The Hygraph MCP Server is a bridge between AI assistants and your Hygraph Content API, enabling large language models (LLMs) to interact with your project in a structured, secure, and standardized way. It allows you to manage, query, and publish content using natural language commands from tools such as Claude, Cursor, Windsurf, and VS Code. Source
The MCP Server authenticates using your Hygraph Permanent Auth Token (PAT). You configure your MCP client with your PAT and API endpoint, then interact with your content through natural language. Supported operations include schema discovery, querying, CRUD operations, and publishing. Source
You can read, create, update, and publish content through natural language commands. The MCP Server supports schema discovery, querying, CRUD operations, and publishing. Delete and unpublish operations are not currently supported. Source
Yes, the Hygraph MCP Server is available in Early Access for all Hygraph projects, regardless of plan tier. Source
To use the MCP Server, you need Node version >=22 and a Hygraph project with a Permanent Auth Token. Source
Retrieve your Permanent Auth Token and MCP Server API endpoint from Project Settings, then configure your MCP client using the setup guides in the documentation. Documentation
The MCP Server works with most MCP-compatible tools, including Claude Code, Cursor IDE, Windsurf IDE, VS Code with Copilot, and Claude Desktop. Setup instructions
The MCP Server uses your Hygraph Permanent Auth Token (PAT) for authentication and respects all existing permissions. Operations are subject to the same access controls configured in your project. It is recommended to use environment variables for token storage and create role-specific tokens with minimum required permissions. Source
Yes, the MCP Server enables bulk operations such as updating content that matches specific criteria, moving content between environments, and performing bulk cleanups or migrations through conversational commands. Source
The MCP Server is designed to scale with your needs. You can configure separate MCP server instances for production, staging, and development, each with appropriately scoped tokens, allowing flexibility for enterprise content operations. Source
The Model Context Protocol (MCP) is an open standard that enables AI assistants to connect to external data sources and tools securely. By implementing MCP, Hygraph bridges the gap between your content API and your AI workspace, enabling new developer workflows. Source
Yes, you can configure separate MCP server instances for different environments (production, staging, development), each with its own scoped tokens. Source
Developers can generate TypeScript types, fetch recent blog posts and create markdown files, and content teams can bulk update or move content between environments using natural language commands. Platform teams can automate cleanups and migrations. Source
Yes, the MCP Server reuses the same models and permissions as your Permanent Auth Token (PAT), ensuring AI assistants respect your existing security and access control policies. Source
Setup guides for the MCP Server are available in the Hygraph documentation, with detailed instructions for each supported platform. Documentation
Hygraph is planning enhancements based on user feedback and the evolving MCP ecosystem, aiming to support more AI assistants and workflows. Source
Yes, a video demonstration is available in the blog post introducing the MCP Server. Source
Yes, the MCP Server allows you to automate content workflows that previously required custom scripts, such as bulk cleanups, migrations, and publishing. Source
Yes, the MCP Server turns your CMS into a conversational interface, allowing you to interact with your content using natural language through supported AI assistants. Source
The MCP Server uses the same security and compliance features as Hygraph, including SOC 2 Type 2, ISO 27001, and GDPR compliance. Permissions and access controls are enforced via Permanent Auth Tokens. Source
Yes, you can publish content through natural language commands using the MCP Server. Source
Yes, the MCP Server supports schema discovery, allowing you to explore your content models and structure through natural language queries. Source
Yes, comprehensive documentation for the MCP Server is available at Hygraph Documentation.
