How to Use the Prismic MCP in Mastra AI

Q: How do I initialize Prismic with Mastra AI?

Install @mastra/mcp and instantiate MCPClient with your Vinkius server URL. Call mcpClient.listTools() and spread them into your agent's configuration. Mastra auto-detects the transport layer.

Q: How does the Prismic MCP Server support human-in-the-loop?

You can configure requireToolApproval for sensitive operations in Mastra. While reading listglobaltags is safe, you might want human sign-off before the agent acts on outdated content. The workflow pauses until you approve.

Q: Can Mastra AI query Prismic forms directly?

The agent calls getqueryformschema to understand the exact parameters required for complex searches. It constructs the correct predicate payload before executing the fetch. This prevents malformed API requests during autonomous runs.

Build resilient content workflows in Mastra AI using live Prismic repository data.

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 Mastra AI

Create your Vinkius account to connect Prismic to Mastra AI — 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated Content Audits

The `list_documents_by_type` tool feeds entire content categories into your Mastra AI workflows. Your agent pulls all blog posts and maps them through a conditional branching loop. If a post lacks required metadata, the workflow routes it to an editor's queue. For deep analysis on failing items, the workflow triggers `get_document_by_id`. Mastra handles the exponential backoff if the Prismic API rate-limits the requests. Your audit completes reliably without manual intervention.

Prismic MCP Server Metadata Sync

The Prismic MCP Server exposes repository state through the `get_repo_metadata` tool. Mastra reads the master ref to verify if content has changed since the last workflow execution. If the ref matches the cached version, the agent skips the heavy processing steps. When the ref updates, the workflow calls `list_custom_types` to check for schema changes. It dynamically adjusts its extraction logic based on the new fields. You push one command to deploy this self-healing sync process to any cloud.

Conditional Locale Fallbacks

The `search_filtered_locale` tool powers multi-region content validation inside Mastra AI. The agent queries a specific market's documents and checks for missing translations. If a French document returns empty, the workflow branches to a fallback logic path. To determine valid fallback targets, the agent invokes `list_i18n_languages`. It reads the configured repository locales and selects the primary language. The system then queries the English version to populate the missing fields.

Setup guide

Set up Prismic MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Prismic tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "prismic-mcp-client",
  servers: {
    "prismic-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Prismic Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Prismic tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Prismic transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp` and instantiate `MCPClient` with your Vinkius server URL. Call `mcpClient.listTools()` and spread them into your agent's configuration. Mastra auto-detects the transport layer.

Mastra uses built-in exponential backoff for all tool calls. If `query_prismic_documents` hits a throttle response, the workflow pauses and retries automatically. Your long-running content migrations won't crash mid-execution.

You can configure `requireToolApproval` for sensitive operations in Mastra. While reading `list_global_tags` is safe, you might want human sign-off before the agent acts on outdated content. The workflow pauses until you approve.

The agent calls `get_query_form_schema` to understand the exact parameters required for complex searches. It constructs the correct predicate payload before executing the fetch. This prevents malformed API requests during autonomous runs.

The integration processes raw JSON payloads containing your published articles and repository metadata. Vinkius runs the server in an ephemeral container that destroys itself after the workflow ends. Zero cross-tenant data leakage occurs.

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