How to Use the Typefully MCP in Pydantic AI

Q: How does Typefully interact with Pydantic AI for content publishing?

Pydantic AI validates the data returned by the Typefully MCP Server. If you call listdrafts and the response structure doesn't match your Python model, the agent throws a validation error immediately. This prevents bad data from reaching your final action.

Q: Can I use Pydantic AI to check my Typefully profile details?

Yes, you call getuserprofile. The resulting JSON object is automatically validated against your schema. If the API changes and returns a new field, your agent won't break—it will fail gracefully with an explicit validation error.

Q: What happens if I try to update content using Pydantic AI?

When you call updatedraft, the input payload is first checked. The system ensures that every piece of data—like the new text or the target account ID—matches the types defined in your Pydantic model. It's about correctness, period.

Q: What tools are exposed by the Typefully MCP Server?

The server exposes nine functions: createdraft, deletedraft, getdraftdetails, getuserprofile, listdrafts, listsocialaccounts, publishimmediately, schedulecontent, and updatedraft.

Ensure every Typefully publishing action is validated with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Typefully MCP to Pydantic AI

Create your Vinkius account to connect Typefully 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 Typefully with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Draft Integrity via MCP Server

You'll never get corrupted data. When you call `get_draft_details` or `list_drafts`, the response is immediately checked against a Pydantic model. If Typefully returns an unexpected field, your agent fails loud and clear. This type-safe validation means that when you use tools like `update_draft`, you know exactly what data structure you're modifying. It eliminates silent failures.

Controlled Content Lifecycle with Pydantic AI

The agent can manage the entire content lifecycle without guessing. You start by calling `create_draft` and defining all necessary fields in your model. Later, if you need to retire the asset, calling `delete_draft` is also validated. This rigorous structure means that every single step, from initial creation to final deletion, adheres to a defined schema.

Publishing and Scheduling with Pydantic AI

When you're ready to post, the agent must confirm all necessary fields are present. You can validate the input parameters for `schedule_content` or `publish_immediately`. If a required field like `target_account` is missing, the tool call fails immediately. Furthermore, you can check your status using `list_social_accounts`, and that list must conform to your defined Pydantic schema before proceeding.

Setup guide

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

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

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

Pydantic AI validates the data *returned* by the Typefully MCP Server. If you call `list_drafts` and the response structure doesn't match your Python model, the agent throws a validation error immediately. This prevents bad data from reaching your final action.

Yes, you call `get_user_profile`. The resulting JSON object is automatically validated against your schema. If the API changes and returns a new field, your agent won't break—it will fail gracefully with an explicit validation error.

When you call `update_draft`, the input payload is first checked. The system ensures that every piece of data—like the new text or the target account ID—matches the types defined in your Pydantic model. It's about correctness, period.

The server exposes nine functions: `create_draft`, `delete_draft`, `get_draft_details`, `get_user_profile`, `list_drafts`, `list_social_accounts`, `publish_immediately`, `schedule_content`, and `update_draft`.

The server handles user profile details, content drafts (textual), and social account connection metadata. Pydantic AI ensures that all these diverse data types are handled according to strict Python typing.

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