How do I use supos MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@supos MCP Server Search topics by tag 'sensor'" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

supos MCP Server

by zantiu

Overview Schema Related Servers Score Discussions

Remote

supOS MCP Server

本MCP服务器是基于Model Context Protocol (MCP)[https://modelcontextprotocol.io/introduction]协议提供的typescript-sdk进行开发，可以让任何支持MCP协议的客户端使用它。它提供了一系列supOS open-api的功能，例如：查询topic树结构，topic详情等。

接下来跟随文档一起使用吧

系统要求

本服务基于typescript-sdk开发，需要具备Node.js环境

Tools

get-model-topic-tree
- 查询topic 树结构菜单数据
- 输入:
  - key (string): Fuzzy search keyword for child nodes
  - showRec (string): Number of records to display
  - type (string): Search type: 1--Text search, 2--Tag search
- 返回: topic 树结构菜单数据
get-model-topic-detail
- 获取某个topic详情
- 输入:
  - topic (string): The topic path corresponding to the model
- 返回: 某个topic详情
get-topic-realtime-data
- 获取某个topic的实时数据
- 输入:
  - topic (string): The topic path corresponding to the model
- 返回: 某个topic实时数据
get-all-topic-realtime-data
- 获取所有topic的实时数据并分析
- 返回: 所有topic实时数据

接下来跟随文档一起使用吧

Related MCP server: Safie API MCP Server

开始使用

系统要求

Node.js

安装客户端

目前支持MCP协议的客户端已有很多，比如桌面端应用 Claude for Desktop，或者IDE的一些插件等（VSCode 的 Cline 插件），想了解已支持的客户端可访问 Model Context Protocol Client。

这里以 Claude for Desktop 为例。

下载 Claude for Desktop。
为 Claude for Desktop 配置所需的MCP 服务器。
- 在文本编辑器中打开您的 Claude for Desktop 配置：~/Library/Application Support/Claude/claude_desktop_config.json。
- 也可以通过 File -> Setting -> Developer 点击 Edit Config 找到该配置文件位置：

打开配置文件后，添加以下内容到 claude_desktop_config.json中，并重启应用:
注意：每次修改该配置文件后都需要重启应用才会生效。

{
  "mcpServers": {
    "supos": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-supos"
      ],
      "env": {
        "SUPOS_API_KEY": "<API_KEY>",
        "SUPOS_API_URL": "<API_URL>",
        "SUPOS_MQTT_URL": "<MQTT_URL>"
      }
    }
  }
}

- 其中 API_URL 是可访问的supOS社区版地址。API_KEY 可通过登录社区版后，进入 DataModeling -> 查看某个具体的topic详情 -> Data Operation -> Fetch，找到对应的ApiKey复制即可，MQTT_URL可通过访问 UNS -> MqttBroker -> Listeners 查看可订阅的地址。
NODE

由于Windows环境下npx执行可能有环境变量的问题，可以先本地安装mcp-server-supos包，再用node本地执行：

npm install mcp-server-supos -g

{
  "mcpServers": {
    "supos": {
      "command": "node",
      "args": [
        "C://Users//xxx//AppData//Roaming//npm//node_modules//mcp-server-supos//dist//index.js"
      ],
      "env": {
        "SUPOS_API_KEY": "<API_KEY>",
        "SUPOS_API_URL": "<API_URL>",
        "SUPOS_MQTT_URL": "<MQTT_URL>"
      }
    }
  }
}

2.下载该项目本地执行

Install

npm ci

Build

npm run build

{
  "mcpServers": {
    "supos": {
      "command": "node",
      "args": [
        "<本地项目地址>//dist//index.js"
      ],
      "env": {
        "SUPOS_API_KEY": "<API_KEY>",
        "SUPOS_API_URL": "<API_URL>",
        "SUPOS_MQTT_URL": "<MQTT_URL>"
      }
    }
  }
}

结语

以上就是使用该服务的全部教程，配置成功后可在以下面板中看到对应的服务和工具等： alt text

最后的最后

supOS社区版已集成 CopilotKit 作者开源的 open-mcp-client，并内置了 mcp-server-supos 服务，且支持ts版本的 agent，源码可访问 supOS-CE-McpClient。

Available Tools

4 tools

get-all-topic-realtime-dataD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get-model-topic-detailD

ParametersJSON Schema

Name	Required	Description	Default
`topic`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get-model-topic-treeD

ParametersJSON Schema

Name	Required	Description
`key`	No	Fuzzy search keyword for child nodes
`showRec`	No	Is show recommend topic
`type`	No	Search type: 1--Text search, 2--Tag search

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get-topic-realtime-dataD

ParametersJSON Schema

Name	Required	Description	Default
`topic`	Yes

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.6.0May 29, 2026
- First observedget-all-topic-realtime-data
- First observedget-model-topic-detail
- First observedget-model-topic-tree
- First observedget-topic-realtime-data

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

D1.6/5.0

Disambiguation2/5

The tools 'get-all-topic-realtime-data' and 'get-topic-realtime-data' are easily confused, as both relate to realtime data with only a quantifier difference. Similarly, 'get-model-topic-detail' and 'get-model-topic-tree' are distinct but an agent might struggle without descriptions. Overlap between tool purposes is unclear.

Naming Consistency3/5

All tool names start with 'get-' and use hyphens, but the structure varies: some include 'all-topic', others 'model-topic', and suffixes differ ('realtime-data', 'detail', 'tree'). The pattern is somewhat consistent but not fully uniform.

Tool Count4/5

With 4 tools, the scope feels slightly thin but reasonable for a focused server that likely provides read-only access to realtime and model topic data. No strong evidence of over- or under-scoping.

Completeness3/5

The toolset covers reading realtime data (all and specific) and model topic details/tree, but lacks create, update, or delete operations. It is a reasonable read-only surface, though missing a generic 'list topics' tool is a minor gap.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Algenta MCP Server C
io.github.thyn-ai
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Data Platforms Search RAG Systems
1402
meok-abci-bridge-mcp
io.github.CSOAI-ORG
MEOK ABCI Bridge MCP — read-only Tendermint / Cosmos blockchain query for agents. Built-in registry
Blockchain Web3 & Decentralized Tech
2
Plato's Kallipolis A
io.github.handongzhen101-jpg
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
Agent Orchestration AI & Machine Learning
41
SeekOnMe Product Discovery
me.seekon.fast
Remote MCP server for product discovery catalog and retrieving product details.
E-commerce & Retail Search
2

Related MCP Servers

OPC UA MCP Server
Monitoring Networking & Infrastructure
vogler75
A
license
Not graded
quality
D
maintenance
Connects to any OPC UA server and exposes its node tree and data via MCP, with tools to read values and search nodes.
Updated a year ago (2025-07-24 18:32 UTC)
5
MIT
Safie API MCP Serverofficial
Home Automation & IoT Location Services
SafiePublic
A
license
Not graded
quality
D
maintenance
Enables to retrieve device information, images, media, location, thumbnails, and events from the Safie API through MCP.
Updated a year ago (2025-04-24 08:37 UTC)
6
MIT
Toss Invest MCP
Finance
takeachangs
F
license
A
quality
C
maintenance
Enables MCP clients to read Toss Securities market data and account info, and optionally place real-money orders.
Updated 2 months ago (2026-06-23 01:34 UTC)
20
-
akshare-mcp
Finance Data Platforms Research & Data
terrysun1216
A
license
A
quality
B
maintenance
Provides access to Chinese A-share market financial data, including historical K-line, real-time quotes, financial statements, shareholder information, and technical indicators, via MCP protocol.
Updated 2 months ago (2026-07-13 05:49 UTC)
12
69
3
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zantiu/mcp-server-supos'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

supOS MCP Server

系统要求

Tools

开始使用

系统要求

安装客户端

2.下载该项目本地执行

结语

最后的最后

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Safie API MCP Serverofficial

Latest Blog Posts

MCP directory API