Verge

Provides a Model Context Protocol server for VergeCMS enabling AI assistants to manage blogs and articles via natural language.
  • typescript

0

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "tomohirof-verge-mcp-server": {
      "command": "node",
      "args": [
        "/absolute/path/to/verge-mcp-server/dist/index.js"
      ],
      "env": {
        "VERGE_EMAIL": "user@example.com",
        "VERGE_API_URL": "https://api.vergecms.io",
        "VERGE_PASSWORD": "your-password"
      }
    }
  }
}

You run a Model Context Protocol (MCP) server that lets AI assistants manage VergeCMS content directly through natural language. This server exposes tools for authenticating users, managing blogs, and handling articles, enabling end-to-end CMS operations from tools in AI chat interfaces.

How to use

Use a compatible MCP client (such as Claude Desktop or ChatGPT) to connect to the Verge MCP Server. You will access 14 tools that cover authentication, blog management, and article management. You can ask the AI to create blogs, list and edit blogs, draft articles, publish them, and manage authors and categories. The client will invoke the corresponding tools and handle responses, errors, and retries automatically.

How to install

Prerequisites you need before installation are Node.js version 18.0.0 or newer and a VergeCMS account. You also need an MCP client such as Claude Desktop or ChatGPT to connect to the server.

Clone the project, install dependencies, and build the server with these steps:

git clone https://github.com/tomohirof/verge-mcp-server.git
cd verge-mcp-server

npm install

# Build for production or local run
npm run build

Additional configuration and startup details

You can run the MCP server locally and configure your MCP client to connect via a local stdio channel. The recommended runtime uses Node to execute the built index file and pass the Verge API URL to the server.

Configure the MCP client with the local server command and environment variable as shown in the example below.

{
  "mcpServers": {
    "verge_mcp": {
      "type": "stdio",
      "command": "node",
      "args": ["/absolute/path/to/verge-mcp-server/dist/index.js"],
      "env": {
        "VERGE_API_URL": "https://api.vergecms.io"
      }
    }
  }
}

Security and credential handling

The MCP server supports a three-step authentication flow. A browser-based login can be used to obtain a token, which is stored locally for automatic use in subsequent sessions.

Troubleshooting and notes

If you encounter a token expiry, re-authenticate to refresh the token. Ensure the Verge API URL is correct and that any browser-based authentication flow is functioning. If issues persist, verify the MCP client configuration paths and restart the client after applying changes.

Available tools

verge_login

Authenticate with VergeCMS and obtain a JWT token. Supports optional email/password input or workflow via browser authentication.

verge_get_current_user

Retrieve information about the currently authenticated user.

verge_update_user

Update user profile details such as name, email, or password.

verge_list_blogs

List all blogs accessible to the authenticated user.

verge_get_blog

Fetch details for a specific blog by its ID.

verge_create_blog

Create a new blog with a name, title, slug, and optional description.

verge_update_blog

Update an existing blog's properties such as name, title, slug, or description.

verge_delete_blog

Delete a blog by its ID.

verge_list_articles

List articles in a blog with optional search, filters by status, categories, and tags.

verge_get_article

Get the details of a specific article by its ID and blog ID.

verge_create_article

Create a new article with title, content (Markdown), slug, and optional metadata like status, featured image, excerpt, author, categories, and tags.

verge_update_article

Update an existing article with new title, content, slug, status, or metadata.

verge_publish_article

Publish an article to make it publicly visible.

verge_delete_article

Delete an article by its ID and blog ID.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational