How to Use the Sally MCP in Claude Code

Q: How do I add the Sally MCP Server to Claude Code?

Run claude mcp add --transport http sally-mcp -- in your terminal. Claude Code will save the configuration to your /.claude.json file and verify the 12 Sally tools are active.

Q: How does Claude Code display a Sally project board?

Claude Code calls getboard to pull the Kanban layout. It then prints a structured text representation of the columns and tasks right inside your terminal.

Q: Can I comment on frontline tasks using Claude Code?

Yes. Tell Claude Code to add a note, and it will execute addcomment with your text. The comment is instantly visible to the mobile team working in the field.

Q: How does the Sally MCP Server secure our project and task data in Claude Code?

Every request to getproject or listtasks goes through the secure Vinkius V8 sandbox. This ensures your operational project data is fetched ephemerally, never cached on disk, and accessible only to your authenticated terminal session.

Pipe frontline task data and timesheets directly into your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sally MCP to Claude Code

Create your Vinkius account to connect Sally to Claude Code — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sally with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Command-line task updates via Claude Code

The `list_tasks` tool lets you query active frontline tickets directly from your shell. Claude Code runs this tool to filter Sally tasks by project ID, dumping the raw status of your deskless team straight to stdout. You can pipe this output to grep or local scripts. If you need to make changes, tell Claude Code to run `update_task` to modify Sally priorities or statuses without leaving your SSH session.

Automated terminal-based timesheet audits

The `get_timesheet_report` tool pulls frontline hours directly into your terminal environment. Claude Code executes this to run instant audits on Sally workspace hours, helping you spot anomalies without clicking through a web app. You can combine this with `get_profile` to match Sally hours with specific field technician accounts. It is a fast, keyboard-only way to verify work logs before running payroll scripts.

Scripting project setups with the Sally MCP Server

The `create_project` tool allows Claude Code to initialize frontline workspaces during CI/CD builds. When a deployment script finishes, Claude Code can automatically spin up a matching Sally operations project. It then runs `create_task` to assign post-deployment checks to the on-call field team. This bridges the gap between your server deployments and your physical Sally operations.

Setup guide

Set up Sally 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 sally-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http sally-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 Sally 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": {
    "sally-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 Sally. 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 Sally 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 Sally MCP in Claude Code

Run `claude mcp add --transport http sally-mcp -- ` in your terminal. Claude Code will save the configuration to your `~/.claude.json` file and verify the 12 Sally tools are active.

Yes. You can ask Claude Code to verify the connection, which triggers the `check_sally_health` tool. It returns the status of the frontline communication API directly in your terminal.

Claude Code calls `get_board` to pull the Kanban layout. It then prints a structured text representation of the columns and tasks right inside your terminal.

Yes. Tell Claude Code to add a note, and it will execute `add_comment` with your text. The comment is instantly visible to the mobile team working in the field.

Every request to `get_project` or `list_tasks` goes through the secure Vinkius V8 sandbox. This ensures your operational project data is fetched ephemerally, never cached on disk, and accessible only to your authenticated terminal session.

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