How to Use the EPA ECHO (Enforcement & Compliance) MCP in Pydantic AI

Q: How do I configure the EPA ECHO (Enforcement & Compliance) MCP Server with Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Initialize MCPToolset with your Vinkius HTTP endpoint and pass it to the toolsets array in your Agent definition.

Q: Can the Pydantic AI agent track drinking water violations using EPA ECHO (Enforcement & Compliance)?

The searchdrinkingwatersystems tool pulls active violations for public water utilities. Your agent maps these records into strictly typed Python objects for downstream analysis.

Q: Do I need to use the deprecated MCPServerHTTP class?

No. You use the unified MCPToolset approach. It handles the Streamable HTTP transport automatically.

Enforce strict type safety on federal compliance data with the EPA ECHO (Enforcement & Compliance) MCP Server for Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EPA ECHO (Enforcement & Compliance) MCP to Pydantic AI

Create your Vinkius account to connect EPA ECHO (Enforcement & Compliance) to Pydantic AI 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 EPA ECHO (Enforcement & Compliance) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate EPA ECHO records with Pydantic AI

The `search_hazardous_waste_facilities` tool locates RCRA-regulated waste handlers and returns their compliance status. Your agent parses this data directly into Pydantic models, failing loudly if the federal API returns malformed structures. You integrate this MCP Server by passing `MCPToolset` to your Agent constructor. The framework guarantees that every facility record your application processes matches your exact schema constraints, eliminating silent data corruption.

Chart wastewater discharge metrics securely

Using `get_effluent_chart`, your AI client grabs dynamic tables of permitted limits and actual releases for Clean Water Act permits. The agent extracts the raw exceedance numbers for your internal risk models. Because Pydantic AI is model-agnostic, you swap between OpenAI and local models without rewriting the tool logic. The framework handles the JSON mapping, ensuring the effluent metrics always cast to the correct integer types.

Audit complete facility enforcement histories

The `get_detailed_facility_report` tool pulls a target's entire environmental record across all EPA programs. Your agent reads the historical penalties and maps them to your internal risk assessment objects. Connecting to the MCP Server happens through a single HTTP endpoint. The agent cross-references findings from `search_air_facilities` and `search_water_facilities` to build a typed, multi-media violation profile.

Setup guide

Set up EPA ECHO (Enforcement & Compliance) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "epa-echo-enforcement-compliance-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to EPA ECHO (Enforcement & Compliance) tools.",
)

result = await agent.run("List recent EPA ECHO (Enforcement & Compliance) transactions")
print(result.output)

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 EPA ECHO. 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 EPA ECHO (Enforcement & Compliance) 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 EPA ECHO (Enforcement & Compliance) MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Initialize `MCPToolset` with your Vinkius HTTP endpoint and pass it to the `toolsets` array in your Agent definition.

Federal APIs occasionally return unexpected nulls or missing fields. Pydantic AI validates the response from tools like `search_all_facilities` against your schema, throwing an error instead of hallucinating data.

The `search_drinking_water_systems` tool pulls active violations for public water utilities. Your agent maps these records into strictly typed Python objects for downstream analysis.

No. You use the unified `MCPToolset` approach. It handles the Streamable HTTP transport automatically.

Your agent sends facility names and permit numbers to the endpoint. The infrastructure isolates every request in a dedicated sandbox, preventing any cross-tenant data leakage before tearing the environment down.

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