How to Use the Eden AI MCP in Pydantic AI

Q: How do I attach Eden AI to Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset array to your Agent instance.

Q: Will Pydantic AI catch missing fields in Eden AI responses?

Yes. If a tool like listallllmmodels returns a JSON structure that violates your Pydantic model, the framework raises a ValidationError. It refuses to pass bad data to your logic.

Q: Can my Pydantic AI agent compare Eden AI vendor pricing?

Yes. It can invoke getaifeaturepricing to fetch the cost details for a specific AI feature. The agent can then mathematically compare vendors before routing a request.

Q: How do I list my active workflows?

Trigger the listaiworkflows tool. It returns the IDs and names of your configured automation pipelines directly from your account.

Q: Is my API usage data secure during type validation?

Yes. Data retrieved via getapiusagestatistics routes through a stateless V8 Isolate. The connection is ephemeral, ensuring your historical consumption metrics are processed, validated, and immediately flushed from memory.

Strictly validate Eden AI workflow configurations and API usage stats using this Pydantic 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 Eden AI MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate workflow configurations strictly

When your agent calls `get_workflow_configuration`, Pydantic AI forces the response into your predefined schema. Silent failures ruin production systems. If the API returns an unexpected field type, the system throws a loud validation error immediately. The agent invokes `list_ai_workflows` or `list_latest_ai_automations` to fetch active setups securely. You get the same strictness when discovering pipelines. Every workflow name and ID gets type-checked before your application logic even sees the data.

Query providers via MCP Server

Your agent runs `list_ai_providers` to fetch the current active vendor roster for any given feature. Hardcoded lists break when APIs update. It then uses `quick_ai_provider_audit` to grab high-level summaries for text analysis tasks. The `list_available_ai_features` tool pulls every supported capability from the platform straight into your validated models. Feature mapping works exactly the same way. Your agent receives a checked list of subfeatures, ensuring it never tries to call an endpoint that does not exist.

Enforce cost and usage constraints

Your agent executes `get_api_usage_statistics` to pull raw consumption metrics for cost tracking. Budget overruns happen when tracking fails. Because Pydantic AI validates the numbers, you know your cost calculations are based on exact integers, not malformed strings. The `get_ai_feature_pricing` tool retrieves the cost matrix for specific tasks to help predict costs. You can also check your remaining balance using `get_eden_ai_metadata`, allowing your agent to halt execution if funds drop below a safe threshold.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset array to your Agent instance.

Yes. If a tool like `list_all_llm_models` returns a JSON structure that violates your Pydantic model, the framework raises a `ValidationError`. It refuses to pass bad data to your logic.

Yes. It can invoke `get_ai_feature_pricing` to fetch the cost details for a specific AI feature. The agent can then mathematically compare vendors before routing a request.

Trigger the `list_ai_workflows` tool. It returns the IDs and names of your configured automation pipelines directly from your account.

Yes. Data retrieved via `get_api_usage_statistics` routes through a stateless V8 Isolate. The connection is ephemeral, ensuring your historical consumption metrics are processed, validated, and immediately flushed from memory.

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