Shovels MCP Server for AutoGen 7 tools — connect in under 2 minutes
Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add Shovels as an MCP tool provider through Vinkius and every agent in the group can access live data and take action.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with McpWorkbench(
server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
transport="streamable_http",
) as workbench:
tools = await workbench.list_tools()
agent = AssistantAgent(
name="shovels_agent",
tools=tools,
system_message=(
"You help users with Shovels. "
"7 tools available."
),
)
print(f"Agent ready with {len(tools)} tools")
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Shovels MCP Server
Empower your AI agent to access the most comprehensive database of construction permits and licensed contractors with Shovels. By connecting Shovels to your agent, you transform complex real estate and construction auditing into a natural conversation. Your agent can instantly search for active permits, audit contractor history, and retrieve market statistics for specific geographic areas without you ever touching a dashboard. Whether you are analyzing market trends or verifying contractor credentials, your agent acts as a real-time construction data analyst, ensuring your insights are always structured and up-to-date.
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Shovels tools. Connect 7 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
What you can do
- Contractor Discovery — Find licensed professionals based on location, work type (solar, roofing, etc.), and property type.
- Permit Auditing — Search for and inspect detailed building permit records, including status and estimated values.
- Activity Tracking — Identify contractors actively working within a specific radius of any address.
- Market Intelligence — Retrieve aggregated permit statistics to analyze construction trends in different cities or counties.
- License Verification — Instantly pull contractor profiles using their state business license IDs.
The Shovels MCP Server exposes 7 tools through the Vinkius. Connect it to AutoGen in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Shovels to AutoGen via MCP
Follow these steps to integrate the Shovels MCP Server with AutoGen.
Install AutoGen
Run pip install "autogen-ext[mcp]"
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Integrate into workflow
Use the agent in your AutoGen multi-agent orchestration
Explore tools
The workbench discovers 7 tools from Shovels automatically
Why Use AutoGen with the Shovels MCP Server
AutoGen provides unique advantages when paired with Shovels through the Model Context Protocol.
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Shovels tools to solve complex tasks
Role-based architecture lets you assign Shovels tool access to specific agents. a data analyst queries while a reviewer validates
Human-in-the-loop support: agents can pause for human approval before executing sensitive Shovels tool calls
Code execution sandbox: AutoGen agents can write and run code that processes Shovels tool responses in an isolated environment
Shovels + AutoGen Use Cases
Practical scenarios where AutoGen combined with the Shovels MCP Server delivers measurable value.
Collaborative analysis: one agent queries Shovels while another validates results and a third generates the final report
Automated review pipelines: a researcher agent fetches data from Shovels, a critic agent evaluates quality, and a writer produces the output
Interactive planning: agents negotiate task allocation using Shovels data to make informed decisions about resource distribution
Code generation with live data: an AutoGen coder agent writes scripts that process Shovels responses in a sandboxed execution environment
Shovels MCP Tools for AutoGen (7)
These 7 tools become available when you connect Shovels to AutoGen via MCP:
get_contractor
Get contractor details
get_contractor_activity
Find contractors active at an address
get_contractor_by_license
Find contractor by license ID
get_permit
Get permit details
get_permit_stats
Get permit activity statistics
search_contractors
Search for licensed contractors
search_permits
Search for building permits
Example Prompts for Shovels in AutoGen
Ready-to-use prompts you can give your AutoGen agent to start working with Shovels immediately.
"Search for roofing contractors in ZIP 94105."
"Show me permit stats for Austin, TX."
"Find contractors active near 1600 Amphitheatre Pkwy, Mountain View."
Troubleshooting Shovels MCP Server with AutoGen
Common issues when connecting Shovels to AutoGen through the Vinkius, and how to resolve them.
McpWorkbench not found
pip install "autogen-ext[mcp]"Shovels + AutoGen FAQ
Common questions about integrating Shovels MCP Server with AutoGen.
How does AutoGen connect to MCP servers?
Can different agents have different MCP tool access?
Does AutoGen support human approval for tool calls?
Connect Shovels with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Shovels to AutoGen
Get your token, paste the configuration, and start using 7 tools in under 2 minutes. No API key management needed.
