Do I need an API key to use TED?

No! The TED Search API allows anonymous access for basic queries. An API key only increases your rate limits for high-volume usage. You can start searching tenders immediately without any credentials. If you need higher throughput, get a free key at developer.ted.europa.eu.

How can I find IT contracts over 500K EUR in Germany?

Combine tools: use `search_by_cpv` with code 72000000 (IT services) or `search_by_country` with code DE, then ask your agent to filter by value. Or use `search_by_value` with min_value 500000 and max_value 10000000. Your agent cross-references the results to show only German IT contracts above your threshold.

Is TED data limited to EU countries only?

TED primarily covers the 27 EU member states, but it also includes notices from EEA countries (Norway, Iceland, Liechtenstein), EU candidate countries, and some international organizations. All tools return data across this full scope. The `search_by_country` tool supports ISO codes for all covered territories.

TED EU MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: TED EU
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect TED EU through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to TED EU "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in TED EU?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 TED EU MCP Server

Connect TED (Tenders Electronic Daily) to any AI agent and search EU public procurement opportunities through natural conversation instead of navigating complex procurement portals.

Pydantic AI validates every TED EU tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Full-Text Search — Search across all TED procurement notices using keywords like "software development" or "medical equipment"
Country Filtering — Find active tenders from any of the 27 EU member states using ISO country codes
CPV Classification — Search by Common Procurement Vocabulary codes to target specific industry sectors
Value Range Search — Filter tenders by contract value in EUR to match your company size and capacity
Recent Opportunities — Monitor newly published tenders from the last 7 days to stay ahead of deadlines
Notice Details — Retrieve full procurement details including lots, award criteria, timelines, and contracting authority contacts

The TED EU MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI 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 TED EU to Pydantic AI via MCP

Follow these steps to integrate the TED EU MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from TED EU with type-safe schemas

Why Use Pydantic AI with the TED EU MCP Server

Pydantic AI provides unique advantages when paired with TED EU through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your TED EU integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your TED EU connection logic from agent behavior for testable, maintainable code

TED EU + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the TED EU MCP Server delivers measurable value.

Type-safe data pipelines: query TED EU with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple TED EU tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query TED EU and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock TED EU responses and write comprehensive agent tests

TED EU MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect TED EU to Pydantic AI via MCP:

get_tender

Includes description, lots, award criteria, timelines, and contracting authority contact. Get tender notice details

list_recent_tenders

Default is 7 days. Use to monitor new opportunities. List recently published tenders

search_by_country

Use ISO country codes: DE, FR, ES, IT, PT, NL, etc. Search tenders by country

search_by_cpv

CPV codes classify EU contracts by sector: 72000000 (IT), 45000000 (Construction), 33000000 (Medical). Search tenders by CPV code

search_by_value

Useful for finding contracts matching your company size. Search tenders by contract value

search_tenders

Returns title, country, value, deadline, and contracting authority. Covers all 27 EU member states. Search EU public tenders

Example Prompts for TED EU in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with TED EU immediately.

"Find recent tenders for software development in France."

"Show me construction tenders worth over 5 million euros."

"What new tenders were published this week?"

Troubleshooting TED EU MCP Server with Pydantic AI

Common issues when connecting TED EU to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

TED EU + Pydantic AI FAQ

Common questions about integrating TED EU MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your TED EU MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.