How to Use the Convoy MCP in Pydantic AI

Q: Can Pydantic AI manage webhook routing filters in Convoy?

Yes, the agent calls createfilter to set up subscription rules. Pydantic AI validates the filter query syntax before sending it to Convoy, preventing API errors.

Q: How do I import event types from OpenAPI using Pydantic AI?

The agent runs importeventtypes to pull schemas directly into Convoy. Pydantic AI validates the OpenAPI document structure to ensure clean schema registration.

Manage Convoy webhooks with Pydantic AI to ensure type-safe endpoint creation and event delivery without runtime schema failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convoy MCP to Pydantic AI

Create your Vinkius account to connect Convoy 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 Convoy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Convoy endpoints with Pydantic AI

The `create_endpoint` tool registers new webhook destinations and validates the configuration parameters against strict Python types. Pydantic AI enforces this schema at runtime, blocking malformed URLs before they reach the Convoy MCP Server. When an endpoint is no longer needed, the agent calls `delete_endpoint` to clean up the project. The framework ensures that the target ID matches the expected UUID format, preventing destructive accidental deletions.

Publish structured events securely

The `dynamic_event` tool allows your agent to construct and publish custom event payloads with dynamic routing rules. Pydantic AI validates the payload structure against your models to prevent sending invalid JSON to consumers. Running `create_event_type` registers new event schemas directly in your Convoy project. This locks down the payload structure, ensuring downstream consumers only receive formatted data that passes validation.

Audit webhook deliveries using type-safe models

The `list_event_deliveries` tool fetches delivery histories and parses the results directly into typed Python objects. Pydantic AI raises immediate validation errors if any field deviates from the expected Convoy schema. To fix errors, the agent calls `retry_event_delivery` using the validated delivery ID. This gives you a reliable, self-healing webhook loop that never crashes due to unexpected null values in the API response.

Setup guide

Set up Convoy 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": {
        "convoy-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Instantiate MCPToolset with your Vinkius server URL and pass it to the Agent toolsets argument. This MCP integration registers all 26 tools and validates their inputs against Pydantic schemas.

The framework fails loudly with a validation error instead of passing dirty data to your model. This guarantees that your agent never acts on corrupted webhook delivery logs.

Yes, the agent calls `create_filter` to set up subscription rules. Pydantic AI validates the filter query syntax before sending it to Convoy, preventing API errors.

The agent runs `import_event_types` to pull schemas directly into Convoy. Pydantic AI validates the OpenAPI document structure to ensure clean schema registration.

All endpoint configuration details are processed inside isolated V8 sandboxes. Vinkius secures these credentials using end-to-end encryption, ensuring your webhook secrets are never exposed to the LLM or external networks. The MCP Server runs in a zero-trust sandbox to prevent exposure.

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