How to Use the Trigger.dev MCP in Pydantic AI

Q: How do I list all scheduled jobs using Trigger.dev and Pydantic AI?

You call the listschedules tool. This returns a structured, validated list of cron schedules that your agent can reliably process.

Q: Does the Pydantic AI framework guarantee data integrity when calling Trigger.dev?

Yes. Every field returned by any tool—including getrun and listruns—is validated against your defined Pydantic models at runtime.

Q: If I need to check if a task is running, which function should the Pydantic AI agent use?

Use listruns. This gives you a list of currently active or recently completed tasks, and then getrun for deep status checks.

Get guaranteed structured data on workflow status with Pydantic AI's 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 Trigger.dev MCP to Pydantic AI

Create your Vinkius account to connect Trigger.dev 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 Trigger.dev with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Task Run History with Pydantic AI

The agent gathers raw run history using `list_runs` and `get_run`. Because the response is validated by Pydantic, you're guaranteed that every field—like `status` or `run_id`—will be correctly structured. This eliminates silent failures; if the API messes up its JSON, your agent fails loud with a clear validation error.

Audit Project Scope using Pydantic AI

The `list_projects` tool feeds project names into your models. You'll receive a typed list of every available project, ready for structured consumption. It also checks environments with `list_environments`, ensuring the agent knows the exact deployment context it's working in.

Control and Replay Workflows

You can initiate a job with `trigger_task` or force a retest using `replay_run`. In both cases, the resulting data is typed and validated against your Pydantic schema, giving you reliable inputs. It also lets you manually stop running processes via `cancel_run`.

Setup guide

Set up Trigger.dev 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": {
        "triggerdev-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You call the `list_schedules` tool. This returns a structured, validated list of cron schedules that your agent can reliably process.

It handles task run details, project lists, and schedule information. This operational data is key to building reliable, type-safe applications.

Yes. Every field returned by any tool—including `get_run` and `list_runs`—is validated against your defined Pydantic models at runtime.

Use `list_runs`. This gives you a list of currently active or recently completed tasks, and then `get_run` for deep status checks.

The tool returns a structured collection of Project names and identifiers. This typed output allows your agent to proceed without guessing the field format.

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