# How to integrate Spondyr MCP with Autogen ```json { "title": "How to integrate Spondyr MCP with Autogen", "toolkit": "Spondyr", "toolkit_slug": "spondyr", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/spondyr/framework/autogen", "markdown_url": "https://composio.dev/toolkits/spondyr/framework/autogen.md", "updated_at": "2026-05-12T10:26:53.357Z" } ``` ## Introduction This guide walks you through connecting Spondyr to AutoGen using the Composio tool router. By the end, you'll have a working Spondyr agent that can list all transaction types in spondyr, create condition rules for refund events, update event type name for shipped orders through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Spondyr account through Composio's Spondyr MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Spondyr with - [OpenAI Agents SDK](https://composio.dev/toolkits/spondyr/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/spondyr/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/spondyr/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/spondyr/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/spondyr/framework/codex) - [OpenClaw](https://composio.dev/toolkits/spondyr/framework/openclaw) - [Hermes](https://composio.dev/toolkits/spondyr/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/spondyr/framework/cli) - [Google ADK](https://composio.dev/toolkits/spondyr/framework/google-adk) - [LangChain](https://composio.dev/toolkits/spondyr/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/spondyr/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/spondyr/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/spondyr/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/spondyr/framework/crew-ai) ## TL;DR Here's what you'll learn: - Get and set up your OpenAI and Composio API keys - Install the required dependencies for Autogen and Composio - Initialize Composio and create a Tool Router session for Spondyr - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Spondyr tools - Run a live chat loop where you ask the agent to perform Spondyr operations ## What is AutoGen? Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows. Key features include: - Multi-Agent Systems: Build collaborative agent workflows - MCP Workbench: Native support for Model Context Protocol tools - Streaming HTTP: Connect to external services through streamable HTTP - AssistantAgent: Pre-built agent class for tool-using assistants ## What is the Spondyr MCP server, and what's possible with it? The Spondyr MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Spondyr account. It provides structured and secure access to your Spondyr templates, transaction types, events, and correspondence workflows, so your agent can perform actions like managing conditions, handling recipients, orchestrating correspondence delivery, and monitoring status updates for your business communications. - Comprehensive transaction type management: Quickly create, list, or update transaction types—making it easy for your agent to adapt Spondyr to your evolving business data needs. - Rule-based template selection: Define and manage conditions that control which templates are used for different transaction scenarios, ensuring your communications are always personalized and relevant. - Automated correspondence delivery and tracking: Have your agent trigger the delivery of generated correspondence and fetch real-time status updates, so you always know when and how your messages are sent. - Dynamic event and recipient handling: List, retrieve, update, or delete event types and recipient information to keep your communication flows flexible and up-to-date. - Seamless integration and configuration management: Effortlessly connect, configure, and synchronize your Spondyr settings and workflows—without manual intervention or custom code. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `SPONDYR_CONDITIONS_LIST` | List Conditions | Tool to list all conditions for a transaction type. Use when you need to discover existing condition rules before creating templates or generating correspondence. Conditions define criteria for selecting specific templates based on transaction data. | | `SPONDYR_CREATE_CONDITION` | Create Condition | Create a condition rule for template selection in Spondyr. Conditions define matching criteria on transaction data fields that determine which document template to use. For example, create a condition on an 'OrderStatus' field to trigger different email templates for 'Pending' vs 'Shipped' orders. | | `SPONDYR_CREATE_TRANSACTION_TYPE` | Create Transaction Type | Tool to create a new transaction type. Use after defining the JSON schema for your data to register it in Spondyr. | | `SPONDYR_DELIVER_SPONDYR` | Deliver Spondyr correspondence | Trigger delivery of previously