How to Use the Tower MCP in Claude Code

Q: How do I check project details using Tower and Claude Code?

You execute getproject via a shell script. The output is standard JSON, which you can then pipe into tools like jq or process it further within your CI pipeline.

Q: Can I update tasks with Tower and Claude Code?

Yes. Use updatetask in a non-interactive script environment. This allows automated workflow changes, such as moving task statuses from 'In Progress' to 'Review' upon successful build completion.

Q: What is the best way to list available teams using Tower and Claude Code?

Simply run listteams in your pipeline. This provides a clean, machine-readable output of all defined teams, which you can use for conditional logic checks.

Q: Does Tower and Claude Code handle discussions?

It does. You can programmatically run listdiscussions to gather historical context needed for post-mortem analysis or audit logs, all without needing a graphical interface.

Automate project workflows headless: Run Tower tasks in CI/CD pipelines using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tower MCP to Claude Code

Create your Vinkius account to connect Tower 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 Tower with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Batch task management for CI.

Don't rely on manual status checks. Set up a cron job to run `list_tasks` across every project ID. The output pipes directly into your logging tool, giving you an auditable record of all tasks. Need to enforce updates? A pipeline can call `update_task` for compliance reasons. Claude Code handles the authentication and ensures the change is recorded via the terminal.

Project metadata extraction.

Use this MCP Server in a CI/CD build step to check project scope. The pipeline runs `list_projects` to confirm which repositories are active before deployment. It then uses `get_project` to pull specific identifiers. This is key for validation scripts, making sure all necessary resources defined by Tower are present and accounted for.

Team roster verification.

Before a major release, you need confirmation on who's involved. Run `list_members` to generate an immutable list of current team users. You can pipe this output directly into an access control system. Similarly, `list_teams` allows your script to validate that all required departmental groups are active and accessible in the target environment.

Setup guide

Set up Tower 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 tower-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http tower-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 Tower 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": {
    "tower-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 Tower. 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 Tower 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 Tower MCP in Claude Code

You execute `get_project` via a shell script. The output is standard JSON, which you can then pipe into tools like jq or process it further within your CI pipeline.

Yes. Use `update_task` in a non-interactive script environment. This allows automated workflow changes, such as moving task statuses from 'In Progress' to 'Review' upon successful build completion.

Simply run `list_teams` in your pipeline. This provides a clean, machine-readable output of all defined teams, which you can use for conditional logic checks.

It does. You can programmatically run `list_discussions` to gather historical context needed for post-mortem analysis or audit logs, all without needing a graphical interface.

You access tasks, projects, discussions, members, teams, and document folders. Everything is exposed as structured data via the command line, perfect for automated processing in any script.

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