How to Use the Prismic MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK handle Prismic schema changes?

Yes. By calling listcustomtypes, your agent detects changes to your content model in real-time. It updates its internal logic to match your new fields without a redeploy.

Connect Prismic to your OpenAI Agents SDK pipeline for direct content retrieval and schema validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Prismic MCP to OpenAI Agents SDK

Create your Vinkius account to connect Prismic to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Prismic with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Direct Prismic content access for OpenAI Agents SDK

Your agent pulls raw data straight from your repository using `get_document_by_id`. It skips the middleware and hits the content source directly. This setup works perfectly within your async context managers. You get the exact document structure you need without extra parsing.

Dynamic type discovery in OpenAI Agents SDK

Let your agent inspect your content architecture using `list_custom_types`. It learns your schemas on the fly. Once the agent knows the structure, it uses `query_prismic_documents` to pull specific entries. It’s a clean way to keep your agent’s knowledge current with your CMS.

Precision locale management for OpenAI Agents SDK

Target international content by using `search_filtered_locale` to force specific language responses. It isolates content by region instantly. Your agent maintains strict control over the requested locale. It avoids the mess of cross-language queries by locking into the correct version at the tool level.

Setup guide

Set up Prismic MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Prismic tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Prismic tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Prismic tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Prismic Agent",
            instructions="You have access to Prismic tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Prismic. 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 Prismic 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 Prismic MCP in OpenAI Agents SDK

You pass the Prismic MCP server to the agent constructor via the mcp_servers parameter. The agent auto-discovers all tools, allowing you to trigger a search with a natural language request.

Yes. By calling `list_custom_types`, your agent detects changes to your content model in real-time. It updates its internal logic to match your new fields without a redeploy.

Vinkius handles the auth layer with a single endpoint token. Your agent only sees the data you explicitly query, keeping your repository access isolated.

The server returns a standard error message. Your agent receives this immediately, allowing you to trigger fallback logic or log the failure in your dashboard.

It does. The tools return the full Prismic document object. You can pass this JSON directly into your agent's context for processing or summarization.

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