How to Use the Exa AI MCP in Pydantic AI

Q: How do I connect the Exa AI MCP Server to Pydantic AI?

Point your application to the Vinkius endpoint using the MCPToolset constructor. Pass the toolset instance directly into the Agent constructor to expose the semantic search tools to your model.

Q: Can I retrieve search links with Exa AI using Pydantic AI?

Yes, the getsearchlinks tool returns only the top URLs for a given query. This lightweight operation is ideal when you need to validate web addresses before committing to a full download over the MCP Server.

Build type-safe search pipelines using Pydantic AI and the Exa AI 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 Exa AI MCP to Pydantic AI

Create your Vinkius account to connect Exa AI 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 Exa AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe semantic search with Pydantic AI

`search_web` queries the Exa index and returns structured web data that validates against your Pydantic models at runtime. If the search payload departs from your defined schema, your application raises a clear validation error. This strict validation prevents malformed search data from silently corrupting your downstream RAG pipelines. Your agent works only with clean, predictable JSON objects.

Strict content extraction and validation

`get_contents` retrieves cleaned text and HTML from specific Exa IDs, ensuring the output conforms to your exact type definitions. You write the schema, and Pydantic AI enforces the structure before your agent processes the content. For faster execution, `search_with_contents` runs both search and extraction in one step. This reduces network round-trips while maintaining the same rigorous type-checking across your entire data flow.

Semantic similarity and usage tracking

`find_similar` analyzes a given URL and outputs a validated list of related websites. This tool helps your agent build reliable maps of web ecosystems without relying on fragile scraping scripts. You can monitor your resource limits by calling `get_api_usage` to fetch crawl statistics and API calls. This tool returns structured usage metrics, making it easy to build automated alerts when you near your plan limits.

Setup guide

Set up Exa AI 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": {
        "exa-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Exa AI tools.",
)

result = await agent.run("List recent Exa AI 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 Exa AI. 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 Exa AI 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 Exa AI MCP in Pydantic AI

Point your application to the Vinkius endpoint using the `MCPToolset` constructor. Pass the toolset instance directly into the `Agent` constructor to expose the semantic search tools to your model.

Pydantic AI will raise a validation error instantly. This prevents your agent from hallucinating or acting on corrupt search metadata, keeping your production environment completely stable.

Yes, the `get_search_links` tool returns only the top URLs for a given query. This lightweight operation is ideal when you need to validate web addresses before committing to a full download over the MCP Server.

The framework is completely model-agnostic. You can run the search tools with local models or commercial endpoints while keeping the exact same validation rules for your web data.

Your API usage metrics and search queries are handled within an ephemeral V8 sandbox. The system processes all validation checks in memory and discards the data immediately after the request completes.

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