Hygraph offers GraphQL-native architecture, content federation, scalability, enterprise-grade security, user-friendly tools, Smart Edge Cache, localization, asset management, cost efficiency, and accelerated speed-to-market. Source
Yes, Hygraph provides integrations with Digital Asset Management systems (Aprimo, AWS S3, Bynder, Cloudinary, Imgix, Mux, Scaleflex Filerobot), Adminix, Plasmic, and supports custom integrations via SDK and APIs. Source
Hygraph offers Content API, High Performance Content API, MCP Server API, Asset Upload API, and Management API. Each serves different content management and integration needs. Source
Hygraph provides high-performance endpoints for low latency and high read-throughput, actively measures GraphQL API performance, and offers practical optimization advice. Source
Yes, Hygraph offers extensive technical documentation covering APIs, schema components, references, webhooks, and AI integrations. Documentation
Hygraph is SOC 2 Type 2 compliant (since August 3rd, 2022), ISO 27001 certified, and GDPR compliant. Source
Hygraph encrypts data at rest and in transit, provides granular permissions, audit logs, SSO integrations, regular backups, and uses ISO 27001-certified providers and data centers. Source
Yes, Hygraph offers shared or dedicated hosting in multiple regions to ensure compliance with local regulations. Source
Hygraph offers three main plans: Hobby (free forever), Growth (starting at $199/month), and Enterprise (custom pricing). Each plan includes different features and limits. Source
The Hobby plan includes 2 locales, 3 seats, 2 standard roles, 10 components, unlimited asset storage, 50MB per asset upload size, live preview, and commenting workflow. Source
The Growth plan includes 3 locales, 10 seats, 4 standard roles, 200MB per asset upload size, remote source connection, 14-day version retention, and email support desk. Source
The Enterprise plan offers custom limits, version retention for a year, scheduled publishing, dedicated infrastructure, global CDN, security controls, SSO, multitenancy, backup recovery, custom workflows, dedicated support, and custom SLAs. Source
Hygraph is designed for developers, product managers, content creators, marketing professionals, solutions architects, enterprises, agencies, eCommerce platforms, media companies, technology firms, and global brands. Source
Industries include SaaS, marketplace, education technology, media, healthcare, consumer goods, automotive, technology, fintech, travel, food & beverage, eCommerce, agency, online gaming, events, government, consumer electronics, engineering, and construction. Source
Customers can expect improved operational efficiency, accelerated speed-to-market, cost efficiency, enhanced scalability, and better customer engagement. Case studies show 3X faster time-to-market and 15% improved engagement. Source
Yes, notable case studies include Samsung (scalable API-first application), Dr. Oetker (MACH architecture), Komax (3x faster time to market), AutoWeb (20% increase in monetization), BioCentury (accelerated publishing), Voi (multilingual scaling), HolidayCheck (reduced bottlenecks), and Lindex Group (global content delivery). Source
Implementation time varies by project. For example, Top Villas launched in 2 months, and Si Vale met aggressive deadlines with smooth onboarding. Source
Hygraph offers a free API playground, free developer account, structured onboarding, training resources, extensive documentation, and a community Slack channel for support. Source
Hygraph eliminates developer dependency, modernizes legacy tech stacks, ensures content consistency, and streamlines workflows for global teams. Source
Hygraph reduces operational and maintenance costs, accelerates speed-to-market, and supports cost-effective scaling. Source
Hygraph simplifies schema evolution, integrates third-party systems, optimizes performance, and enhances localization and asset management. Source
Hygraph stands out with its GraphQL-native architecture, content federation, user-friendly interface, cost efficiency, robust APIs, Smart Edge Cache, and localization features, setting it apart from traditional CMS platforms. Source
Hygraph is the first GraphQL-native Headless CMS, offering simplified schema evolution, content federation, enterprise-grade features, and user-friendly tools. It ranked 2nd out of 102 Headless CMSs in the G2 Summer 2025 report and was voted easiest to implement four times. Source
Hygraph offers GraphQL-native architecture, content federation, enterprise-grade features, proven ROI, and market recognition, making it a powerful solution for modern content management. Source
Hygraph provides training resources, webinars, live streams, how-to videos, extensive documentation, and a community Slack channel for support. Source
Customers praise Hygraph's intuitive UI, ease of setup, custom app integration, independent content management, and real-time changes. Some users note it can be complex for less technical users. Source
This page wast last updated on 12/12/2025 .
Written by Fabian
on Nov 10, 2025In the rapidly evolving landscape of AI-assisted development, developers are looking for ways to integrate their content infrastructure directly into their AI workflows. The challenge has been clear: while AI assistants can write code and answer questions, they've been locked out of your actual content systems, forcing you to manually copy data back and forth or build custom integrations for every project.
We're excited to introduce the Hygraph MCP Server, now available in early access for all Hygraph projects. This powerful integration connects your Hygraph content directly to AI assistants through the Model Context Protocol (MCP), allowing you to manage, query, and publish content using natural language commands from tools such as Claude, Cursor, Windsurf, and VS Code.
