How to Use the Guerrilla Marketing MCP in LlamaIndex

Index zero-budget guerrilla plays into LlamaIndex using our managed MCP Server to verify risk-checked marketing tactics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Guerrilla Marketing MCP to LlamaIndex

Create your Vinkius account to connect Guerrilla Marketing 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 Guerrilla Marketing with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index verified guerrilla tactics in LlamaIndex

The `validate_guerrilla_tactic` tool integrates with LlamaIndex to turn raw marketing ideas into structured, risk-checked documents that you can index immediately. This MCP Server prevents your RAG pipeline from retrieving unverified or expensive campaigns during future queries. When your agent runs this tool, the resulting zero-budget validation metrics are written directly to your vector store as metadata. This allows your LlamaIndex query engine to filter future marketing ideas based on their verified attribution paths.

Query past ambush points semantically

The `validate_guerrilla_tactic` tool analyzes where your audience is off-guard, and LlamaIndex indexes these temporal insights for future semantic search. Instead of guessing when to launch a new stunt, you can query your index to find previously validated timing windows. This setup feeds live API validation data directly into your knowledge base. Your LlamaIndex agent can retrieve successful guerrilla patterns and adapt them to new product launches without starting from scratch.

Prevent hallucinations with grounded risk data

The `validate_guerrilla_tactic` tool provides cold, hard risk metrics that ground your LlamaIndex agent in reality, preventing it from inventing impossible viral loops. By feeding the tool's strict risk scores into your index, you ensure your RAG application only recommends compliant plays. Your query engine compares new campaign proposals against this index of flagged risks. If an agent proposes a high-liability stunt, LlamaIndex uses the indexed data to reject the idea instantly.

Setup guide

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

You initialize the McpToolSpec with your Vinkius credentials and register it with your agent. The output from your validation runs can then be parsed and loaded directly into any document index.

Yes, by storing the results of past validation checks in your vector database, your LlamaIndex query engine can retrieve past scores to guide the generation of new zero-cost campaigns.

Absolutely, you can configure a sub-question engine to split a complex campaign into smaller pieces, running each piece through the validation tool to check for hidden costs.

The validation engine inspects your campaign parameters for hidden ad buys or platform fees. It blocks any proposal that requires a budget, forcing your pipeline to rely strictly on organic loops.

The server only processes the text of your proposed guerrilla tactics and risk profiles. This data is handled in an isolated, ephemeral sandbox on Vinkius, ensuring your proprietary marketing hooks never leak into public vector indexes.

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