# How to integrate Parallel MCP with Pydantic AI ```json { "title": "How to integrate Parallel MCP with Pydantic AI", "toolkit": "Parallel", "toolkit_slug": "parallel", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/parallel/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/parallel/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:21:17.787Z" } ``` ## Introduction This guide walks you through connecting Parallel to Pydantic AI using the Composio tool router. By the end, you'll have a working Parallel agent that can find top articles on generative ai trends, summarize recent news about electric vehicles, batch search for competitors' product launches through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Parallel account through Composio's Parallel MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Parallel with - [OpenAI Agents SDK](https://composio.dev/toolkits/parallel/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/parallel/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/parallel/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/parallel/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/parallel/framework/codex) - [OpenClaw](https://composio.dev/toolkits/parallel/framework/openclaw) - [Hermes](https://composio.dev/toolkits/parallel/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/parallel/framework/cli) - [Google ADK](https://composio.dev/toolkits/parallel/framework/google-adk) - [LangChain](https://composio.dev/toolkits/parallel/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/parallel/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/parallel/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/parallel/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/parallel/framework/crew-ai) ## TL;DR Here's what you'll learn: - How to set up your Composio API key and User ID - How to create a Composio Tool Router session for Parallel - How to attach an MCP Server to a Pydantic AI agent - How to stream responses and maintain chat history - How to build a simple REPL-style chat interface to test your Parallel workflows ## What is Pydantic AI? Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications. Key features include: - Type Safety: Built on Pydantic for automatic data validation - MCP Support: Native support for Model Context Protocol servers - Streaming: Built-in support for streaming responses - Async First: Designed for async/await patterns ## What is the Parallel MCP server, and what's possible with it? The Parallel MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Parallel account. It provides structured and secure access to advanced web research automation, so your agent can perform actions like launching batch research tasks, running semantic searches, monitoring task progress, and generating research suggestions on your behalf. - Automated web research task creation: Instantly create structured research tasks or batch multiple queries for parallel execution, saving time and effort. - Semantic search across multiple topics: Direct your agent to run parallel semantic searches and retrieve top-matching documents or data for several queries at once. - Real-time task group monitoring: Let your agent stream live updates about the progress, completion, or status of ongoing research task groups. - Context-driven research suggestions: Have the agent suggest the next best research tasks based on your project or intent, keeping your workflow efficient and on track. - Task group retrieval and management: Fetch detailed information about specific research task groups to review results or track progress seamlessly. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `PARALLEL_ADD_ENRICHMENT_TO_FIND_ALL_RUN` | Add Enrichment to FindAll Run | Tool to add an enrichment to a FindAll run. Use when you need to enrich existing FindAll run results with additional structured data fields. Enrichments define what information to extract from matched entities using a JSON schema. | | `PARALLEL_ADD_RUNS_TO_TASK_GROUP` | Add Runs to Task Group | Tool to initiate multiple task runs within a TaskGroup. Use when you need to execute multiple tasks in parallel within an existing task group. | | `PARALLEL_CANCEL_FIND_ALL_RUN` | Cancel FindAll Run | Tool to cancel an active FindAll run by findall_id. Use when you need to stop a running FindAll operation before it completes. Cannot cancel runs that have already terminated. | | `PARALLEL_CREATE_CHAT_COMPLETIONS` | Create Chat Completions | Tool to get realtime chat completions from Parallel AI. Use when you need conversational AI responses or structured outputs via chat interface. Can be combined with Task API processors for research-grade structured outputs with citations and reasoning. | | `PARALLEL_CREATE_MONITOR` | Create Monitor | Tool to create a web monitor that periodically runs the specified query. The monitor runs once at creation and then continues according to the specified cadence (hourly, daily, weekly, or every two weeks). Use when you need to track changes or developments for a specific search query over