How to Use the Covalent MCP in OpenAI Agents SDK

Q: How do specialized agents handle multi-chain data?

Your router agent uses listsupportedchains to identify where a token lives, then hands the task to a regional agent. This regional agent calls getdexpools to analyze liquidity on that specific network.

Build production-ready OpenAI Agents SDK systems that query live multi-chain data with native guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Covalent MCP to OpenAI Agents SDK

Create your Vinkius account to connect Covalent to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Covalent with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Chain Queries with OpenAI Agents SDK

`get_token_balances` pulls live wallet balances directly into your OpenAI Agents SDK runtime for immediate validation. This tool prevents your agent from hallucinating balances or contract addresses during execution. If a balance check fails your custom guardrail, the SDK intercepts execution before triggering on-chain steps. Your agent then uses `get_chains_status` to check network latency before it tries again.

Handoff Portfolio Analysis to Specialized Agents

`get_historical_portfolio` allows your primary router to hand off historical valuation tasks to a dedicated financial analysis agent. This setup runs on our managed MCP Server infrastructure to keep your OpenAI Agents SDK system fast and highly focused. The specialized agent parses the USD valuation history and passes the clean data back to the supervisor. You can trace this entire handoff and tool execution path directly inside your OpenAI developer dashboard.

Audit Smart Contracts via Decoded Event Logs

`get_transaction_details` extracts raw log events and decoded parameters directly into your agent's context window. Your OpenAI Agents SDK setup uses this MCP tool to analyze smart contract behavior without parsing raw hex values manually. When debugging complex transactions, the agent calls `get_token_transfers` to map the exact movement of assets. This provides your safety guardrails with the precise data needed to approve or halt automated workflows.

Setup guide

Set up Covalent MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Covalent tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Covalent tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Covalent tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Covalent Agent",
            instructions="You have access to Covalent tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Covalent. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Covalent now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Covalent MCP in OpenAI Agents SDK

Install the library and connect using our managed MCP endpoint. Pass this instance in the `mcp_servers` list when initializing your agent. The SDK auto-discovers all ten tools like `get_token_balances` instantly.

Yes, you can write validation logic that checks the output of tools like `get_transaction_details` before the agent proceeds. If the retrieved gas metrics exceed your threshold, the SDK halts execution.

Yes, you can cache tools locally. This prevents redundant schema lookups when your agent repeatedly calls `get_chains_status` across different sessions. It keeps agent response times under a second.

Your router agent uses `list_supported_chains` to identify where a token lives, then hands the task to a regional agent. This regional agent calls `get_dex_pools` to analyze liquidity on that specific network.

Vinkius runs the Covalent integration in a zero-trust, ephemeral V8 isolate sandbox. Your wallet addresses and transaction hashes are never logged or stored on our servers. Every request executes in memory and vanishes immediately after completion.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript