How to Use the GatherContent MCP in Claude Code

Q: How do I add the GatherContent MCP server to Claude Code?

Run claude mcp add --transport http gathercontent -- in your terminal. Make sure all flags come before the server name. Claude Code stores this configuration in your /.claude.json file.

Q: Can Claude Code fetch GatherContent templates for my backend?

Yes. The agent uses the gettemplateschema tool to pull the raw field definitions. You can then instruct it to generate database models based on those exact constraints.

Q: Can Claude Code use the GatherContent MCP server in a CI/CD pipeline?

Yes. Claude Code runs headless, so you can trigger updatecontentitem from a GitHub Action to sync CMS statuses when your code deploys.

Q: How does Claude Code handle GatherContent project structures?

It maps the hierarchy using listcontentprojects and listprojectfolders. The agent navigates the tree programmatically to locate the specific items your script needs.

Pipe GatherContent data straight into your terminal with Claude Code to automate headless CMS migrations and syncs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GatherContent MCP to Claude Code

Create your Vinkius account to connect GatherContent to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup GatherContent with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Claude Code Pipeline Automation

Extracting bulk text records directly from the command line relies on the `list_project_items` and `get_item_content` tools. You can script Claude Code to pull an entire folder of drafts and pipe that output into your static site generator build process. There is no GUI to slow you down. The agent runs `list_content_projects` to find the target workspace, grabs the copy, and writes it to your local markdown files. Manual content exports become a single terminal command.

Headless Schema Extraction

Exposing the raw field definitions for any content type requires `get_template_schema` from the MCP server. When you write database migrations or set up new backend models, your agent fetches the exact CMS constraints to ensure your database schema matches. It maps out text limits, required fields, and data types. Claude Code then takes that JSON output and generates the corresponding SQL tables or Prisma schemas. You eliminate the guesswork between the content platform and your backend.

Programmatic State Updates

Mutating content records from a CI/CD pipeline is handled by `update_content_item`. If a deployment succeeds, you can have your agent automatically move all related release notes to the 'Published' state. It first runs `list_workflow_statuses` to grab the correct transition IDs. Then it fires the updates and confirms success via `get_project_details`. Your content operations stay perfectly synchronized with your deployment schedule.

Setup guide

Set up GatherContent MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see gathercontent-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest GatherContent transactions." It will automatically discover and invoke the available GatherContent tools.

Terminal

claude mcp add --transport http gathercontent-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the GatherContent MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "gathercontent-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 GatherContent. 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 GatherContent 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 GatherContent MCP in Claude Code

Run `claude mcp add --transport http gathercontent -- ` in your terminal. Make sure all flags come before the server name. Claude Code stores this configuration in your `~/.claude.json` file.

Yes. The agent uses the `get_template_schema` tool to pull the raw field definitions. You can then instruct it to generate database models based on those exact constraints.

Yes. Claude Code runs headless, so you can trigger `update_content_item` from a GitHub Action to sync CMS statuses when your code deploys.

It maps the hierarchy using `list_content_projects` and `list_project_folders`. The agent navigates the tree programmatically to locate the specific items your script needs.

The server processes workflow states, folder structures, and plain text drafts. All data routes through an isolated sandbox that drops memory after execution. Your terminal only retains the final output, keeping the raw connection token secure and out of your shell history.

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