How to Use the Mention MCP in LlamaIndex

Q: Can LlamaIndex update vector stores using Mention searchmentionsbykeyword?

Yes. Your agent can run searchmentionsbykeyword on a schedule, parse the returned text into documents, and upsert them into your vector store to keep your knowledge base fresh.

Q: How does LlamaIndex use Mention's getalertstatistics to optimize queries?

Your agent can call getalertstatistics to check reach metrics first. It can then prioritize indexing mentions from alerts that have the highest volume or reach, saving vector storage space.

Index live web alerts into LlamaIndex vector stores to ground your RAG applications in real-time brand data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mention MCP to LlamaIndex

Create your Vinkius account to connect Mention 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 Mention with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Web Mentions for Grounded RAG

The `list_recent_mentions` tool pulls live social and web data directly into your LlamaIndex data ingestion pipeline. Your agent uses this MCP tool to load these documents, turning raw web text into node objects that are immediately indexed in your vector database. By calling `get_mention_content` for specific high-impact posts, your pipeline ensures that your semantic search index always contains up-to-date brand discussions. This prevents your LLM from hallucinating facts when answering questions about current public sentiment.

Manage Active Alerts via LlamaIndex MCP Server

The `list_monitoring_alerts` tool gives your index agent a clear view of your active brand tracking parameters. The agent inspects this list to determine if your current knowledge base covers all necessary market segments or if new sources are required. If a gap is found, the agent executes `create_monitoring_alert` to add new search terms. It then removes stale configurations using `remove_monitoring_alert` to keep your vector database focused on relevant, high-priority topics.

Run Semantic Queries on Keyword Hits

The `search_mentions_by_keyword` tool queries your active monitoring feeds for specific terms. Your LlamaIndex agent uses this to isolate critical discussions, feeding the raw text directly into your query engine to resolve user questions. To keep track of what has been indexed, the agent runs `mark_mention_as_read` on processed items. This metadata is saved alongside the vectorized text, allowing you to filter your vector index by read status during subsequent retrieval steps.

Setup guide

Set up Mention 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 Mention 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 Mention tools.",
)
response = await agent.run("List recent Mention 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 Mention. 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 Mention 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 Mention MCP in LlamaIndex

Install the MCP tool spec package, initialize the basic client with your Vinkius URL, and call `to_tool_list_async()`. Pass those tools to your FunctionAgent to let it query web data.

Yes. Your agent can run `search_mentions_by_keyword` on a schedule, parse the returned text into documents, and upsert them into your vector store to keep your knowledge base fresh.

Your agent can call `get_alert_statistics` to check reach metrics first. It can then prioritize indexing mentions from alerts that have the highest volume or reach, saving vector storage space.

No. Vinkius handles the API authentication for you. Your LlamaIndex code only needs a single endpoint token to securely access all 12 tools on this server.

All alert settings, search keywords, and webhook configurations remain on the target platform. The MCP Server only acts as a secure transit layer, processing your queries inside a sandboxed environment that deletes data upon execution.

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