Name: TagoIO
Author: tago-io

LABSCO SUMMARY

The debugging loop is the reason to install it.

Reading a device list is table stakes. What is unusual here is that the analysis console, the script upload and the single test run are all reachable from the same conversation, so "why did the daily report fail" ends with a fix that ran, not with a stack trace you go paste somewhere. Token choice is the real access decision: a Profile Token reaches your whole profile, while an Analysis token is scoped by IAM and is the one that belongs in a shared or production setup.

What it is

TagoIO's own server for its IoT platform. Your assistant reads devices, data, dashboards and analyses, and makes the changes you ask for, from your IDE or chat client.

What you get

Fleet work: list devices, find the ones that stopped sending, read recent records from a device, create a device on a network and get its token
Debugging without tab-switching: read an analysis console to find out why last night's run failed, upload the fixed script, and run it once to confirm
Dashboard building from a description — a map of units, a temperature line chart, a card for battery level — and comparing a widget's configuration against the variables a device actually sends
Permissions: work out which policy an analysis needs to write to an entity, and list every access policy touching TagoRUN users
Account housekeeping: check how close you are to a data-records limit, or find and delete stored files by age and size
Official code examples for payload parsers, found and adapted to your device
Writes go through your client's confirmation flow, so deletes, credential rotation and script uploads are approved before they land

Requirements

A TagoIO Profile Token from your profile settings, and the hosted server at https://mcp.ai.tago.io. Requests go to US East by default; set an x-tagoio-region header to eu-w1, or to a full API endpoint for a dedicated TagoDeploy instance. Analysis and Device tokens work too, with correspondingly narrower reach. To run it yourself, the npm package @tago-io/mcp-server, version 4.0.0, over npx with TAGOIO_TOKEN; over stdio there are no headers, so set TAGOIO_API instead.

Setup effort

One command plus a key — npx -y @tago-io/mcp-server, then supply credentials

See installation options

USE CASES

01

Finding the devices that went quiet

Ask which ones stopped sending data this week and read back the last records from one of them.

search_devicesget_deviceread_device_data

02

Fixing a failed analysis

Read the console, find the cause, upload the corrected script and run it once to confirm.

read_analysis_consoleget_analysisupdate_analysisupload_analysis_scriptrun_analysis

03

Building a dashboard from a sentence

Describe the widgets you want and get them created, then compare a silent gauge against what the device actually sends.

create_dashboardcreate_widgetwidget_schema_lookupvalidate_widget_configuration

04

Untangling a permission error

Ask which policy an analysis needs to write to an entity instead of trial-and-error in the UI.

search_access_policiesget_access_policylookup_access_permissionscreate_analysis_access_policy

81 tools

Listed in project docs. Your client may show a different list.

search_devices

get_device

create_device

update_device

delete_device

configure_device

read_device_data

send_device_data

edit_device_data

delete_device_data

search_actions

get_action

create_action

update_action

delete_action

BEFORE YOU INSTALL

What to know first

Tools you get

81 tools named in the project's documentation.

Requires

npx on PATH
TAGOIO_TOKEN in your environment

INSTALLATION

Connect your client

Server setup

npx

TERMINAL

npx -y @tago-io/mcp-server

Hosted endpoint

ENDPOINT URL

https://mcp.ai.tago.io

Add this hosted endpoint to your MCP client using the credentials listed under Requirements.

MCP Clients

GitHub Copilot in VS Code

GITHUB COPILOT IN VS CODE · JSON

{
  "servers": {
    "@tago-io/mcp": {
      "type": "http",
      "url": "https://mcp.ai.tago.io",
      "headers": {
        "Authorization": "Bearer ${input:tagoToken}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "tagoToken",
      "description": "TagoIO Profile Token",
      "password": true
    }
  ]
}

Claude Code

CLAUDE CODE · TERMINAL

claude mcp add-json tagoio '{"type":"http","url":"https://mcp.ai.tago.io","headers":{"Authorization":"Bearer <YOUR_TAGOIO_TOKEN>"}}'

Claude Desktop, Warp, Kiro

JSON

{
  "mcpServers": {
    "@tago-io/mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.ai.tago.io",
        "--header",
        "Authorization: Bearer <YOUR_TAGOIO_TOKEN>"
      ]
    }
  }
}

Cursor, Amazon Q

JSON

{
  "mcpServers": {
    "@tago-io/mcp": {
      "url": "https://mcp.ai.tago.io",
      "headers": {
        "Authorization": "Bearer <YOUR_TAGOIO_TOKEN>"
      }
    }
  }
}

Windsurf

WINDSURF · JSON

{
  "mcpServers": {
    "@tago-io/mcp": {
      "serverUrl": "https://mcp.ai.tago.io",
      "headers": {
        "Authorization": "Bearer <YOUR_TAGOIO_TOKEN>"
      }
    }
  }
}

JetBrains IDEs

JETBRAINS IDES · JSON

{
  "servers": {
    "@tago-io/mcp": {
      "url": "https://mcp.ai.tago.io",
      "requestInit": {
        "headers": {
          "Authorization": "Bearer <YOUR_TAGOIO_TOKEN>"
        }
      }
    }
  }
}

Gemini CLI

GEMINI CLI · JSON

{
  "mcpServers": {
    "@tago-io/mcp": {
      "httpUrl": "https://mcp.ai.tago.io",
      "headers": {
        "Authorization": "Bearer <YOUR_TAGOIO_TOKEN>"
      }
    }
  }
}

ChatGPT, OpenAI Agents

Server URL: https://mcp.ai.tago.io

Protocol: Streamable HTTP

Authentication: header Authorization: Bearer <YOUR_TAGOIO_TOKEN>, with your TagoIO Profile Token

Any MCP client — stdio

ANY MCP CLIENT — STDIO · JSON

{
  "mcpServers": {
    "@tago-io/mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tago-io/mcp-server"
      ],
      "env": {
        "TAGOIO_TOKEN": "<YOUR_TAGOIO_TOKEN>"
      }
    }
  }
}

Claude Code — stdio

CLAUDE CODE — STDIO · TERMINAL

claude mcp add @tago-io/mcp-server -e TAGOIO_TOKEN=<YOUR_TAGOIO_TOKEN> -- npx -y @tago-io/mcp-server

TagoIO