How to Use the Meltwater MCP in LlamaIndex

Q: Can I use Meltwater saved searches to update my LlamaIndex vector store?

Yes. You can configure a pipeline that calls listsavedsearches and then runs getsearchdetails to fetch and index the latest matches. This keeps your knowledge base updated with fresh industry news.

Q: How does LlamaIndex handle large Meltwater payloads?

When searchcontent returns hundreds of articles, LlamaIndex's node parsers split the text into manageable chunks. This prevents your LLM context window from overflowing while preserving critical metadata.

Q: Can I filter Meltwater sources before indexing them in LlamaIndex?

Yes. Your agent can call listmediasources to identify active outlets, then apply those filters to subsequent search queries. This ensures only relevant, high-tier news sources enter your vector index.

Q: Where does my Meltwater search data go during LlamaIndex execution?

All data retrieved via getmentiondetails and search analytics passes straight through Vinkius's ephemeral sandbox to your local LlamaIndex instance. We do not cache, inspect, or store your media monitoring payloads.

Index live Meltwater media insights and search results directly into your LlamaIndex vector stores.

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 LlamaIndex

Create your Vinkius account to connect Meltwater to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live media insights for RAG

`get_media_insights` retrieves high-level performance metrics of news coverage to ground your RAG applications in real-time data. LlamaIndex ingestion pipelines convert these metrics into searchable nodes. This MCP Server eliminates hallucinations by forcing your agent to reference actual media metrics. You query your index and get answers backed by verified public relations data.

Query Meltwater search analytics with LlamaIndex

`get_search_analytics` pulls historical volume and sentiment trends directly into your semantic search index. Your LlamaIndex query engine matches user questions against these structured data points. Instead of reading raw JSON, your users ask conversational questions about media trends. The engine uses this MCP Server to fetch the analytics and summarize the shifts.

Build a dynamic knowledge base from exports

`list_content_exports` provides a list of downloadable media reports that your indexer can parse. LlamaIndex loads these files, splits the text, and updates your vector store automatically. You can also use `get_mention_details` to enrich specific nodes with deep metadata like author reach and source rank. This turns static media tracking into an interactive, updated repository.

Setup guide

Set up Meltwater MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Meltwater MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Meltwater tools.",
)
response = await agent.run("List recent Meltwater data")

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 LlamaIndex

LlamaIndex uses the MCP tool specification to turn Meltwater tools like `search_content` into queryable data loaders. The engine calls the tool, receives the text payload, and indexes it into your vector store.

Yes. You can configure a pipeline that calls `list_saved_searches` and then runs `get_search_details` to fetch and index the latest matches. This keeps your knowledge base updated with fresh industry news.

When `search_content` returns hundreds of articles, LlamaIndex's node parsers split the text into manageable chunks. This prevents your LLM context window from overflowing while preserving critical metadata.

Yes. Your agent can call `list_media_sources` to identify active outlets, then apply those filters to subsequent search queries. This ensures only relevant, high-tier news sources enter your vector index.

All data retrieved via `get_mention_details` and search analytics passes straight through Vinkius's ephemeral sandbox to your local LlamaIndex instance. We do not cache, inspect, or store your media monitoring payloads.

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