How to Use the Meltwater MCP in OpenAI Agents SDK

Q: Can I trace Meltwater search queries inside the OpenAI Agents SDK dashboard?

Yes, every tool call is traced. When your agent invokes getsearchanalytics or getmentiondetails, the exact input parameters and JSON payloads show up in your OpenAI run logs, making debugging incredibly straightforward.

Q: How do I register the Meltwater MCP Server with my OpenAI Agents SDK pipeline?

You initialize the server using MCPServerStreamableHttp with your Vinkius endpoint. Then, pass that server instance into the Agent constructor's mcpservers list, enabling automatic tool discovery.

Q: Can I use multiple specialized agents to process Meltwater data?

Absolutely. You can have a triage agent run listtags to organize media sources, and then hand off the actual analysis of those sources to a specialized PR agent using the SDK's native handoff features.

Monitor news and social mentions directly inside your OpenAI Agents SDK production workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Meltwater MCP to OpenAI Agents SDK

Create your Vinkius account to connect Meltwater 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 Meltwater with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Media Intelligence with OpenAI Agents SDK

By using `search_content` and `get_search_analytics`, your Python agents can run live media tracking without worrying about API limits. This MCP Server lets your Python agents query Meltwater's index and pull deep analytics while keeping execution safe. The SDK's built-in guardrails validate every query parameter before your agent triggers the call, saving your API quota from bad syntax. If a search yields too many results, you can programmatically hand off the task to a specialized analysis agent. This setup uses `get_search_details` to inspect the parameters of saved queries, ensuring that only highly filtered, relevant media data enters your LLM context window.

Automated Mention Triage and Handoffs

The `get_mention_details` tool lets your agent inspect specific hits and determine brand sentiment automatically. Because the SDK manages agent handoffs natively, a monitoring agent can instantly pass critical mentions to a PR specialist agent. To keep these operations organized, the agent can fetch folders using `list_folders` to categorize incoming alerts. This prevents your main run loop from getting bogged down with raw data processing, keeping your production agents focused on high-level decision making.

Bulk Export Management with Full Tracing

Retrieving raw CSVs becomes trivial when your agent runs `list_content_exports` to find ready-to-process data dumps. Every step of this process is fully traced on the OpenAI dashboard, giving you complete visibility into when and why your agent requested an export. By using `list_saved_searches` alongside these exports, your agent can match raw files back to their original search criteria. It's a clean, traceable way to handle massive media datasets without writing brittle cron jobs.

Setup guide

Set up Meltwater 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 Meltwater tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Meltwater 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="Meltwater Agent",
            instructions="You have access to Meltwater 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 Meltwater. 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 Meltwater 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 Meltwater MCP in OpenAI Agents SDK

The SDK uses built-in guardrails to validate tool arguments before they hit the Meltwater API. If your agent tries to run an overly broad query using `search_content`, the guardrail catches it early, preventing useless requests that drain your API quota.

Yes, every tool call is traced. When your agent invokes `get_search_analytics` or `get_mention_details`, the exact input parameters and JSON payloads show up in your OpenAI run logs, making debugging incredibly straightforward.

You initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint. Then, pass that server instance into the `Agent` constructor's `mcp_servers` list, enabling automatic tool discovery.

Absolutely. You can have a triage agent run `list_tags` to organize media sources, and then hand off the actual analysis of those sources to a specialized PR agent using the SDK's native handoff features.

Your proprietary search strings and media intelligence queries are never stored. The Vinkius runtime executes the MCP Server in an ephemeral V8 sandbox, passing your Meltwater API credentials directly to their endpoints through a secure, isolated channel.

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