generated correspondence to recipients. Use this action after generating correspondence (via POST /Spondyr with IsGenerateOnly=true) to actually deliver the documents via email, fax, mail, or text message. The ReferenceID from the generate request is required to identify which correspondence to deliver. | | `SPONDYR_EVENT_TYPE_UPDATE` | Update Event Type | Tool to update an existing event type name within a transaction type. Use when you need to rename an Event Type. Example: Rename the 'OrderShipped' event to 'OrderDelivered' within the 'CustomerOrders' transaction type. Note: This only changes the event type's name - it does not move the event to a different transaction type. | | `SPONDYR_GET_EVENT_TYPES` | List Event Types for Transaction Type | Retrieves all event types associated with a specific transaction type in Spondyr. Event types define the kinds of events that can occur for a transaction type (e.g., "Created", "Updated", "Cancelled" events for an "Order" transaction type). Use this action after retrieving transaction types to discover what event types are available for a given transaction type. This is essential for understanding the event-driven workflows and setting up event-based automation in Spondyr. Returns an empty list if the transaction type exists but has no event types configured. | | `SPONDYR_GET_SPONDYR_STATUS` | Get Spondyr Status | Tool to retrieve the status of a previously generated correspondence. Use after generating correspondence to check its processing and delivery status. | | `SPONDYR_GET_TRANSACTION_TYPES` | Get Transaction Types | Tool to retrieve a list of available transaction types. Use after authentication to discover data schemas. | | `SPONDYR_RECIPIENT_DELETE` | Delete Recipient | Deletes a recipient configuration from a transaction type in Spondyr. Recipients are configured delivery endpoints (email addresses, fax numbers, physical addresses) that determine where correspondence will be sent when a transaction is processed. This action permanently removes a recipient configuration from the specified transaction type. Before deletion, use the 'List Recipients' action to verify the recipient name and transaction type. After successful deletion, the recipient will no longer be available for correspondence delivery. | | `SPONDYR_RECIPIENT_GET` | Get Recipient | Tool to retrieve details of a specific recipient. Use when you need to fetch recipient configuration for a given transaction type. Example: "Retrieve recipient 'Customer' for transaction type 'OrderPlaced'." | | `SPONDYR_RECIPIENTS_LIST` | List Recipients | Tool to list all recipients for a transaction type. Use when you need to discover or verify all configured recipients before sending or managing correspondence. | | `SPONDYR_SEARCH_FILTER_CREATE` | Create Search Filter | Create a new search filter for a transaction type in Spondyr. Search filters enable you to define searchable fields within your transaction data. Once created, these filters allow you to quickly search and retrieve specific transactions based on field values (e.g., search by OrderID, CustomerName, InvoiceNumber). Use this tool when you need to make a specific field searchable within a transaction type. | | `SPONDYR_SEARCH_FILTER_DELETE` | Delete Search Filter | Deletes a specific search filter from the Spondyr system. Use this when you need to remove a search filter that is no longer needed. Both the filter name and transaction type must exactly match the values used when the filter was created. If the filter does not exist, the API will return an error. | | `SPONDYR_SEARCH_FILTER_GET` | Get Search Filter | Retrieves details of a specific search filter in Spondyr by name and transaction type. Returns the filter's name, tag value, and associated transaction type. Use this when you need to look up an existing search filter's configuration, verify its tag format, or confirm which transaction type it belongs to before using it for correspondence searches. | | `SPONDYR_SEARCH_FILTERS_LIST` | List Search Filters | Tool to list all search filters for a transaction type. Use when you need to discover available filters before searching correspondence. | | `SPONDYR_SEARCH_SPONDYRS` | Search Correspondence | Search for generated correspondence (spondyrs) by multiple criteria including batch ID, event type, and custom search filters. Returns paginated results with delivery status, recipient information, and URIs to access generated documents. Use this to find and retrieve previously generated correspondence. | | `SPONDYR_SSO_STUB` | Create Spondyr SSO stub | Tool to create a one-time SSO user stub in Spondyr. Use after application authentication to generate a temporary SSO token for embedding or redirecting users. | | `SPONDYR_TEMPLATE_GET` | Get Template | Retrieve detailed configuration for a specific correspondence template. Returns template content reference ID, event type, recipients, delivery methods, conditions, and search filters. Use this action when you need to: - Inspect template settings and configuration - View recipient delivery methods (Email, Mail, Text, DocuSign, Fax, Destination) - Review template selection conditions and search filters - Get the template content reference ID for correspondence generation Prerequisites: Use 'Get Transaction Types' to discover transaction types, then 'List Templates' to find available template names. Example: Retrieve template 'OrderConfirmationEmail' for transaction type 'CustomerOrder'. | | `SPONDYR_TEMPLATES_LIST` | List Templates | List all templates configured for a transaction type. Use this to discover available templates before generating correspondence or to audit template configurations. Returns template metadata including name, event type, content type, recipients, conditions, and search filters. Use Get Template action to retrieve full template content and detailed configuration. | | `SPONDYR_TRANSACTION_TYPE_GET` | Get Transaction Type | Tool to retrieve details of a specific transaction type. Use when inspecting a transaction type schema. Returns the schema definition including JSON structure and CSV field mappings. Example: "Get transaction type 'CustomerOrder' to view its JSON schema and available fields." | | `SPONDYR_TRANSACTION_TYPE_UPDATE` | Update Transaction Type | Updates an existing transaction type's name and/or JSON schema in Spondyr. Use this tool to: - Modify the JSON schema/template of a transaction type to add, remove, or change data fields - Rename an existing transaction type - Update sample data values in the template Prerequisites: The transaction type must already exist. Use 'Get Transaction Types' to list available types or 'Get Transaction Type' to retrieve the current schema before updating. Example: Update the 'OrderPlaced' transaction type with a new JSON schema that includes customer address fields. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Spondyr MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Spondyr. Instead of manually wiring Spondyr APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely. 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 You will need: - A Composio API key - An OpenAI API key (used by Autogen's OpenAIChatCompletionClient) - A Spondyr account you can connect to Composio - Some basic familiarity with Autogen and Python async ### 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 Install Composio, Autogen extensions, and dotenv. What's happening: - composio connects your agent to Spondyr via MCP - autogen-agentchat provides the AssistantAgent class - autogen-ext-openai provides the OpenAI model client - autogen-ext-tools provides MCP workbench support ```bash pip install composio python-dotenv pip install autogen-agentchat autogen-ext-openai autogen-ext-tools ``` ### 3. Set up environment variables Create a .env file in your project folder. What's happening: - COMPOSIO_API_KEY is required to talk to Composio - OPENAI_API_KEY is used by Autogen's OpenAI client - USER_ID is how Composio identifies which user's Spondyr connections to use ```bash COMPOSIO_API_KEY=your-composio-api-key OPENAI_API_KEY=your-openai-api-key USER_ID=your-user-identifier@example.com ``` ### 4. Import dependencies and create Tool Router session What's happening: - load_dotenv() reads your .env file - Composio(api_key=...) initializes the SDK - create(...) creates a Tool Router session that exposes Spondyr tools - session.mcp.url is the MCP endpoint that Autogen will connect to ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams load_dotenv() async def main(): # Initialize Composio and create a Spondyr session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["spondyr"] ) url = session.mcp.url ``` ### 5. Configure MCP parameters for Autogen Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for. What's happening: - url points to the Tool Router MCP endpoint from Composio - timeout is the HTTP timeout for requests - sse_read_timeout controls how long to wait when streaming responses - terminate_on_close=True cleans up the MCP server process when the workbench is closed ```python # Configure MCP server parameters for Streamable HTTP server_params = StreamableHttpServerParams( url=url, timeout=30.0, sse_read_timeout=300.0, terminate_on_close=True, headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")} ) ``` ### 6. Create the model client and agent What's happening: - OpenAIChatCompletionClient wraps the OpenAI model for Autogen - McpWorkbench connects the agent to the MCP tools - AssistantAgent is configured with the Spondyr tools from the workbench ```python # Create model client model_client = OpenAIChatCompletionClient( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY") ) # Use McpWorkbench as context manager async with McpWorkbench(server_params) as workbench: # Create Spondyr assistant agent with MCP tools agent = AssistantAgent( name="spondyr_assistant", description="An AI assistant that helps with Spondyr operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) ``` ### 7. Run the interactive chat loop What's happening: - The script prompts you in a loop with You: - Autogen passes your input to the model, which decides which Spondyr tools to call via MCP - agent.run_stream(...) yields streaming messages as the agent thinks and calls tools - Typing exit, quit, or bye ends the loop ```python print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Spondyr related question or task to the agent.\n") # Conversation loop while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue print("\nAgent is thinking...\n") # Run the agent with streaming try: response_text = "" async for message in agent.run_stream(task=user_input): if hasattr(message, "content") and message.content: response_text = message.content # Print the final response if response_text: print(f"Agent: {response_text}\n") else: print("Agent: I encountered an issue processing your request.\n") except Exception as e: print(f"Agent: Sorry, I encountered an error: {str(e)}\n") ``` ## Complete Code ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams load_dotenv() async def main(): # Initialize Composio and create a Spondyr session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["spondyr"] ) url = session.mcp.url # Configure MCP server parameters for Streamable HTTP server_params = StreamableHttpServerParams( url=url, timeout=30.0, sse_read_timeout=300.0, terminate_on_close=True, headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")} ) # Create model client model_client = OpenAIChatCompletionClient( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY") ) # Use McpWorkbench as context manager async with McpWorkbench(server_params) as workbench: # Create Spondyr assistant agent with MCP tools agent = AssistantAgent( name="spondyr_assistant", description="An AI assistant that helps with Spondyr operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Spondyr related question or task to the agent.\n") # Conversation loop while True: user_input = input("You: ").strip() if user_input.lower() in ['exit', 'quit', 'bye']: print("\nGoodbye!") break if not user_input: continue print("\nAgent is thinking...\n") # Run the agent with streaming try: response_text = "" async for message in agent.run_stream(task=user_input): if hasattr(message, 'content') and message.content: response_text = message.content # Print the final response if response_text: print(f"Agent: {response_text}\n") else: print("Agent: I encountered an issue processing your request.\n") except Exception as e: print(f"Agent: Sorry, I encountered an error: {str(e)}\n") if __name__ == "__main__": asyncio.run(main()) ``` ## Conclusion You now have an Autogen assistant wired into Spondyr through Composio's Tool Router and MCP. From here you can: - Add more toolkits to the toolkits list, for example notion or hubspot - Refine the agent description to point it at specific workflows - Wrap this script behind a UI, Slack bot, or internal tool Once the pattern is clear for Spondyr, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Spondyr MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/spondyr/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/spondyr/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/spondyr/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/spondyr/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/spondyr/framework/codex) - [OpenClaw](https://composio.dev/toolkits/spondyr/framework/openclaw) - [Hermes](https://composio.dev/toolkits/spondyr/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/spondyr/framework/cli) - [Google ADK](https://composio.dev/toolkits/spondyr/framework/google-adk) - [LangChain](https://composio.dev/toolkits/spondyr/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/spondyr/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/spondyr/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/spondyr/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/spondyr/framework/crew-ai) ## Related Toolkits - [Apilio](https://composio.dev/toolkits/apilio) - Apilio is a home automation platform that lets you connect and control smart devices from different brands. It helps you build flexible automations with complex conditions, schedules, and integrations. - [Basin](https://composio.dev/toolkits/basin) - Basin is a no-code form backend for quickly setting up reliable contact forms. It lets you collect and manage form submissions without writing any server-side