` | Invite Participants to Storm | Tool to invite people to join a Storm by email. Use when you need to add new participants to a Storm. | | `STORMBOARD_JOIN_A_STORM` | Join a Storm | Tool to join a Storm using its ID and access key. Use when a user wants to add themselves to a Storm's participant list. | | `STORMBOARD_MARK_CHAT_MESSAGES_AS_READ` | Mark Chat Messages as Read | Tool to mark all chat messages as read in a Storm. Use when you need to mark all unread chat messages in a specific Storm as read. | | `STORMBOARD_REMOVE_A_FAVORITE_STAR` | Remove a Favorite Star | Tool to remove a favorite star from a Storm on the Dashboard. Use when you need to unmark a Storm as a favorite. | | `STORMBOARD_REOPEN_A_STORM` | Reopen a Storm | Tool to reopen a closed Storm. Use when you need to reopen a previously closed Storm. Note: You must be a Storm administrator or the team owner to perform this action. | | `STORMBOARD_UPDATE_A_LINE_CONNECTOR` | Update a Line Connector | Tool to update a specific line connector between two ideas. Use when you need to modify the label or style properties of an existing connector. | | `STORMBOARD_UPDATE_NOTIFICATIONS` | Update Notifications | Tool to update user notification preferences. Use when you need to enable or disable email notifications for the authenticated user. | | `STORMBOARD_UPDATE_SECTION_IN_STORM` | Update Section in Storm | Tool to update a section's title, description, and/or character in a Storm. Use when you need to modify section properties. Note: You must be a Storm administrator to perform this action. | | `STORMBOARD_UPDATE_STORM_LEGEND` | Update Storm Legend | Tool to update the color labels of the legend for a storm. Use when you need to customize the legend labels for storm items. You must be the storm creator or a storm administrator to perform this action. | | `STORMBOARD_UPDATE_YOUR_PROFILE` | Update Your Profile | Tool to update your user profile information. Use when you need to modify the authenticated user's first name or last name. | | `STORMBOARD_VERIFY_YOUR_ACCOUNT` | Verify Your Account | Tool to verify a Stormboard account using a verification code. Use when you need to confirm account ownership or complete the account verification process. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Stormboard MCP server is an implementation of the Model Context Protocol that connects your AI agent to Stormboard. It provides structured and secure access so your agent can perform Stormboard 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 No description provided. ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models, or you can connect to another model provider. - Keep the API key safe. Composio API Key - Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies No description provided. ```python pip install composio-langchain langchain-mcp-adapters langchain python-dotenv ``` ```typescript npm install @composio/langchain @langchain/core @langchain/openai @langchain/mcp-adapters dotenv ``` ### 3. Set up environment variables Create a .env file in your project root. What's happening: - COMPOSIO_API_KEY authenticates your requests to Composio's API - COMPOSIO_USER_ID identifies the user for session management - OPENAI_API_KEY enables access to OpenAI's language models ```bash COMPOSIO_API_KEY=your_composio_api_key_here COMPOSIO_USER_ID=your_composio_user_id_here OPENAI_API_KEY=your_openai_api_key_here ``` ### 4. Import dependencies No description provided. ```python from langchain_mcp_adapters.client import MultiServerMCPClient from langchain.agents import create_agent from dotenv import load_dotenv from composio import Composio import asyncio import os load_dotenv() ``` ```typescript import { Composio } from '@composio/core'; import { LangchainProvider } from '@composio/langchain'; import { MultiServerMCPClient } from "@langchain/mcp-adapters"; import { createAgent } from "langchain"; import * as readline from 'readline'; import 'dotenv/config'; dotenv.config(); ``` ### 5. Initialize Composio client What's happening: - We're loading the COMPOSIO_API_KEY from environment variables and validating it exists - Creating a Composio instance that will manage our connection to Stormboard tools - Validating that COMPOSIO_USER_ID is also set before proceeding ```python async def main(): composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) if not os.getenv("COMPOSIO_API_KEY"): raise ValueError("COMPOSIO_API_KEY is not set") if not os.getenv("COMPOSIO_USER_ID"): raise ValueError("COMPOSIO_USER_ID is not set") ``` ```typescript const composioApiKey = process.env.COMPOSIO_API_KEY; const userId = process.env.COMPOSIO_USER_ID; if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set'); if (!userId) throw new Error('COMPOSIO_USER_ID is not set'); async function main() { const composio = new Composio({ apiKey: composioApiKey as string, provider: new LangchainProvider() }); ``` ### 6. Create a Tool Router session What's happening: - We're creating a Tool Router session that gives your agent access to Stormboard tools - The create