How to Use the Voyage AI (AI Embeddings API) MCP in Pydantic AI

Q: How do I handle large-scale embedding generation with Voyage AI (AI Embeddings API) and Pydantic AI?

Process batches by first calling uploadfile to stage the data. The agent then runs the job via createbatch, but crucially, it validates the resulting vector embeddings against your defined models.

Q: Can I mix different types of data (text, image) for embeddings with Voyage AI (AI Embeddings API) and Pydantic AI?

Yes. Use createmultimodalembeddings to process mixed media. The agent ensures that even when dealing with varied inputs, the final output structure remains consistent and type-safe.

Q: How does Voyage AI (AI Embeddings API) interact with file data using Pydantic AI?

The process starts with listfiles to map out available documents. If the agent needs to work with the actual content, it calls getfilecontent. This ensures that every piece of source material is correctly loaded and validated.

Guarantee data correctness using Pydantic AI and Voyage AI (AI Embeddings API).

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Voyage AI (AI Embeddings API) MCP to Pydantic AI

Create your Vinkius account to connect Voyage AI (AI Embeddings API) 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 Voyage AI (AI Embeddings API) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Vector Generation

When you call `create_embeddings`, the agent ensures that the output structure matches your defined schema. If the embedding data is malformed, the system fails loudly with a validation error. This makes it impossible for corrupted vector results to silently break downstream components of your application.

Controlled Document Retrieval

The `rerank` tool lets you run high-precision scoring against documents. Because the agent uses Pydantic validation, it can guarantee that the context returned from this process is correctly typed and usable. Before ranking, you use `list_files` to identify which specific data sources are relevant for the current user query.

Robust Batch Data Handling

To handle large inputs, your agent calls `upload_file`. The batch process is managed by calling `create_batch`, and the results you receive are validated against expected Pydantic models. You track these jobs using `get_batch`, knowing that every status update or failure message will conform to a strict data contract.

Setup guide

Set up Voyage AI (AI Embeddings API) 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": {
        "voyage-ai-ai-embeddings-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Voyage AI (AI Embeddings API) 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 Voyage 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 Voyage AI (AI Embeddings API) 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 Voyage AI (AI Embeddings API) MCP in Pydantic AI

Process batches by first calling `upload_file` to stage the data. The agent then runs the job via `create_batch`, but crucially, it validates the resulting vector embeddings against your defined models.

The agent's validation layer catches unexpected data types or structural issues immediately. You can stop the process by calling `cancel_batch` and then examine the error using `get_batch` to pinpoint the exact failure point.

Yes. Use `create_multimodal_embeddings` to process mixed media. The agent ensures that even when dealing with varied inputs, the final output structure remains consistent and type-safe.

The process starts with `list_files` to map out available documents. If the agent needs to work with the actual content, it calls `get_file_content`. This ensures that every piece of source material is correctly loaded and validated.

The server handles raw text payloads, file metadata, and computed vector embeddings. Because of Pydantic's role, you get a guaranteed structure on the `file_metadata`.

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