How to Use the Mode Analytics MCP in Claude Code

Q: Can I run a Mode Analytics report in a CI/CD pipeline with Claude Code?

Yes, you can trigger runmodereport within headless environments using Claude Code. The CLI agent executes the tool, polls the run status, and exits with a non-zero code if the run fails.

Q: How does Claude Code fetch SQL queries from Mode Analytics?

Claude Code calls the listmodequeries tool to fetch raw SQL query definitions. It displays them in the terminal or writes them to a file for easy debugging.

Q: What is the fastest way to register the Mode Analytics MCP Server in Claude Code?

Run claude mcp add --transport http mode-analytics -- in your terminal. This registers the server inside your local /.claude.json configuration file instantly.

Q: Does this server support tracking multiple parallel report runs?

Yes, the listmodereportruns tool allows you to monitor all active and historical runs for a specific report. You can filter and inspect individual runs using getmodereportrun.

Run Mode Analytics reports and audit SQL pipelines straight from your terminal using Claude Code CLI commands.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mode Analytics MCP to Claude Code

Create your Vinkius account to connect Mode Analytics 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 Mode Analytics with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate report pipelines via Claude Code

The `run_mode_report` tool, acting as a core MCP utility, triggers data runs directly from your command-line interface. By combining this with `get_mode_report_run`, you can script automated checks that verify if your pipelines succeeded. This replaces complex API curl commands in your bash scripts. You can pipe the terminal output directly into downstream systems or trigger alerts if a critical run fails.

Query workspace status and account details

The `get_mode_account` tool retrieves the authenticated connection details to verify your API credentials. To audit system access, the CLI agent calls `list_mode_members` to dump the list of active users. This makes compliance audits fast and scriptable. You can verify who has access to your data spaces without opening a browser or digging through complex admin consoles.

Inspect SQL assets using this terminal MCP Server

The `list_mode_queries` tool dumps the SQL statements of any report directly into your stdout stream. For deeper debugging, the agent uses `list_mode_definitions` to print calculated field logic directly to your console. You get raw, unformatted text that you can grep, diff, or redirect into local SQL files. It simplifies tracing data lineage and debugging broken database queries from your terminal.

Setup guide

Set up Mode Analytics 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 mode-analytics-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http mode-analytics-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 Mode Analytics 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": {
    "mode-analytics-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 Mode Analytics. 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 Mode Analytics 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 Mode Analytics MCP in Claude Code

Yes, you can trigger `run_mode_report` within headless environments using Claude Code. The CLI agent executes the tool, polls the run status, and exits with a non-zero code if the run fails.

Claude Code calls the `list_mode_queries` tool to fetch raw SQL query definitions. It displays them in the terminal or writes them to a file for easy debugging.

Run `claude mcp add --transport http mode-analytics -- ` in your terminal. This registers the server inside your local `~/.claude.json` configuration file instantly.

Yes, the `list_mode_report_runs` tool allows you to monitor all active and historical runs for a specific report. You can filter and inspect individual runs using `get_mode_report_run`.

The integration is highly secure because it runs within Vinkius's ephemeral, zero-trust V8 sandbox. Your sensitive database credentials and query definitions are never stored on disk or exposed to other processes.

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