method takes the user ID and specifies which toolkits should be available - The returned session.mcp.url is the MCP server URL that your agent will use - This approach allows the agent to dynamically load and use Stormboard tools as needed ```python # Create Tool Router session for Stormboard session = composio.create( user_id=os.getenv("COMPOSIO_USER_ID"), toolkits=['stormboard'] ) url = session.mcp.url ``` ```typescript const session = await composio.create( userId as string, { toolkits: ['stormboard'] } ); const url = session.mcp.url; ``` ### 7. Configure the agent with the MCP URL No description provided. ```python client = MultiServerMCPClient({ "stormboard-agent": { "transport": "streamable_http", "url": session.mcp.url, "headers": { "x-api-key": os.getenv("COMPOSIO_API_KEY") } } }) tools = await client.get_tools() agent = create_agent("gpt-5", tools) ``` ```typescript const client = new MultiServerMCPClient({ "stormboard-agent": { transport: "http", url: url, headers: { "x-api-key": process.env.COMPOSIO_API_KEY } } }); const tools = await client.getTools(); const agent = createAgent({ model: "gpt-5", tools }); ``` ### 8. Set up interactive chat interface No description provided. ```python conversation_history = [] print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Stormboard related question or task to the agent.\n") while True: user_input = input("You: ").strip() if user_input.lower() in ['exit', 'quit', 'bye']: print("\nGoodbye!") break if not user_input: continue conversation_history.append({"role": "user", "content": user_input}) print("\nAgent is thinking...\n") response = await agent.ainvoke({"messages": conversation_history}) conversation_history = response['messages'] final_response = response['messages'][-1].content print(f"Agent: {final_response}\n") ``` ```typescript let conversationHistory: any[] = []; console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n"); console.log("Ask any Stormboard related question or task to the agent.\n"); const rl = readline.createInterface({ input: process.stdin, output: process.stdout, prompt: 'You: ' }); rl.prompt(); rl.on('line', async (userInput: string) => { const trimmedInput = userInput.trim(); if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) { console.log("\nGoodbye!"); rl.close(); process.exit(0); } if (!trimmedInput) { rl.prompt(); return; } conversationHistory.push({ role: "user", content: trimmedInput }); console.log("\nAgent is thinking...\n"); const response = await agent.invoke({ messages: conversationHistory }); conversationHistory = response.messages; const finalResponse = response.messages[response.messages.length - 1]?.content; console.log(`Agent: ${finalResponse}\n`); rl.prompt(); }); rl.on('close', () => { console.log('\n👋 Session ended.'); process.exit(0); }); ``` ### 9. Run the application No description provided. ```python if __name__ == "__main__": asyncio.run(main()) ``` ```typescript main().catch((err) => { console.error('Fatal error:', err); process.exit(1); }); ``` ## Complete Code ```python from langchain_mcp_adapters.client import MultiServerMCPClient from langchain.agents import create_agent from dotenv import load_dotenv from composio import Composio import asyncio import os load_dotenv() async def main(): composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) if not os.getenv("COMPOSIO_API_KEY"): raise ValueError("COMPOSIO_API_KEY is not set") if not os.getenv("COMPOSIO_USER_ID"): raise ValueError("COMPOSIO_USER_ID is not set") session = composio.create( user_id=os.getenv("COMPOSIO_USER_ID"), toolkits=['stormboard'] ) url = session.mcp.url client = MultiServerMCPClient({ "stormboard-agent": { "transport": "streamable_http", "url": url, "headers": { "x-api-key": os.getenv("COMPOSIO_API_KEY") } } }) tools = await client.get_tools() agent = create_agent("gpt-5", tools) conversation_history = [] print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Stormboard related question or task to the agent.\n") while True: user_input = input("You: ").strip() if user_input.lower() in ['exit', 'quit', 'bye']: print("\nGoodbye!") break if not user_input: continue conversation_history.append({"role": "user", "content": user_input}) print("\nAgent is thinking...\n") response = await agent.ainvoke({"messages": conversation_history}) conversation_history = response['messages'] final_response = response['messages'][-1].content print(f"Agent: {final_response}\n") if __name__ == "__main__": asyncio.run(main()) ``` ```typescript import { Composio } from '@composio/core'; import { LangchainProvider } from '@composio/langchain'; import { MultiServerMCPClient } from "@langchain/mcp-adapters"; import { createAgent } from "langchain"; import * as readline from 'readline'; import 'dotenv/config'; const composioApiKey = process.env.COMPOSIO_API_KEY; const userId = process.env.COMPOSIO_USER_ID; if (!composioApiKey) throw new Error('COMPOSIO_API_KEY is not set'); if (!userId) throw new Error('COMPOSIO_USER_ID is not set'); async function main() { const composio = new Composio({ apiKey: composioApiKey as string, provider: new LangchainProvider() }); const session = await composio.create( userId as string, { toolkits: ['stormboard'] } ); const url = session.mcp.url; const client = new MultiServerMCPClient({ "stormboard-agent": { transport: "http", url: url, headers: { "x-api-key": process.env.COMPOSIO_API_KEY } } }); const tools = await client.getTools(); const agent = createAgent({ model: "gpt-5", tools }); let conversationHistory: any[] = []; console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n"); console.log("Ask any Stormboard related question or task to the agent.