How to integrate Rkvst MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Rkvst Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Rkvst to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Rkvst agent that can download attachment from latest asset event, show details of asset by uuid, retrieve metadata for a specific event, get public asset event information through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Rkvst account through Composio's Rkvst MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Rkvst
  • Configure an AI agent that can use Rkvst as a tool
  • Run a live chat session where you can ask the agent to perform Rkvst operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Rkvst MCP server, and what's possible with it?

The Rkvst MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Rkvst account. It provides structured and secure access to your supply chain evidence data, so your agent can perform actions like retrieving asset details, verifying event authenticity, downloading attachments, and managing chain of custody records on your behalf.

  • Asset and event retrieval: Instantly fetch detailed information about assets, events, or public assets by their unique identifiers, including historical state data.
  • Chain of custody verification: Have your agent review event metadata and associated trails to ensure data authenticity and transparency throughout your supply chain.
  • Download evidence attachments: Let your agent securely download raw binary attachments associated with supply chain events for auditing or record-keeping.
  • App and member inspection: Effortlessly pull configuration and credential details for app registrations or retrieve member and IAM subject information to monitor access and permissions.
  • Tenancy and blob management: Retrieve tenancy details or access specific data blobs related to your supply chain records for better oversight and control.

Supported Tools & Triggers

Tools
Download Event AttachmentTool to download an attachment from a specified event on an asset.
Get App RegistrationTool to retrieve details for a given app registration id.
Get AssetTool to retrieve details for a given asset.
Get BlobTool to retrieve details of a blob by id.
Get EventTool to retrieve details of a specified event.
Get IAM SubjectTool to retrieve iam subject details.
Get MemberTool to retrieve details for a given member id.
Get Public AssetTool to retrieve details for a public asset.
Get Public Asset EventTool to retrieve a specific public asset event.
Get TenancyTool to retrieve details for a specific tenancy.
List App RegistrationsTool to list all app registrations.
List Asset EventsTool to list events for a specified asset.
List AssetsTool to list all assets with optional pagination and filters.
List IAM SubjectsTool to list iam subjects.
List MembersTool to list all tenant members.
List Public Asset EventsTool to list events for a specific public asset.
List Public AssetsTool to list all public assets.
List TenanciesTool to list all tenancies.
Promote MemberTool to promote a tenant member to owner role.
Retrieve asset attachment metadataTool to retrieve metadata for an attachment on a specified asset.
Retrieve CapsTool to retrieve resource limit quotas for a specified service.
Retrieve Event Attachment MetadataTool to retrieve metadata for an attachment on a specified event.
Retrieve Public Asset Attachment MetadataTool to retrieve metadata for an attachment on a specified public asset.
Retrieve Public Event Attachment MetadataTool to retrieve metadata for an attachment on a public asset event.
Search EventsTool to search events matching filter criteria with pagination.
Update App RegistrationTool to update an application's display name or custom claims.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Rkvst project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard 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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Rkvst.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Rkvst Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["rkvst"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only rkvst.
  • The router checks the user's Rkvst connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Rkvst.
  • This approach keeps things lightweight and lets the agent request Rkvst tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Rkvst. "
        "Help users perform Rkvst operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Rkvst and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Rkvst operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Rkvst.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Rkvst and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["rkvst"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Rkvst. "
        "Help users perform Rkvst operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Rkvst MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Rkvst.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Rkvst MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Rkvst MCP with Claude Agent SDK

Google ADK

Google ADK

Use Rkvst MCP with Google ADK

LangChain

LangChain

Use Rkvst MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Rkvst MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Rkvst MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Rkvst MCP with LlamaIndex

CrewAI

CrewAI

Use Rkvst MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Rkvst MCP?

With a standalone Rkvst MCP server, the agents and LLMs can only access a fixed set of Rkvst tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Rkvst and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Rkvst tools.

Can I manage the permissions and scopes for Rkvst while using Tool Router?

Yes, absolutely. You can configure which Rkvst 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 Rkvst data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free