How to Use the Hive AI MCP in Claude Code
Run headless moderation checks on your build artifacts using Claude Code.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Hive AI MCP to Claude Code
Create your Vinkius account to connect Hive AI 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.
Scan pull requests for synthetic media
The `detect_ai_generated_text` tool identifies LLM-written copy inside your documentation or codebase. You run Claude Code in your terminal, point it at a PR, and it flags generated filler. This keeps your technical docs human-readable and accurate. If a PR includes new assets, the `detect_ai_generated_image` tool checks the image URLs for generative artifacts. Claude Code executes this entirely headless. You pipe the output straight into your CI/CD pipeline to block synthetic commits automatically.
Automate compliance checks in CI/CD
The `moderate_text` tool analyzes strings for compliance violations directly from your shell. SREs don't have time to review localization files manually. You script Claude Code to read your JSON language packs and run the text moderation tool across every value. The `moderate_image` tool handles the visual side by scoring public URLs against safety policies. Claude Code can pull every image link from your staging environment and verify them in one terminal command. It fails the build if anything violates your threshold.
Script video checks via Claude Code MCP Server
The `moderate_video_async` tool dispatches large video files for processing and hands back a task ID. Video moderation blocks CI pipelines if you wait synchronously. Claude Code triggers the scan and exits, letting your other tests run. A separate cron job uses the `get_async_task_status` tool to check on the video processing. Once complete, your terminal script pulls the results and updates the database. You get heavy media moderation without tying up your deployment runners.
Set up Hive AI 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 userto make it available across all projects. - 2
Verify the connection
Start a Claude Code session and type
/mcpto list connected servers. You should seehive-ai-mcpwith a green status indicator. - 3
Start using tools
Ask Claude Code something like "Check my latest Hive AI transactions." It will automatically discover and invoke the available Hive AI tools.
claude mcp add --transport http hive-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
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 Hive AI MCP in Claude Code
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Hive AI MCP today
We host it, we monitor it, we maintain it. You just paste one token.