\n"); const rl = readline.createInterface({ input: process.stdin, output: process.stdout, prompt: 'You: ' }); rl.prompt(); rl.on('line', async (userInput: string) => { const trimmedInput = userInput.trim(); if (['exit', 'quit', 'bye'].includes(trimmedInput.toLowerCase())) { console.log("\nGoodbye!"); rl.close(); process.exit(0); } if (!trimmedInput) { rl.prompt(); return; } conversationHistory.push({ role: "user", content: trimmedInput }); console.log("\nAgent is thinking...\n"); const response = await agent.invoke({ messages: conversationHistory }); conversationHistory = response.messages; const finalResponse = response.messages[response.messages.length - 1]?.content; console.log(`Agent: ${finalResponse}\n`); rl.prompt(); }); rl.on('close', () => { console.log('\nSession ended.'); process.exit(0); }); } main().catch((err) => { console.error('Fatal error:', err); process.exit(1); }); ``` ## Conclusion You've successfully built a LangChain agent that can interact with Stormboard through Composio's Tool Router. Key features of this implementation: - Dynamic tool loading through Composio's Tool Router - Conversation history maintenance for context-aware responses - Async Python provides clean, efficient execution of agent workflows You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows. ## How to build Stormboard MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/stormboard/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/stormboard/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/stormboard/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/stormboard/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/stormboard/framework/codex) - [OpenClaw](https://composio.dev/toolkits/stormboard/framework/openclaw) - [Hermes](https://composio.dev/toolkits/stormboard/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/stormboard/framework/cli) - [Google ADK](https://composio.dev/toolkits/stormboard/framework/google-adk) - [Vercel AI SDK](https://composio.dev/toolkits/stormboard/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/stormboard/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/stormboard/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/stormboard/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. - [Google Sheets](https://composio.dev/toolkits/googlesheets) - Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly. - [Notion](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place. - [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. - [Airtable](https://composio.dev/toolkits/airtable) - Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations. - [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. - [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals. - [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem. - [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity. - [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. - [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently. - [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place. - [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. - [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time. - [Figma](https://composio.dev/toolkits/figma) - Figma is a collaborative interface design tool for teams and individuals. It streamlines design workflows with real-time collaboration and easy sharing. - [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. - [Abyssale](https://composio.dev/toolkits/abyssale) - Abyssale is a creative automation platform for generating images, videos, GIFs, PDFs, and HTML5 content programmatically. It streamlines and scales visual content production for marketing, design, and operations teams. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [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. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Stormboard MCP? With a standalone Stormboard MCP server, the agents and LLMs can only access a fixed set of Stormboard tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Stormboard and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with LangChain? Yes, you can. LangChain 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 Stormboard tools. ### Can I manage the permissions and scopes for Stormboard while using Tool Router? Yes, absolutely. You can configure which Stormboard 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 Stormboard data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)