# How to integrate Perplexityai MCP with Mastra AI ```json { "title": "How to integrate Perplexityai MCP with Mastra AI", "toolkit": "Perplexityai", "toolkit_slug": "perplexityai", "framework": "Mastra AI", "framework_slug": "mastra-ai", "url": "https://composio.dev/toolkits/perplexityai/framework/mastra-ai", "markdown_url": "https://composio.dev/toolkits/perplexityai/framework/mastra-ai.md", "updated_at": "2026-05-12T10:21:48.578Z" } ``` ## Introduction This guide walks you through connecting Perplexityai to Mastra AI using the Composio tool router. By the end, you'll have a working Perplexityai agent that can summarize the latest ai research papers, generate a creative story about space travel, explain quantum computing in simple terms through natural language commands. This guide will help you understand how to give your Mastra AI agent real control over a Perplexityai account through Composio's Perplexityai MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Perplexityai with - [ChatGPT](https://composio.dev/toolkits/perplexityai/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/perplexityai/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/perplexityai/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/perplexityai/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/perplexityai/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/perplexityai/framework/codex) - [Cursor](https://composio.dev/toolkits/perplexityai/framework/cursor) - [VS Code](https://composio.dev/toolkits/perplexityai/framework/vscode) - [OpenCode](https://composio.dev/toolkits/perplexityai/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/perplexityai/framework/openclaw) - [Hermes](https://composio.dev/toolkits/perplexityai/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/perplexityai/framework/cli) - [Google ADK](https://composio.dev/toolkits/perplexityai/framework/google-adk) - [LangChain](https://composio.dev/toolkits/perplexityai/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/perplexityai/framework/ai-sdk) - [LlamaIndex](https://composio.dev/toolkits/perplexityai/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/perplexityai/framework/crew-ai) ## TL;DR Here's what you'll learn: - Set up your environment so Mastra, OpenAI, and Composio work together - Create a Tool Router session in Composio that exposes Perplexityai tools - Connect Mastra's MCP client to the Composio generated MCP URL - Fetch Perplexityai tool definitions and attach them as a toolset - Build a Mastra agent that can reason, call tools, and return structured results - Run an interactive CLI where you can chat with your Perplexityai agent ## What is Mastra AI? Mastra AI is a TypeScript framework for building AI agents with tool support. It provides a clean API for creating agents that can use external services through MCP. Key features include: - MCP Client: Built-in support for Model Context Protocol servers - Toolsets: Organize tools into logical groups - Step Callbacks: Monitor and debug agent execution - OpenAI Integration: Works with OpenAI models via @ai-sdk/openai ## What is the Perplexityai MCP server, and what's possible with it? The Perplexityai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Perplexity AI account. It provides structured and secure access to Perplexity's conversational AI models, so your agent can perform actions like running search queries, generating detailed answers, summarizing content, and retrieving citations automatically. - Conversational AI search and Q&A: Let your agent ask questions or search a wide range of topics, returning clear, human-like answers from Perplexity's advanced models. - Contextual and multi-turn queries: Enable your agent to conduct follow-up questions and maintain context for more in-depth, accurate answers. - Model selection and fine-tuning: Allow your agent to choose between different Perplexity AI models and adjust parameters like temperature, top-k, and top-p for tailored responses. - Source citations and image retrieval: Have your agent fetch answers with source citations and relevant images, providing richer, more trustworthy outputs. - Auto-prompting and query refinement: Let your agent automatically enhance and refine user queries for better, more relevant search results. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `PERPLEXITYAI_CREATE_ASYNC_CHAT_COMPLETION` | Create Async Chat Completion | Create Async Chat Completion (POST /v1/async/sonar). Submits an asynchronous chat completion request for long-running tasks. Returns immediately with a request ID that can be polled using the Get Async Chat Completion action. Only the 'sonar-deep-research' model is supported for async processing. Async jobs have a 7-day TTL. Deep research generates very long responses (10K-100K+ words) with exhaustive multi-source analysis. Use the idempotency_key to prevent duplicate submissions. Poll with Get Async Chat Completion using the returned request ID to retrieve results when status is COMPLETED. | | `PERPLEXITYAI_CREATE_CHAT_COMPLETION` | Create Chat Completion | Perplexity Sonar Chat Completions (POST /v1/sonar). Generates web-grounded