AVENAINTEGRATE

Integrate Avena Terminal

Copy-paste configs to connect Avena Terminal's property data to your AI tool. 7 tools, 1,881 scored properties, live data. No API key. No auth. Just connect.

Endpoint: https://avenaterminal.com/mcp · Transport: Streamable HTTP · Auth: None

🟣

Claude Desktop

AI Assistant

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "avena-terminal": {
      "url": "https://avenaterminal.com/mcp"
    }
  }
}
File: claude_desktop_config.jsonPath: ~/Library/Application Support/Claude/ (Mac) or %APPDATA%/Claude/ (Windows)
⚡

Cursor

AI Code Editor

Add to your .cursor/mcp.json:

{
  "mcpServers": {
    "avena-terminal": {
      "url": "https://avenaterminal.com/mcp",
      "transport": "http"
    }
  }
}
File: .cursor/mcp.jsonPath: Project root or ~/.cursor/
🏄

Windsurf

AI Code Editor

Add to your mcp_config.json:

{
  "mcpServers": {
    "avena-terminal": {
      "serverUrl": "https://avenaterminal.com/mcp"
    }
  }
}
File: mcp_config.jsonPath: ~/.codeium/windsurf/
🔧

Cline (VS Code)

AI Extension

Add in Cline MCP settings:

{
  "mcpServers": {
    "avena-terminal": {
      "url": "https://avenaterminal.com/mcp",
      "transportType": "streamable-http"
    }
  }
}
File: Cline MCP SettingsPath: VS Code → Cline Extension → MCP Servers
🔨

Smithery CLI

MCP Registry

Install via Smithery:

smithery mcp add henrik-kmvv/avena-terminal
File: TerminalPath: npx smithery or global install
🦜

LangChain (Python)

Agent Framework

Connect via MCP adapter:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-sonnet-4-20250514")

async with MultiServerMCPClient({
    "avena-terminal": {
        "url": "https://avenaterminal.com/mcp",
        "transport": "streamable_http",
    }
}) as client:
    agent = create_react_agent(model, client.get_tools())
    result = await agent.ainvoke({
        "messages": [{"role": "user", "content": "Find villas under 300k in Costa Blanca"}]
    })
File: Python scriptPath: pip install langchain-mcp-adapters
👥

CrewAI

Agent Framework

Add to CrewAI agent:

from crewai import Agent, Task, Crew
from langchain_mcp_adapters.client import MultiServerMCPClient

async with MultiServerMCPClient({
    "avena": {
        "url": "https://avenaterminal.com/mcp",
        "transport": "streamable_http"
    }
}) as client:
    analyst = Agent(
        role="Property Analyst",
        goal="Find best investments in Spain",
        tools=client.get_tools()
    )
    crew = Crew(agents=[analyst], tasks=[...])
    crew.kickoff()
File: Python scriptPath: pip install crewai langchain-mcp-adapters
🌐

Direct HTTP

Any Language

Call the MCP endpoint directly:

curl -X POST https://avenaterminal.com/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {
      "name": "search_properties",
      "arguments": {
        "region": "costa-blanca",
        "max_price": 300000,
        "min_score": 60
      }
    },
    "id": 1
  }'
File: Terminal / any HTTP clientPath: No dependencies required

Available Tools

search_properties — Search and filter by region, price, score, type
get_property — Full details with score breakdown
get_market_stats — Regional statistics and top towns
get_top_deals — Today's best investments ranked
estimate_roi — Projected returns over holding period
compare_alternatives — Similar properties comparison
market_timing — Buyer's vs seller's market assessment

Also Available

Full MCP Docs

Complete tool documentation

LangChain Guide

Detailed Python integration

PDP Protocol

Data exchange standard