time. | | `PARALLEL_CREATE_TASK_GROUP` | Create Task Group | Tool to create a new task group. Use when batching multiple tasks for parallel execution. Task Groups enable grouping and tracking of multiple task runs within a single manageable unit. | | `PARALLEL_CREATE_TASK_RUN` | Create Task Run | Tool to create and initiate a task run. Returns immediately with a run object in status 'queued'. Use when you need to execute tasks asynchronously with Parallel AI processors. | | `PARALLEL_DELETE_MONITOR` | Delete Monitor | Tool to delete a monitor, stopping all future executions. Use when you need to permanently remove a monitor. Deleted monitors can no longer be updated or retrieved. | | `PARALLEL_EXTEND_FIND_ALL_RUN` | Extend FindAll Run | Tool to extend a FindAll run by adding additional matches to the current match limit. Use when you need to increase the number of matches for an existing FindAll run that is still active or has completed. | | `PARALLEL_EXTRACT` | Extract Content from URLs | Tool to extract relevant content from specific web URLs. Use when you need to fetch and extract content from known URLs with optional focusing on specific objectives or search queries. | | `PARALLEL_FETCH_TASK_GROUP_RUNS` | Fetch Task Group Runs | Tool to retrieve task runs from a Task Group as a resumable stream. Use when you need to fetch all runs within a group, optionally including their inputs and outputs. The stream can be resumed using the event_id as a cursor. | | `PARALLEL_FIND_ALL` | Start FindAll Run | Tool to start a FindAll run. Use when you need to discover and match entities based on natural-language objectives. Supports custom conditions, exclusion lists, and webhook callbacks. | | `PARALLEL_GET_FIND_ALL_RUN_RESULT` | Get FindAll Run Result | Tool to fetch the final (or latest available) FindAll candidates and result payload for a run. Use when you need to retrieve matched/unmatched candidates after a FindAll run has progressed or completed. | | `PARALLEL_GET_FIND_ALL_RUN_SCHEMA` | Get FindAll Run Schema | Tool to retrieve the schema configuration of a FindAll run by findall_id. Use when you need to inspect the objective, entity type, match conditions, and other schema details for a previously created FindAll run. | | `PARALLEL_INGEST_FIND_ALL_RUN` | Ingest FindAll Run | Tool to transform a natural language search objective into a structured FindAll specification. Use when you need to generate a FindAll run spec from a user's natural language description. The generated specification serves as a suggested starting point and can be further customized. | | `PARALLEL_LIST_MONITOR_EVENTS` | List Monitor Events | Tool to list events for a monitor from up to the last 300 event groups. Retrieves events including errors and material changes in reverse chronological order. | | `PARALLEL_LIST_MONITORS` | List Monitors | Tool to list active monitors for the user. Returns all monitors regardless of status with their configuration and current state. Supports cursor-based pagination using monitor_id and limit parameters. | | `PARALLEL_RETRIEVE_EVENT_GROUP` | Retrieve Event Group | Tool to retrieve an event group for a monitor. Use when you have a valid monitor ID and event group ID and want to view the execution history. | | `PARALLEL_RETRIEVE_FIND_ALL_RUN_STATUS` | Retrieve FindAll Run Status | Tool to retrieve status and metadata for a FindAll run by findall_id. Use when you need to poll or check the progress of a FindAll run that was previously created. | | `PARALLEL_RETRIEVE_MONITOR` | Retrieve Monitor | Tool to retrieve a specific monitor by ID. Returns the monitor configuration including status, cadence, query, and webhook settings. | | `PARALLEL_RETRIEVE_TASK_GROUP` | Retrieve Task Group | Tool to retrieve details of a specific task group. Use when you have a valid task group ID and want to view its details. | | `PARALLEL_RETRIEVE_TASK_GROUP_RUN` | Retrieve Task Group Run | Tool to retrieve run status by run_id for a task group. Use when you need to check the status of a specific task group run or poll for completion. | | `PARALLEL_RETRIEVE_TASK_RUN` | Retrieve Task Run | Tool to retrieve run status by run_id. Use when you need to check the status or details of a specific task run. The run result is available from the /result endpoint. | | `PARALLEL_RETRIEVE_TASK_RUN_INPUT` | Retrieve Task Run Input | Tool to retrieve the input data of a specific task run by run_id. Use when you need to view the original input parameters that were provided to a task run. | | `PARALLEL_RETRIEVE_TASK_RUN_RESULT` | Retrieve Task Run Result | Tool to retrieve the result of a task run by run_id, blocking until the run completes. Use when you need to wait for and fetch the final output of a previously initiated task run. The request will block until the run completes or the timeout is reached. | | `PARALLEL_PARALLEL_SEARCH` | Parallel Search | Tool to perform parallel semantic search. Use when you need to retrieve top matching documents for multiple queries in a single call. | | `PARALLEL_SIMULATE_EVENT` | Simulate Event | Tool to simulate sending an