conversational AI responses with citations. Supports multiple Sonar models optimized for different use cases: - sonar: Fast, cost-effective for simple queries - sonar-pro: Enhanced quality for complex questions - sonar-reasoning-pro: Chain-of-thought reasoning with blocks - sonar-deep-research: Exhaustive multi-source research (generates very long responses, 10K+ words; prefer the async endpoint for this model) Features: web search grounding, citations, images, structured JSON output, search filtering by domain/date/language/recency, and streaming. Important constraints: - search_recency_filter and date filters (search_after_date_filter, search_before_date_filter, etc.) are mutually exclusive. Use one or the other, not both. - Messages with the 'tool' role must alternate with 'assistant' messages. A valid pattern is: system -> user -> assistant -> tool -> user. - The 'stop' parameter is not currently supported by the API. | | `PERPLEXITYAI_CREATE_CONTEXTUALIZED_EMBEDDINGS` | Create Contextualized Embeddings | Create Contextualized Embeddings (POST /v1/contextualizedembeddings). Generates document-aware embeddings where chunks from the same document share context. Unlike standard embeddings, these recognize sequential relationships within documents, improving retrieval quality. Models: pplx-embed-context-v1-0.6b (1024 dims) and pplx-embed-context-v1-4b (2560 dims). Both support Matryoshka dimension reduction and INT8/binary quantization. | | `PERPLEXITYAI_CREATE_EMBEDDINGS` | CreateEmbeddings | Generate vector embeddings for independent texts (queries, sentences, documents). This action takes one or more input texts and generates vector embeddings using Perplexity AI's embedding models. Embeddings are useful for semantic search, similarity matching, and machine learning downstream tasks. Supported models: - pplx-embed-v1-0.6b: Smaller, faster model (1024 dimensions) - pplx-embed-v1-4b: Larger, more accurate model (2560 dimensions) The output embeddings are base64-encoded for efficient transmission. Use the dimensions parameter to reduce embedding size for faster processing when full precision is not required (Matryoshka representation). | | `PERPLEXITYAI_EXECUTE_AGENT` | Execute Agent | Create Agent Response (POST /v1/agent). Orchestrates multi-step agentic workflows with built-in tools (web search, URL fetching, function calling), reasoning, and multi-model support. Streaming is not supported by this action. At least one of 'model', 'models', or 'preset' must be provided. Available presets: 'fast-search', 'pro-search', 'deep-research'. The 'deep-research' preset generates very long responses (10K-100K+ words) with exhaustive multi-source analysis. Available models include Perplexity Sonar, OpenAI, Anthropic, Google, xAI, and NVIDIA models at direct provider rates. Use the List Models action to see available model identifiers. | | `PERPLEXITYAI_GET_ASYNC_CHAT_COMPLETION` | Get Async Chat Completion | Get Async Chat Completion (GET /v1/async/sonar/{id}). Retrieves the result of an asynchronous chat completion request by its ID. Use this to poll for the result after creating an async job. The response includes the status and, when completed, the full completion. | | `PERPLEXITYAI_LIST_ASYNC_CHAT_COMPLETIONS` | List Async Chat Completions | List Async Chat Completions (GET /v1/async/sonar). Retrieves a list of all asynchronous chat completion requests for the authenticated user. Use this to see the status of all your pending, completed, and failed async jobs. | | `PERPLEXITYAI_LIST_MODELS` | List Models | List Models (GET /v1/models). Lists models available for the Agent API. Returns model identifiers that can be used with the Agent endpoint. The response follows the OpenAI List Models format for compatibility. This is a public endpoint that does not require authentication. | | `PERPLEXITYAI_SEARCH` | Perplexity Search (Raw Results) | Search the Web (POST /search). Returns raw, ranked web search results directly from Perplexity's index without LLM processing. Faster and cheaper than chat completions when you need raw results. Supports filtering by domain, date, language, country, and recency. Max 20 results per request. Important: search_recency_filter and date filters (search_after_date_filter, search_before_date_filter, last_updated_after_filter, last_updated_before_filter) are mutually exclusive. Use one or the other, not both. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Perplexityai MCP server is an implementation of the Model Context Protocol that connects your AI agent to Perplexityai. It provides structured and secure access so your agent can perform Perplexityai 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: - Node.js 18 or higher - A Composio account with an active API key - An OpenAI API key - Basic familiarity with TypeScript ### 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 need credits or a connected billing setup to use the models. - Store the key somewhere safe. Composio API Key - Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Go to Settings and copy your API key. - This key lets your Mastra agent talk to Composio and reach Perplexityai through MCP. ### 2. Install dependencies Install the required packages. What's happening: - @composio/core is the Composio SDK for creating MCP sessions - @mastra/core provides the Agent class - @mastra/mcp is Mastra's MCP client - @ai-sdk/openai is the model wrapper for OpenAI - dotenv loads environment variables from .env ```bash npm install @composio/core @mastra/core @mastra/mcp @ai-sdk/openai 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 - COMPOSIO_USER_ID tells Composio which user this session belongs to - OPENAI_API_KEY lets the Mastra agent call OpenAI models ```bash COMPOSIO_API_KEY=your_composio_api_key_here COMPOSIO_USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key_here ``` ### 4. Import libraries and validate environment What's happening: - dotenv/config auto loads your .env so process.env.* is available - openai gives you a Mastra compatible model wrapper - Agent is the Mastra agent that will call tools and produce answers - MCPClient connects Mastra to your Composio MCP server - Composio is used to create a Tool Router session ```typescript import "dotenv/config"; import { openai } from "@ai-sdk/openai"; import { Agent } from "@mastra/core/agent"; import { MCPClient } from "@mastra/mcp"; import { Composio } from "@composio/core"; import * as readline from "readline"; import type { AiMessageType } from "@mastra/core/agent"; const openaiAPIKey = process.env.OPENAI_API_KEY; const composioAPIKey = process.env.COMPOSIO_API_KEY; const composioUserID = process.env.COMPOSIO_USER_ID; if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set"); if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set"); if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set"); const composio = new Composio({ apiKey: composioAPIKey as string, }); ``` ### 5. Create a Tool Router session for Perplexityai What's happening: - create spins up a short-lived MCP HTTP endpoint for this user - The toolkits array contains "perplexityai" for Perplexityai access - session.mcp.url is the MCP URL that Mastra's MCPClient will connect to ```typescript async function main() { const session = await composio.create( composioUserID as string, { toolkits: ["perplexityai"], }, ); const composioMCPUrl = session.mcp.url; console.log("Perplexityai MCP URL:", composioMCPUrl); ``` ### 6. Configure Mastra MCP client and fetch tools What's happening: - MCPClient takes an id for this client and a list of MCP servers - The headers property includes the x-api-key for authentication - getTools fetches the tool definitions exposed by the Perplexityai toolkit ```typescript const mcpClient = new MCPClient({ id: composioUserID as string, servers: { nasdaq: { url: new URL(composioMCPUrl), requestInit: { headers: session.mcp.headers, }, }, }, timeout: 30_000, }); console.log("Fetching MCP tools from Composio..."); const composioTools = await mcpClient.getTools(); console.log("Number of tools:", Object.keys(composioTools).length); ``` ### 7. Create the Mastra agent What's happening: - Agent is the core Mastra agent - name is just an identifier for logging and debugging - instructions guide the agent to use tools instead of only answering in natural language - model uses openai("gpt-5") to configure the underlying LLM ```typescript const agent = new Agent({ name: "perplexityai-mastra-agent", instructions: "You are an AI agent with Perplexityai tools via Composio.", model: "openai/gpt-5", }); ``` ### 8. Set up interactive chat interface What's happening: - messages keeps the full conversation history in Mastra's expected format - agent.generate runs the agent with conversation history and Perplexityai toolsets - maxSteps limits how many tool calls the agent can take in a single run - onStepFinish is a hook that prints intermediate steps for debugging ```typescript let messages: AiMessageType[] = []; console.log("Chat started! Type 'exit' or 'quit' to end.\n"); const rl = readline.createInterface({ input: process.stdin, output: process.stdout, prompt: "> ", }); 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; } messages.push({ id: crypto.randomUUID(), role: "user", content: trimmedInput, }); console.log("\nAgent is thinking...\n"); try { const response = await agent.generate(messages, { toolsets: { perplexityai: composioTools, }, maxSteps: 8, }); const { text } = response; if (text && text.trim().length > 0) { console.log(`Agent: ${text}\n`); messages.push({ id: crypto.randomUUID(), role: "assistant", content: text, }); } } catch (error) { console.error("\nError:", error); } rl.prompt(); }); rl.on("close", async () => { console.log("\nSession ended."); await mcpClient.disconnect(); process.exit(0); }); } main().catch((err) => { console.error("Fatal error:", err); process.exit(1); }); ``` ## Complete Code ```typescript import "dotenv/config"; import { openai } from "@ai-sdk/openai"; import { Agent } from "@mastra/core/agent"; import { MCPClient } from "@mastra/mcp"; import { Composio } from "@composio/core"; import * as readline from "readline"; import type { AiMessageType } from "@mastra/core/agent"; const openaiAPIKey = process.env.OPENAI_API_KEY; const composioAPIKey = process.env.COMPOSIO_API_KEY; const composioUserID = process.env.COMPOSIO_USER_ID; if (!openaiAPIKey) throw new Error("OPENAI_API_KEY is not set"); if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set"); if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set"); const composio = new Composio({ apiKey: composioAPIKey as string }); async function main() { const session = await composio.create(composioUserID as string, { toolkits: ["perplexityai"], }); const composioMCPUrl = session.mcp.url; const mcpClient = new MCPClient({ id: composioUserID as string, servers: { perplexityai: { url: new URL(composioMCPUrl), requestInit: { headers: session.mcp.headers, }, }, }, timeout: 30_000, }); const composioTools = await mcpClient.getTools(); const agent = new Agent({ name: "perplexityai-mastra-agent", instructions: "You are an AI agent with Perplexityai tools via Composio.", model: "openai/gpt-5", }); let messages: AiMessageType[] = []; const rl = readline.createInterface({ input: process.stdin, output: process.stdout, prompt: "> ", }); rl.prompt(); rl.on("line", async (input: string) => { const trimmed = input.trim(); if (["exit", "quit"].includes(trimmed.toLowerCase())) { rl.close(); return; } messages.push({ id: crypto.randomUUID(), role: "user", content: trimmed }); const { text } = await agent.generate(messages, { toolsets: { perplexityai: composioTools }, maxSteps: 8, }); if (text) { console.log(`Agent: ${text}\n`); messages.push({ id: crypto.randomUUID(), role: "assistant", content: text }); } rl.prompt(); }); rl.on("close", async () => { await mcpClient.disconnect(); process.exit(0); }); } main(); ``` ## Conclusion You've built a Mastra AI agent that can interact with Perplexityai through Composio's Tool Router. You can extend this further by: - Adding other toolkits like Gmail, Slack, or GitHub - Building a web-based chat interface around this agent - Using multiple MCP endpoints to enable cross-app workflows ## How to build Perplexityai MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/perplexityai/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/perplexityai/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/perplexityai/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/perplexityai/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/perplexityai/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/perplexityai/framework/codex) - [Cursor](https://composio.dev/toolkits/perplexityai/framework/cursor) - [VS Code](https://composio.dev/toolkits/perplexityai/framework/vscode) - [OpenCode](https://composio.dev/toolkits/perplexityai/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/perplexityai/framework/openclaw) - [Hermes](https://composio.dev/toolkits/perplexityai/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/perplexityai/framework/cli) - [Google ADK](https://composio.dev/toolkits/perplexityai/framework/google-adk) - [LangChain](https://composio.dev/toolkits/perplexityai/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/perplexityai/framework/ai-sdk) - [LlamaIndex](https://composio.dev/toolkits/perplexityai/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/perplexityai/framework/crew-ai) ## Related Toolkits - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service. - [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow. - [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows. - [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application. - [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities. - [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization. - [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications. - [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations. - [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key. - [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient. - [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions. - [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences. - [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement. - [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team. - [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs. - [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code. - [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets. - [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features. - [DeepImage](https://composio.dev/toolkits/deepimage) - DeepImage is an AI-powered image enhancer and upscaler. Get higher-quality images with just a few clicks. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Perplexityai MCP? With a standalone Perplexityai MCP server, the agents and LLMs can only access a fixed set of Perplexityai tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Perplexityai and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Mastra AI? Yes, you can. Mastra 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 Perplexityai tools. ### Can I manage the permissions and scopes for Perplexityai while using Tool Router? Yes, absolutely. You can configure which Perplexityai 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 Perplexityai data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)