# How to integrate Clientary MCP with LangChain ```json { "title": "How to integrate Clientary MCP with LangChain", "toolkit": "Clientary", "toolkit_slug": "clientary", "framework": "LangChain", "framework_slug": "langchain", "url": "https://composio.dev/toolkits/clientary/framework/langchain", "markdown_url": "https://composio.dev/toolkits/clientary/framework/langchain.md", "updated_at": "2026-03-29T06:27:37.976Z" } ``` ## Introduction This guide walks you through connecting Clientary to LangChain using the Composio tool router. By the end, you'll have a working Clientary agent that can create new invoice for a client, list all active projects this month, send payment reminder to overdue clients through natural language commands. This guide will help you understand how to give your LangChain agent real control over a Clientary account through Composio's Clientary MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Clientary with - [ChatGPT](https://composio.dev/toolkits/clientary/framework/chatgpt) - [Antigravity](https://composio.dev/toolkits/clientary/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/clientary/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/clientary/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/clientary/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/clientary/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/clientary/framework/codex) - [Cursor](https://composio.dev/toolkits/clientary/framework/cursor) - [VS Code](https://composio.dev/toolkits/clientary/framework/vscode) - [OpenCode](https://composio.dev/toolkits/clientary/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/clientary/framework/openclaw) - [Hermes](https://composio.dev/toolkits/clientary/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/clientary/framework/cli) - [Google ADK](https://composio.dev/toolkits/clientary/framework/google-adk) - [Vercel AI SDK](https://composio.dev/toolkits/clientary/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/clientary/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/clientary/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/clientary/framework/crew-ai) ## TL;DR Here's what you'll learn: - Get and set up your OpenAI and Composio API keys - Connect your Clientary project to Composio - Create a Tool Router MCP session for Clientary - Initialize an MCP client and retrieve Clientary tools - Build a LangChain agent that can interact with Clientary - 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 Clientary MCP server, and what's possible with it? The Clientary MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Clientary account. It provides structured and secure access so your agent can perform Clientary operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `CLIENTARY_CREATE_CLIENT` | Create Client | Tool to create a new client record in Clientary. Use when you need to add a new client to the system with company details and contact information. | | `CLIENTARY_CREATE_CONTACT` | Create Contact | Tool to create a new contact within a specified client. Use when you need to add a contact to a client account with name and email as required fields. | | `CLIENTARY_CREATE_EXPENSE` | Create Expense | Tool to create a new expense record in Clientary to track expenditures within your account. Use when you need to record expenses, optionally assigning them to specific clients or projects. Requires an amount field. | | `CLIENTARY_CREATE_LEAD` | Create Lead | Tool to create a new lead record in Clientary. Use when you need to add a new lead to the system with company details and contact information. | | `CLIENTARY_CREATE_PROJECT` | Create Project | Tool to create a new project in Clientary with name and rate. Use when you need to set up a new project for tracking time, expenses, or managing client work. | | `CLIENTARY_CREATE_TASK` | Create Task | Tool to create a new task in Clientary. Use when you need to create a task with a title, optionally associating it with a project and assignee. | | `CLIENTARY_DELETE_CLIENT` | Delete Client | Tool to remove a client and all associated projects, invoices, estimates, and contacts. Use when you need to permanently delete a client from Clientary. WARNING: Deletions are permanent and not reversible. | | `CLIENTARY_DELETE_LEAD` | Delete Lead | Tool to permanently delete a lead and all associated Estimates and Contacts. Use when you need to remove a lead that is no longer needed. Warning: This action is irreversible. | | `CLIENTARY_DELETE_PAYMENT` | Delete Payment | Tool to remove an existing payment from an invoice. Use when you need to permanently delete a payment record. WARNING: Deletions are permanent and not reversible. | | `CLIENTARY_DELETE_PAYMENT_PROFILE` | Delete Payment Profile | Tool to remove a specific payment profile from a client's account. Use when you need to delete a payment profile. Note: Client must have an active payment integration with Stripe to manage payment profiles. | | `CLIENTARY_DELETE_RECURRING_SCHEDULE` | Delete Recurring Schedule | Tool to remove a recurring schedule by its identifier. Use when you need to permanently delete a recurring schedule from Clientary. Once deleted, the recurring schedule will no longer generate periodic invoices. | | `CLIENTARY_GET_CLIENT` | Get Client | Tool to fetch details for a specific client using its ID. Use when you need to retrieve complete information about a client from Clientary. | | `CLIENTARY_GET_CONTACT` | Get Contact | Tool to retrieve a single contact by its ID. Use when you need to fetch detailed information about a specific contact from Clientary. | | `CLIENTARY_GET_ESTIMATE` | Get Estimate | Tool to retrieve details for a single estimate by ID. Use when you need to obtain comprehensive estimate information including line items, tax details, and financial data. | | `CLIENTARY_GET_EXPENSE` | Get Expense | Tool to retrieve details for a single expense record in Clientary. Use when you need to get specific information about an expense by its unique identifier. | | `CLIENTARY_GET_HOUR_ENTRY` | Get Hour Entry | Tool to obtain