event for a monitor. Use when testing monitor webhooks or validating monitor configurations. Simulates sending an event of the specified type (defaults to monitor.event.detected). | | `PARALLEL_STREAM_FIND_ALL_EVENTS` | Stream FindAll Events | Tool to stream events from a FindAll run. Use when you need real-time updates on candidate discovery, matching progress, and run status. | | `PARALLEL_STREAM_TASK_GROUP_EVENTS` | Stream Task Group Events | Tool to stream events for a Task Group. Use when you want real-time updates of group status and run completions. | | `PARALLEL_STREAM_TASK_RUN_EVENTS` | Stream Task Run Events | Tool to stream events for a Task Run. Returns progress updates and state changes for the task run. For runs without enable_events=true, event frequency is reduced. | | `PARALLEL_SUGGEST_TASK` | Suggest Task | Tool to suggest tasks based on user intent. Use when you need task specifications generated from a natural language description of what you want to accomplish. | | `PARALLEL_UPDATE_MONITOR` | Update Monitor | Tool to update a monitor's configuration. Use when you need to modify an existing monitor's cadence, query, metadata, or webhook settings. At least one field must be non-null to apply an update. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Parallel MCP server is an implementation of the Model Context Protocol that connects your AI agent to Parallel. It provides structured and secure access so your agent can perform Parallel 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 starting, make sure you have: - Python 3.9 or higher - A Composio account with an active API key - Basic familiarity with Python and async programming ### 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 the required libraries. What's happening: - composio connects your agent to external SaaS tools like Parallel - pydantic-ai lets you create structured AI agents with tool support - python-dotenv loads your environment variables securely from a .env file ```bash pip install composio pydantic-ai python-dotenv ``` ### 3. Set up environment variables Create a .env file in your project root. What's happening: - COMPOSIO_API_KEY authenticates your agent to Composio's API - USER_ID associates your session with your account for secure tool access - OPENAI_API_KEY to access OpenAI LLMs ```bash COMPOSIO_API_KEY=your_composio_api_key_here USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key ``` ### 4. Import dependencies What's happening: - We load environment variables and import required modules - Composio manages connections to Parallel - MCPServerStreamableHTTP connects to the Parallel MCP server endpoint - Agent from Pydantic AI lets you define and run the AI assistant ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from pydantic_ai import Agent from pydantic_ai.mcp import MCPServerStreamableHTTP load_dotenv() ``` ### 5. Create a Tool Router Session What's happening: - We're creating a Tool Router session that gives your agent access to Parallel 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 ```python async def main(): api_key = os.getenv("COMPOSIO_API_KEY") user_id = os.getenv("USER_ID") if not api_key or not user_id: raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment") # Create a Composio Tool Router session for Parallel composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["parallel"], ) url = session.mcp.url if not url: raise ValueError("Composio session did not return an MCP URL") ``` ### 6. Initialize the Pydantic AI Agent What's happening: - The MCP client connects to the Parallel endpoint - The agent uses GPT-5 to interpret user commands and perform Parallel operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent parallel_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[parallel_mcp], instructions=( "You are a Parallel assistant. Use Parallel tools to help users " "with their requests. Ask clarifying questions when needed." ), ) ``` ### 7. Build the chat interface What's happening: - The agent reads input from the terminal and streams its response - Parallel API calls happen automatically under the hood - The model keeps conversation history to maintain context across turns ```python # Simple REPL with message history history = [] print("Chat started! Type 'exit' or 'quit' to end.\n") print("Try asking the agent to help you with Parallel.