How to Use the HiFlow MCP in Claude Code

Q: How do I install the HiFlow MCP server in Claude Code?

Run claude mcp add --transport http hiflow-mcp -- in your terminal. Make sure you put all flags before the server name. Verify the installation with claude mcp list.

Q: Does Claude Code handle pagination for HiFlow timesheets?

It handles the raw output from listtimesheets. You can prompt the agent to loop through pages if the dataset exceeds the single-request limit.

Q: How do I check a specific estimate?

Invoke the getestimate tool with the required ID. The terminal will output the raw JSON data for that specific quote.

Q: How safe are my job and estimate records in the terminal?

Your requests to getjob and getestimate require only a single endpoint token. The infrastructure relies on stateless execution. Once the terminal receives the payload, the backend session vanishes entirely, leaving no trace of your project specs.

Manage your HiFlow jobs and timesheets straight from the terminal with 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 HiFlow MCP to Claude Code

Create your Vinkius account to connect HiFlow 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 HiFlow with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query the HiFlow MCP Server in CI/CD

The `list_jobs` and `get_job` tools allow your terminal agent to pull active project statuses during automated builds. You can write shell scripts that check job completion before deploying specific environments. Claude Code grabs the exact job ID and pipes it into your next command. If a deployment fails, it can run `get_activity` to see if someone changed the project scope in the last ten minutes.

Audit invoices from the command line

The `list_invoices` and `get_invoice` tools expose your billing data to headless cron jobs. You can instruct your AI client to scan for unpaid invoices every Friday at 5 PM. It cross-references those invoices with `list_estimates` to find discrepancies. The agent processes the JSON output and pipes a summary directly to your Slack webhook or a local text file.

Script bulk customer operations

The `create_customer` and `list_customers` tools let you write bash scripts that sync clients from your internal database. Claude Code handles the API mapping and executes the creations sequentially. It also pulls `list_timesheets` and `get_me` to verify that the API user has the right permissions to log hours. You get raw, actionable data without ever touching a graphical interface.

Setup guide

Set up HiFlow 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 hiflow-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http hiflow-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 HiFlow 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": {
    "hiflow-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 HiFlow. 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 HiFlow 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 HiFlow MCP in Claude Code

Run `claude mcp add --transport http hiflow-mcp -- ` in your terminal. Make sure you put all flags before the server name. Verify the installation with `claude mcp list`.

Yes. Since it operates headlessly, you can schedule commands that trigger `list_invoices` or `get_activity` on a timer.

It handles the raw output from `list_timesheets`. You can prompt the agent to loop through pages if the dataset exceeds the single-request limit.

Invoke the `get_estimate` tool with the required ID. The terminal will output the raw JSON data for that specific quote.

Your requests to `get_job` and `get_estimate` require only a single endpoint token. The infrastructure relies on stateless execution. Once the terminal receives the payload, the backend session vanishes entirely, leaving no trace of your project specs.

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