details about a specific time entry in Clientary. Use when you need to retrieve information about a logged hour entry by its unique identifier. | | `CLIENTARY_GET_INVOICE` | Get Invoice | Tool to retrieve detailed information for a specific invoice by ID. Use when you need to fetch invoice details including line items, payments, tax information, and current status. | | `CLIENTARY_GET_LEAD` | Get Lead | Tool to retrieve a single lead by its ID. Use when you need to fetch detailed information about a specific lead from Clientary. | | `CLIENTARY_GET_PROJECT` | Get Project | Tool to retrieve a single project by its identifier. Use when you need to fetch detailed information about a specific project in Clientary. | | `CLIENTARY_GET_STAFF` | Get Staff | Tool to retrieve a single staff member by their ID. Use when you need to fetch detailed information about a specific staff member from Clientary. | | `CLIENTARY_GET_TASK` | Get Task | Tool to retrieve a specific task by its ID. Use when you need to fetch detailed information about a task from Clientary. | | `CLIENTARY_LIST_CLIENT_CONTACTS` | List Client Contacts | Tool to retrieve all contacts for a specific client with pagination support. Use when you need to fetch the list of contacts associated with a particular client in Clientary. | | `CLIENTARY_LIST_CLIENT_EXPENSES` | List Client Expenses | Tool to retrieve all expenses for a specific client within an optional date range. Use when you need to fetch expense records associated with a particular client from Clientary. | | `CLIENTARY_LIST_CLIENT_INVOICES` | List Client Invoices | Tool to retrieve all invoices for a specific client with pagination support (30 results per page). Use when you need to fetch invoices associated with a particular client from Clientary. | | `CLIENTARY_LIST_CLIENT_PROJECTS` | List Client Projects | Tool to retrieve all projects associated with a specific client with pagination support (10 results per page). Use when you need to fetch projects for a particular client from Clientary. | | `CLIENTARY_LIST_CLIENTS` | List Clients | Tool to retrieve all clients with pagination support (10 results per page). Use when you need to fetch a list of clients from Clientary with optional filtering by modification date or custom sorting. | | `CLIENTARY_LIST_EXPENSES` | List Expenses | Tool to retrieve expenses by date range (defaults to current fiscal year). Use when you need to fetch a list of expenses from Clientary with optional filtering by start and end dates. | | `CLIENTARY_LIST_LEADS` | List Leads | Tool to retrieve all leads with pagination support. Use when you need to fetch a list of leads from Clientary with optional sorting by name or date. | | `CLIENTARY_LIST_PAYMENTS` | List Payments | Tool to retrieve all payments with pagination support (30 results per page). Use when you need to fetch a list of payments from Clientary with optional pagination and custom sorting. | | `CLIENTARY_LIST_PROJECT_ESTIMATES` | List Project Estimates | Tool to retrieve estimates scoped to a particular project with pagination support (30 results per page). Use when you need to fetch all estimates associated with a specific project. | | `CLIENTARY_LIST_PROJECT_EXPENSES` | List Project Expenses | Tool to retrieve all expenses for a specific project within an optional date range. Use when you need to fetch expense records associated with a particular project from Clientary. | | `CLIENTARY_LIST_PROJECT_HOURS` | List Project Hours | Tool to retrieve all time tracking entries logged against a specific project. Use when you need to fetch hour entries for a particular project, optionally filtering by billed or unbilled status. | | `CLIENTARY_LIST_PROJECT_INVOICES` | List Project Invoices | Tool to retrieve all invoices linked to a specific project with pagination support (30 results per page). Use when you need to fetch invoices associated with a particular project from Clientary. | | `CLIENTARY_LIST_PROJECTS` | List Projects | Tool to retrieve all projects with pagination support (10 results per page). Use when you need to fetch a list of projects from Clientary with optional filtering for closed projects. | | `CLIENTARY_LIST_STAFF` | List Staff | Tool to retrieve all staff members for an account. Use when you need to fetch a complete list of staff members from Clientary. | | `CLIENTARY_LIST_TASKS` | List Tasks | Tool to retrieve all tasks with pagination support (50 results per page). Use when you need to fetch a list of tasks from Clientary. | | `CLIENTARY_SEND_INVOICE_MESSAGE` | Send Invoice Message | Tool to send an invoice message to recipients via email. Use when you need to email an invoice to clients with customizable subject, message content, and options to send a copy to yourself or attach a PDF. | | `CLIENTARY_UPDATE_CLIENT` | Update Client | Tool to update an existing client record in Clientary with partial or complete field modifications. Use when you need to modify client details such as name, address, description, or custom fields. All fields except ID are optional. | | `CLIENTARY_UPDATE_EXPENSE` | Update Expense | Tool to update an existing expense record in Clientary with partial or complete field modifications. Use when you need to modify expense details such as amount, description, client assignment, project assignment, or incurred date. All fields except ID are optional. | | `CLIENTARY_UPDATE_HOUR_ENTRY` | Update Hour Entry | Tool to modify an existing time entry in Clientary with partial or complete field updates. Use when you need to update hours, title, date, description, rate, or billing status of a logged hour entry. | | `CLIENTARY_UPDATE_PROJECT` | Update Project | Tool to update an existing project in Clientary with partial or complete field modifications. Use when you need to modify project details such as name, rate, description, budget, status, or other project attributes. All fields except ID are optional - only provided fields will be updated. | | `CLIENTARY_UPDATE_TASK` | Update Task | Tool to update an existing task in Clientary with partial or complete field modifications. Use when you need to modify task details such as title, description, completion status, assignee, or due date. All fields except ID are optional. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Clientary MCP server is an implementation of the Model Context Protocol that connects your AI agent to Clientary. It provides structured and secure access so your agent can perform Clientary 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 Clientary 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 Clientary 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 Clientary tools as needed ```python # Create Tool Router session for Clientary session = composio.create( user_id=os.getenv("COMPOSIO_USER_ID"), toolkits=['clientary'] ) url = session.mcp.url ``` ```typescript const session = await composio.create( userId as string, { toolkits: ['clientary'] } ); const url = session.mcp.url; ``` ### 7. Configure the agent with the MCP URL No description provided. ```python client = MultiServerMCPClient({ "clientary-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({ "clientary-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 Clientary 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 Clientary 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=['clientary'] ) url = session.mcp.url client = MultiServerMCPClient({ "clientary-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 Clientary 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: ['clientary'] } ); const url = session.mcp.url; const client = new MultiServerMCPClient({ "clientary-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 Clientary 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 Clientary 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 Clientary MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/clientary/framework/chatgpt) - [Antigravity](https://composio.dev/toolkits/clientary/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/clientary/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/clientary/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/clientary/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/clientary/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/clientary/framework/codex) - [Cursor](https://composio.dev/toolkits/clientary/framework/cursor) - [VS Code](https://composio.dev/toolkits/clientary/framework/vscode) - [OpenCode](https://composio.dev/toolkits/clientary/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/clientary/framework/openclaw) - [Hermes](https://composio.dev/toolkits/clientary/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/clientary/framework/cli) - [Google ADK](https://composio.dev/toolkits/clientary/framework/google-adk) - [Vercel AI SDK](https://composio.dev/toolkits/clientary/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/clientary/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/clientary/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/clientary/framework/crew-ai) ## Related Toolkits - [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. - [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. - [Hubspot](https://composio.dev/toolkits/hubspot) - HubSpot is an all-in-one marketing, sales, and customer service platform. It lets teams nurture leads, automate outreach, and track every customer interaction in one place. - [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. - [Pipedrive](https://composio.dev/toolkits/pipedrive) - Pipedrive is a sales management platform offering pipeline visualization, lead tracking, and workflow automation. It helps sales teams keep deals moving forward efficiently and never miss a follow-up. - [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. - [Salesforce](https://composio.dev/toolkits/salesforce) - Salesforce is a leading CRM platform that helps businesses manage sales, service, and marketing. It centralizes customer data, enabling teams to drive growth and build strong relationships. - [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. - [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. - [Apollo](https://composio.dev/toolkits/apollo) - Apollo is a CRM and lead generation platform that helps businesses discover contacts and manage sales pipelines. Use it to streamline customer outreach and track your deals from one place. - [Attio](https://composio.dev/toolkits/attio) - Attio is a customizable CRM and workspace for managing your team's relationships and workflows. It helps teams organize contacts, automate tasks, and collaborate more efficiently. - [Stripe](https://composio.dev/toolkits/stripe) - Stripe is a global online payments platform offering APIs for managing payments, customers, and subscriptions. Trusted by businesses for secure, efficient, and scalable payment processing worldwide. - [Acculynx](https://composio.dev/toolkits/acculynx) - AccuLynx is a cloud-based roofing business management software for contractors. It streamlines project tracking, lead management, and document sharing. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools. - [Affinity](https://composio.dev/toolkits/affinity) - Affinity is a relationship intelligence CRM that helps private capital investors find, manage, and close more deals. It streamlines deal flow and surfaces key connections to help you win opportunities. - [Agencyzoom](https://composio.dev/toolkits/agencyzoom) - AgencyZoom is a sales and performance platform built for P&C insurance agencies. It helps agents boost sales, retain clients, and analyze producer results in one place. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Clientary MCP? With a standalone Clientary MCP server, the agents and LLMs can only access a fixed set of Clientary tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Clientary 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 Clientary tools. ### Can I manage the permissions and scopes for Clientary while using Tool Router? Yes, absolutely. You can configure which Clientary 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 Clientary data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)