Storyblok MCP Server

Storyblok MCP Server

Connects AI tools to Storyblok CMS, allowing users to manage content through natural language commands for tasks like story management, asset handling, and AI-powered content operations.

Category
访问服务器

README

Storyblok MCP Server

Connect AI tools to Storyblok instantly - use natural language to manage your CMS like magic.

Demo

<table> <tr> <td><img src="https://github.com/user-attachments/assets/e3f3ae2b-2774-406d-a952-8994b9618202" alt="Demo Image 1" width="300" /></td> <td><img src="https://github.com/user-attachments/assets/3d6b6a34-70eb-4c57-99b7-c81d091f47ff" alt="Demo Image 2" width="300" /></td> <td><img src="https://github.com/user-attachments/assets/960ff18e-537a-4a82-89bc-0f5b0e56f68f" alt="Demo Image 3" width="300" /></td> </tr> <tr> <td><img src="https://github.com/user-attachments/assets/cae92c66-43c7-4b64-a08d-d868f50566b5" alt="Demo Image 4" width="300" /></td> <td><img src="https://github.com/user-attachments/assets/2ecffada-e5ea-4008-8070-c579e0d28b10" alt="Demo Image 5" width="300" /></td> <td><img src="https://github.com/user-attachments/assets/e49d6c52-a805-4044-91dc-e1ed6d19df68" alt="Demo Image 6" width="300" /></td> </tr> </table>


Table of Contents


Why This Project?

Built for the Storyblok Headless CMS Challenge on DEV.to.

The goal: push AI and Storyblok's power together, make something fresh and useful.


What is Storyblok?

Storyblok is a powerful headless CMS. API-first. Easy for devs and content creators to work together.

It's modular, super flexible, and fits with any frontend or workflow you want.


What's an MCP Server?

MCP = a protocol that connects AI, tools, and data.

The MCP server acts as a middleman, showing AI what it can do and what data it has.

This enables AI clients, such as Cursor or Claude Desktop, to interact with Storyblok through natural language and manage content smoothly.


Challenges I Faced

  • Built for myself (lol): Never made or installed an MCP before. Took way longer than I thought.

  • API stress: Kept checking Storyblok's API docs again and again. Scared I'd miss something.

  • AI stuff pressure: Trying to get AI features right without breaking things was a headache.

  • Security: Had to make sure no sensitive info leaks while exposing Storyblok management.

  • Developer experience: Made the server easy to run, extend, and plug into AI tools. No shortcuts.


How to Set Up (For Contributors)

  1. Clone the repo:

    git clone https://github.com/ArjunCodess/storyblok-mcp.git
    cd storyblok-mcp
    
  2. Install dependencies:

    pnpm install
    
  3. Run the server:

    pnpm start
    

How to Use (For Users)

Clone the repo:

git clone https://github.com/ArjunCodess/storyblok-mcp.git
cd storyblok-mcp

Connect with Cursor

https://github.com/user-attachments/assets/98b77544-81c4-49b3-8dc2-14849e6ba7e5

  • Open Cursor in the same directory.
  • Right click on build/index.js file and click Copy Path.
  • Now, go to SettingsMCP Tools.
  • Click on New MCP Server
  • Inside the opened mcp.json file. Paste this and replace PATH_YOU_COPIED with the path copied in the second step:
    {
      "mcpServers": {
        "storyblok": {
          "command": "node PATH_YOU_COPIED",
          "env": {
            "STORYBLOK_SPACE_ID": "your_space_id",
            "STORYBLOK_MANAGEMENT_TOKEN": "your_management_token",
            "STORYBLOK_DEFAULT_PUBLIC_TOKEN": "your_public_token",
            "GOOGLE_GENERATIVE_AI_API_KEY": "your_gemini_ai_api_key"
          }
        }
      }
    }
    

Tools

<details> <summary>1. Story Management</summary>

  • fetch_stories
    Retrieve a list of stories (pages, folders, or content entries) from Storyblok. Supports filtering, pagination, and search.

  • get_story
    Fetch a single story by its ID.

  • create_story
    Create a new story (page, folder, or content entry) in Storyblok.

  • update_story
    Update an existing story's content, name, slug, or tags.

  • delete_story
    Delete a story by its ID.

  • publish_story
    Publish a story, making it live.

  • unpublish_story
    Unpublish a story, removing it from the live site.

  • get_story_versions
    Retrieve all previous versions of a story for version history and rollback.

  • restore_story
    Restore a story to a previous version. </details>

<details> <summary>2. Tag Management</summary>

  • fetch_tags
    List all tags used in the space.

  • create_tag
    Create a new tag.

  • create_tag_and_add_to_story
    Create a tag and immediately assign it to a story.

  • delete_tag
    Delete a tag by its ID. </details>

<details> <summary>3. Release Management</summary>

  • fetch_releases
    List all releases (content batches for scheduled publishing).

  • create_release
    Create a new release.

  • add_story_to_release
    Add a story to a release.

  • publish_release
    Publish all stories in a release.

  • delete_release
    Delete a release. </details>

<details> <summary>4. Asset Management</summary>

  • fetch_assets
    List all assets (images, files, etc.) in the space.

  • get_asset
    Fetch a single asset by its ID.

  • delete_asset
    Delete an asset.

  • init_asset_upload
    Start uploading a new asset.

  • complete_asset_upload
    Complete the asset upload process. </details>

<details> <summary>5. Asset Folder Management</summary>

  • fetch_asset_folders
    List all asset folders.

  • create_asset_folder
    Create a new asset folder.

  • update_asset_folder
    Rename an asset folder.

  • delete_asset_folder
    Delete an asset folder. </details>

<details> <summary>6. Component Management</summary>

  • fetch_components
    List all components (content types) in the space.

  • get_component
    Fetch a single component by its ID.

  • create_component
    Create a new component.

  • update_component
    Update a component's schema or settings.

  • delete_component
    Delete a component. </details>

<details> <summary>7. Advanced Story Search</summary>

  • search_stories
    Search for stories using advanced filters (by slug, tag, etc.).

  • get_story_by_slug
    Fetch a story by its slug. </details>

<details> <summary>8. Space & Folder Info</summary>

  • get_space
    Get information about the current Storyblok space.

  • fetch_folders
    List all story folders.

  • fetch_datasources
    List all datasources (for dynamic select fields, etc.). </details>

<details> <summary>9. Utility</summary>

  • ping
    Check if the server and Storyblok API are reachable. </details>

<details> <summary>10. AI Tools</summary>

  • generate_alt_text
    Automatically create alt text for images based on content or context.

  • translate_story
    Translate the content of a story into different languages using AI.

  • generate_meta_tags
    Generate SEO-friendly meta titles and descriptions for any story.

  • summarize_story
    Get a brief AI-generated summary of a story’s content.

  • tag_story_with_ai
    Auto-generate relevant tags for a story using natural language processing. </details>


How to Contribute

Fork, make changes, open PRs. Found bugs or want features? Open an issue.


Useful Links


Thanks

Made with ❤️ for the DEV.to Storyblok Challenge.


License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选