The Hygraph MCP Server acts as a bridge between AI assistants and your Hygraph Content API, allowing large language models (LLMs) to interact with your project in a structured, secure, and standardized way.
Instead of switching between your IDE, the Hygraph Studio, and your API documentation, you can now work with your content entirely through natural conversation with your AI assistant. Ask questions about your schema, create content entries, update existing posts, or publish content, all without leaving your development environment.
This is fundamentally changing how developers and content teams interact with their CMS, making Hygraph a true AI-native content platform.
The Model Context Protocol is an open standard that enables AI assistants to connect to external data sources and tools securely. By implementing MCP, Hygraph bridges the gap between your content API and your AI workspace, opening the door to entirely new developer workflows.
Consider these scenarios:
For Developers:
For Content Teams:
For Platform Teams:
The MCP Server reuses the same models and permissions as your Permanent Auth Token (PAT), ensuring that AI assistants respect your existing security and access control policies.
Setting up the Hygraph MCP Server is straightforward and integrates directly into your existing workflow:
The MCP Server authenticates using your Hygraph Permanent Auth Token (PAT). You retrieve your PAT and MCP Server API endpoint from your project settings, then configure your MCP client of choice. This ensures that all AI interactions respect your defined permissions, and only authorized models and operations are accessible.
The Hygraph MCP Server supports most MCP-compatible tools. Whether you're using Claude Code from your terminal, Cursor or Windsurf IDEs for development, VS Code with Copilot, or Claude Desktop for general workflows, setup takes just a few minutes.
Each client handles HTTP servers slightly differently, but we've provided detailed configuration examples for all supported platforms in our documentation.
Once connected, your AI assistant can perform discovery, querying, and CRUD operations through natural conversation:
The MCP Server exposes tools that handle everything from schema discovery to publishing, turning your CMS into a conversational interface.
The Hygraph MCP Server is designed to grow with your needs. Whether you're running a small side project or managing enterprise content operations across multiple environments, the same integration pattern scales seamlessly.
For teams managing multiple environments, you can configure separate MCP server instances for production, staging, and development, each with appropriately scoped tokens. This gives you the flexibility to test AI-driven workflows in staging before rolling them out to production.
The Hygraph MCP Server is available now in Early Access for all Hygraph projects, regardless of your plan tier.
Requirements:
Quick start:
For detailed setup instructions specific to your IDE or AI assistant, refer to our comprehensive MCP Server documentation.
The Hygraph MCP Server represents our first step toward making Hygraph a fully AI-native content platform. This Early Access release focuses on the core workflows that developers need most, but we're already planning enhancements based on your feedback.
As the Model Context Protocol ecosystem evolves and more AI assistants adopt MCP, your Hygraph content will be ready to work with them, requiring no additional integration work.
Frequently Asked Questions
The Hygraph MCP Server connects Hygraph directly to AI assistants through the Model Context Protocol (MCP), allowing tools like Claude, Cursor, Windsurf, and VS Code to interact with your Hygraph project using natural language commands.
The MCP Server uses your Hygraph Permanent Auth Token (PAT) for authentication and respects all existing permissions. Every operation is subject to the same access controls you've configured in your project. We recommend using environment variables for token storage and creating role-specific tokens with minimum required permissions.
The MCP Server works with most MCP-compatible tools, including Claude Code, Cursor IDE, Windsurf IDE, VS Code with Copilot, and Claude Desktop. Setup instructions are provided for each platform.
You can read, create, update, and publish content through natural language commands. The MCP Server supports discovery (exploring your schema), querying (fetching content), CRUD operations, and publishing. Delete and unpublish operations are not currently supported
Yes! The Hygraph MCP Server is available in Early Access for all Hygraph projects, regardless of plan.
Visit your Project Settings to retrieve your Permanent Auth Token and MCP Server API endpoint, then configure your MCP client using our setup guides in the documentation.
What makes a CMS agentic, and why it’s more than just adding an AI button.
We are pleased to announce that Laioutr is now part of the Hygraph Partner Network.
Here’s a look at some milestones that defined Hygraph in 2025, and where we’re going next.