code. - [Bouncer](https://composio.dev/toolkits/bouncer) - Bouncer is an email validation platform that verifies the authenticity of email addresses in real-time and batch. It helps boost deliverability and reduce bounce rates for your communications. - [Conveyor](https://composio.dev/toolkits/conveyor) - Conveyor is a platform that automates security reviews with a Trust Center and AI-driven questionnaire automation. It streamlines compliance and vendor security processes for faster, hassle-free reviews. - [Crowdin](https://composio.dev/toolkits/crowdin) - Crowdin is a localization management platform that streamlines translation workflows and collaboration. It helps teams centralize multilingual content, boost productivity, and automate translation processes. - [Databox](https://composio.dev/toolkits/databox) - Databox is a business analytics platform that connects your data from any tool and device. It helps you track KPIs, build dashboards, and discover actionable insights. - [Detrack](https://composio.dev/toolkits/detrack) - Detrack is a delivery management platform for real-time tracking and proof of delivery. It helps businesses automate notifications and keep customers updated every step of the way. - [Dnsfilter](https://composio.dev/toolkits/dnsfilter) - Dnsfilter is a cloud-based DNS security and content filtering solution. It helps organizations block online threats and manage safe internet access with ease. - [Faraday](https://composio.dev/toolkits/faraday) - Faraday lets you embed AI in workflows across your stack for smarter automation. It boosts your favorite tools with actionable intelligence and seamless integration. - [Feathery](https://composio.dev/toolkits/feathery) - Feathery is an AI-powered platform for building dynamic data intake forms with advanced logic. It helps teams automate complex workflows and collect structured data with ease. - [Fillout forms](https://composio.dev/toolkits/fillout_forms) - Fillout forms is an online platform for building and managing forms with a flexible API. It lets you create, distribute, and collect responses from forms with ease. - [Formdesk](https://composio.dev/toolkits/formdesk) - Formdesk is an online form builder for creating and managing professional forms. It's perfect for collecting data, automating workflows, and integrating form submissions with your favorite services. - [Formsite](https://composio.dev/toolkits/formsite) - Formsite lets you build online forms and surveys with drag-and-drop simplicity. Capture, manage, and integrate form responses securely for streamlined workflows. - [Graphhopper](https://composio.dev/toolkits/graphhopper) - GraphHopper is an enterprise-grade Directions API for routing, optimization, and geocoding across multiple vehicle types. It enables fast, reliable route planning and logistics automation for businesses. - [Hyperbrowser](https://composio.dev/toolkits/hyperbrowser) - Hyperbrowser is a next-generation platform for scalable browser automation. It empowers AI agents to interact with web apps, automate workflows, and handle browser sessions at scale. - [La Growth Machine](https://composio.dev/toolkits/lagrowthmachine) - La Growth Machine automates multi-channel sales outreach and routine tasks for sales teams. Streamline your workflow and focus on closing more deals. - [Leverly](https://composio.dev/toolkits/leverly) - Leverly is a workflow automation platform that connects and coordinates actions across your apps. It streamlines repetitive processes so your business runs smoother, faster, and with fewer manual steps. - [Maintainx](https://composio.dev/toolkits/maintainx) - Maintainx is a cloud-based CMMS for centralizing maintenance data, communication, and workflows. It helps organizations streamline maintenance operations and improve team coordination. - [Make](https://composio.dev/toolkits/make) - Make is an automation platform that connects your favorite apps and services. Build powerful, custom workflows without writing code. - [Ntfy](https://composio.dev/toolkits/ntfy) - Ntfy is a notification service to send push messages to phones or desktops. Instantly deliver alerts and updates to users, devices, or teams. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Spondyr MCP? With a standalone Spondyr MCP server, the agents and LLMs can only access a fixed set of Spondyr tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Spondyr and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Autogen? Yes, you can. Autogen 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 Spondyr tools. ### Can I manage the permissions and scopes for Spondyr while using Tool Router? Yes, absolutely. You can configure which Spondyr 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 Spondyr data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)