How to Use the AgentFire MCP in LangChain

Q: How do I connect LangChain to the AgentFire MCP server?

Install langchain-mcp-adapters. Then initialize MultiServerMCPClient with your Vinkius HTTP endpoint and pass the resulting tools to your ReAct agent.

Q: Can LangChain trace token usage for AgentFire tool calls?

Yes. Every time your agent hits searchlistings or createlead, LangSmith logs the exact input payload, the API response, and the token consumption for that specific step.

Q: What happens if the AgentFire API goes down during a LangChain run?

Your agent can call checkagentfirestatus before executing heavy operations. If the check fails, you configure the chain to return a fallback response instead of crashing.

Q: How do I manage multiple brokerage accounts in LangChain with AgentFire?

Use the client.session() method to maintain persistent context for different users. Each session routes requests to the correct Vinkius endpoint token for that specific brokerage.

Build multi-step real estate pipelines by connecting AgentFire listings and leads directly into your LangChain agents via this MCP Server.

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 LangChain

Create your Vinkius account to connect AgentFire to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain AgentFire lead capture into LangChain workflows

The `create_lead` tool captures incoming buyer inquiries directly from your ReAct agent's conversation. You pass the required email address and any contextual notes the agent extracted during the chat, immediately generating a new record in your CRM. Because this runs inside a LangChain pipeline, you link that creation step to follow-up actions. The agent grabs the new lead ID, triggers an external email sequence, and logs the entire interaction path in LangSmith to track token usage and latency.

Feed live property data to ReAct agents via MCP Server

The `search_listings` tool lets your agent query active real estate inventory based on user parameters like price or location. Instead of relying on stale vector databases, the agent pulls fresh market data straight from your brokerage platform. Once the results hit your chain, the agent parses the payload using `get_listing` to extract specific property details. It then formats those specifics into a structured comparison table before passing the final output to the user.

Update buyer profiles automatically during chat

The `update_lead` tool modifies existing client records when your agent uncovers new preferences during a conversation. This MCP integration means if a buyer mentions they need an extra bedroom, the agent pushes that specific field change without overwriting the rest of the profile. You verify these modifications by calling `get_lead` immediately after the update. This verification step ensures the chain only proceeds to the next stage if the brokerage database successfully registered the modified criteria.

Setup guide

Set up AgentFire MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes AgentFire tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "agentfire-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent AgentFire transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters`. Then initialize `MultiServerMCPClient` with your Vinkius HTTP endpoint and pass the resulting tools to your ReAct agent.

Yes. Every time your agent hits `search_listings` or `create_lead`, LangSmith logs the exact input payload, the API response, and the token consumption for that specific step.

Your agent can call `check_agentfire_status` before executing heavy operations. If the check fails, you configure the chain to return a fallback response instead of crashing.

Use the `client.session()` method to maintain persistent context for different users. Each session routes requests to the correct Vinkius endpoint token for that specific brokerage.

No. Your real estate leads and property details process inside an ephemeral V8 Isolate sandbox. The execution environment destroys itself immediately after the MCP tool call finishes, leaving no stored data behind.

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