\n") 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", flush=True) async with agent.run_stream(user_input, message_history=history) as stream_result: collected_text = "" async for chunk in stream_result.stream_output(): text_piece = None if isinstance(chunk, str): text_piece = chunk elif hasattr(chunk, "delta") and isinstance(chunk.delta, str): text_piece = chunk.delta elif hasattr(chunk, "text"): text_piece = chunk.text if text_piece: collected_text += text_piece result = stream_result print(f"Agent: {collected_text}\n") history = result.all_messages() ``` ### 8. Run the application What's happening: - The asyncio loop launches the agent and keeps it running until you exit ```python if __name__ == "__main__": asyncio.run(main()) ``` ## Complete Code ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from pydantic_ai import Agent from pydantic_ai.mcp import MCPServerStreamableHTTP load_dotenv() async def main(): api_key = os.getenv("COMPOSIO_API_KEY") user_id = os.getenv("USER_ID") if not api_key or not user_id: raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment") # Create a Composio Tool Router session for Parallel composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["parallel"], ) url = session.mcp.url if not url: raise ValueError("Composio session did not return an MCP URL") # Attach the MCP server to a Pydantic AI Agent parallel_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[parallel_mcp], instructions=( "You are a Parallel assistant. Use Parallel tools to help users " "with their requests. Ask clarifying questions when needed." ), ) # Simple REPL with message history history = [] print("Chat started! Type 'exit' or 'quit' to end.\n") print("Try asking the agent to help you with Parallel.\n") 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", flush=True) async with agent.run_stream(user_input, message_history=history) as stream_result: collected_text = "" async for chunk in stream_result.stream_output(): text_piece = None if isinstance(chunk, str): text_piece = chunk elif hasattr(chunk, "delta") and isinstance(chunk.delta, str): text_piece = chunk.delta elif hasattr(chunk, "text"): text_piece = chunk.text if text_piece: collected_text += text_piece result = stream_result print(f"Agent: {collected_text}\n") history = result.all_messages() if __name__ == "__main__": asyncio.run(main()) ``` ## Conclusion You've built a Pydantic AI agent that can interact with Parallel through Composio's Tool Router. With this setup, your agent can perform real Parallel actions through natural language. You can extend this further by: - Adding other toolkits like Gmail, HubSpot, or Salesforce - Building a web-based chat interface around this agent - Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Parallel for workflow automation) This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations. ## How to build Parallel MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/parallel/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/parallel/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/parallel/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/parallel/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/parallel/framework/codex) - [OpenClaw](https://composio.dev/toolkits/parallel/framework/openclaw) - [Hermes](https://composio.dev/toolkits/parallel/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/parallel/framework/cli) - [Google ADK](https://composio.dev/toolkits/parallel/framework/google-adk) - [LangChain](https://composio.dev/toolkits/parallel/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/parallel/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/parallel/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/parallel/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/parallel/framework/crew-ai) ## Related Toolkits - [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management. - [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters. - [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort. - [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. - [Agentql](https://composio.dev/toolkits/agentql) - Agentql is a toolkit that connects AI agents to the web using a specialized query language. It enables structured web interaction and data extraction for smarter automations. - [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions. - [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows. - [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations. - [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements. - [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints. - [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots. - [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches. - [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand. - [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance. - [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows. - [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses. - [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research. - [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction. - [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation. - [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Parallel MCP? With a standalone Parallel MCP server, the agents and LLMs can only access a fixed set of Parallel tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Parallel and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Pydantic AI? Yes, you can. Pydantic AI 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 Parallel tools. ### Can I manage the permissions and scopes for Parallel while using Tool Router? Yes, absolutely. You can configure which Parallel 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 Parallel data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)