How to Use the AgentFire MCP in LlamaIndex

Q: How do I load AgentFire MCP tools into my LlamaIndex setup?

Install llama-index-tools-mcp and instantiate the client with your Vinkius HTTP URL. Pass it to McpToolSpec and call totoollistasync() to expose the endpoints.

Q: Can LlamaIndex search through my AgentFire leads?

You pull the records using listleads and index them into your vector store. After that, your query engine searches the embedded data just like any other document node.

Q: How do I ensure LlamaIndex pulls the latest AgentFire property details?

Write a script that routinely calls getlisting for active IDs and updates the corresponding nodes in your vector store. This keeps your RAG application grounded in current market reality.

Index live AgentFire property listings into your LlamaIndex knowledge base for grounded real estate RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentFire MCP to LlamaIndex

Create your Vinkius account to connect AgentFire 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 AgentFire with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorize active real estate inventory

The `list_listings` tool pulls your entire brokerage property catalog into the LlamaIndex environment. You configure your data ingestion script to fetch these records on a schedule and convert the raw JSON into searchable document nodes. Query engines then search this indexed data alongside your static PDF market reports. When a user asks about available three-bedroom homes, the system retrieves exactly matching nodes grounded in live API data rather than hallucinating outdated properties.

Embed your AgentFire profile into RAG queries via MCP Server

The `get_profile` tool injects your specific agent details, contact info, and branding guidelines straight into the query context. RAG applications use this metadata to format responses that sound exactly like you and include your direct phone number. By indexing this profile information alongside property data, your agent answers questions about your specific expertise. It knows your service areas and transaction history because that data lives inside the vectorized knowledge base.

Ground user interactions in historical contact data

The `list_contacts` tool retrieves your existing client roster so LlamaIndex can cross-reference incoming queries against known entities. If an email address matches an existing record, the system pulls their historical interactions before generating a response. This MCP integration prevents duplicate data entry and provides rich context for the LLM. The agent tailors its tone based on whether the user is a first-time inquirer or a long-term investor found in your database.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate the client with your Vinkius HTTP URL. Pass it to `McpToolSpec` and call `to_tool_list_async()` to expose the endpoints.

You pull the records using `list_leads` and index them into your vector store. After that, your query engine searches the embedded data just like any other document node.

Yes. You restrict the function agent to specific operations, like only allowing `search_listings` while blocking `create_lead` for read-only user sessions.

Write a script that routinely calls `get_listing` for active IDs and updates the corresponding nodes in your vector store. This keeps your RAG application grounded in current market reality.

Your client names and email addresses never persist on our infrastructure. The V8 Isolate sandbox handles the authentication, executes the API request, and immediately wipes the memory space clean.

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