World Monitor
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 97 tools.
Humanoid robot intelligence: observed capabilities, BOM supply chain, pilot prep. Free and paid.
Pick the AI app you use, then copy the settings.
Passed 4/4 checks · What you ask goes through the maker’s server (mcp.roboselect360.com) · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 2 min
No key, nothing to install · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
CustomizeConnectors
Copy each value into the field with the same name in Claude, then click Continue
RoboSelect360 - Independent Humanoid Robot Intelligencehttps://mcp.roboselect360.com/mcpClick Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add
+ConnectorsRoboSelect360 - Independent Humanoid Robot Intelligence
Use RoboSelect360 - Independent Humanoid Robot Intelligence and tell me what you can do for me, then show me one thing✓ If Claude says it is using RoboSelect360 - Independent Humanoid Robot Intelligence or shows a RoboSelect360 - Independent Humanoid Robot Intelligence tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with ChatGPT, depending on your plan
Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only
Plugins+Add custom MCP server
Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin
RoboSelect360 - Independent Humanoid Robot Intelligencehttps://mcp.roboselect360.com/mcpStart a new chat and pick RoboSelect360 - Independent Humanoid Robot Intelligence from your plugins before typing
Use RoboSelect360 - Independent Humanoid Robot Intelligence and tell me what you can do for me, then show me one thing✓ If ChatGPT says it is using RoboSelect360 - Independent Humanoid Robot Intelligence or shows a RoboSelect360 - Independent Humanoid Robot Intelligence tool in the answer, you are connected
Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Claude Code · about 2 min
No key, nothing to install
Mac: press Command+Space and type Terminal · Windows: open PowerShell
claude mcp add --transport http --scope user humanoid-robots https://mcp.roboselect360.com/mcpYou should see RoboSelect360 - Independent Humanoid Robot Intelligence listed as connected
Use RoboSelect360 - Independent Humanoid Robot Intelligence and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using RoboSelect360 - Independent Humanoid Robot Intelligence or shows a RoboSelect360 - Independent Humanoid Robot Intelligence tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor · about 2 min
No key, nothing to install
Use RoboSelect360 - Independent Humanoid Robot Intelligence and tell me what you can do for me, then show me one thing✓ If Cursor says it is using RoboSelect360 - Independent Humanoid Robot Intelligence or shows a RoboSelect360 - Independent Humanoid Robot Intelligence tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code · about 2 min
No key, nothing to install
Use RoboSelect360 - Independent Humanoid Robot Intelligence and tell me what you can do for me, then show me one thing✓ If VS Code says it is using RoboSelect360 - Independent Humanoid Robot Intelligence or shows a RoboSelect360 - Independent Humanoid Robot Intelligence tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
Address for apps that connect over the web
https://mcp.roboselect360.com/mcpJSON settings are under “For developers” below
Claude Code
claude mcp add --transport http --scope user humanoid-robots https://mcp.roboselect360.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"humanoid-robots": {
"url": "https://mcp.roboselect360.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"humanoid-robots": {
"type": "http",
"url": "https://mcp.roboselect360.com/mcp"
}
}
}Descriptions are as written by the maker.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Connect over the internet in
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
Tool names and descriptions exactly as the server reported them on Nov 9, 2026. The maker wrote them, not us; we show them as plain text.
hardware_get_system_statusHealth of the SEMICONDUCTOR layer: profiles loaded, semiconductor signal counts, load errors. One status tool per layer - the three report different layers, not the same server.
hardware_list_robotsList the robot catalogue with filters, including semiconductor-layer scope and payload. Returns the same catalogue as the mechanical and software variants - call one, not three. Pick this one to filter on whether a robot is in scope for the semiconductor layer.
hardware_get_robotCommercial profile of one robot (specs, pricing, viability score), plus whether a per-robot semiconductor bill of materials exists for it. The commercial fields are identical in all three get_robot variants - the layer flag is the only difference. Also returns observed_capabiliti
hardware_list_signalsList semiconductor supply chain, performance and operational signals across the panel, with filters. Panel-wide, not per robot: requires an access right on at least one robot.
hardware_get_robot_signalsActive supply chain signals affecting one robot's semiconductor BOM. Requires an access right on the robot requested.
hardware_get_block_analysisAnalyse one functional block of the semiconductor layer, for a single robot at a time. Requires an access right on the robot named, or on at least one robot when none is.
hardware_compare_robotsCompare 2 to 5 robots side by side on semiconductor BOM, metrics, risk and geographic exposure. Requires an access right on EVERY robot listed; if one is missing the call returns a refusal naming it, and compares nothing.
hardware_get_dependency_profileGeopolitical and supply chain dependency analysis for one robot, built on its semiconductor BOM: geographic concentration, single-source exposure, export control. Requires an access right on the robot requested.
hardware_get_robot_hardwareSemiconductor bill of materials for one robot: functional blocks, components, suppliers. Requires an access right on the robot requested; without it the call returns a refusal naming that robot.
mechanical_get_system_statusHealth of the MECHANICAL layer: mechanical profiles loaded, mechanical signal counts, load errors. One status tool per layer - the three report different layers, not the same server.
mechanical_list_robotsList the robot catalogue with filters, including mechanical-profile status and payload. Returns the same catalogue as the hardware and software variants - call one, not three. Pick this one to filter on mechanical coverage.
mechanical_get_robotCommercial profile of one robot (specs, pricing, viability score), plus its mechanical-profile status. The commercial fields are identical in all three get_robot variants - the layer flag is the only difference. Also returns observed_capabilities: the evidence label per capabilit
mechanical_list_signalsList mechanical supply chain, performance and operational signals across the panel, with filters. Panel-wide, not per robot: requires an access right on at least one robot.
mechanical_get_robot_signalsActive supply chain signals affecting one robot's mechanical BOM. Requires an access right on the robot requested.
mechanical_get_block_analysisAnalyse one mechanical block (actuation, structure, energy, perception), for a single robot at a time. Requires an access right on the robot named, or on at least one robot when none is.
mechanical_compare_robotsCompare 2 to 5 robots side by side on mechanical BOM, specifications, risk and geographic exposure. Requires an access right on EVERY robot listed; if one is missing the call returns a refusal naming it, and compares nothing.
mechanical_get_dependency_profileGeopolitical and supply chain dependency analysis for one robot, built on its mechanical BOM: geographic concentration, critical raw materials, single-source exposure. Requires an access right on the robot requested.
mechanical_get_robot_mechanicalMechanical bill of materials for one robot: motors, reducers, screws, bearings, batteries, structure, wiring. Requires an access right on the robot requested; without it the call returns a refusal naming that robot.
software_get_system_statusHealth of the SOFTWARE layer: software profiles loaded, software signal counts, load errors. One status tool per layer - the three report different layers, not the same server.
software_list_robotsList the robot catalogue with filters, including software tier and software-profile status. Returns the same catalogue as the hardware and mechanical variants - call one, not three. Pick this one to filter by software tier.
software_get_robotCommercial profile of one robot (specs, pricing, viability score), plus its software tier and profile status. The commercial fields are identical in all three get_robot variants - the layer flag is the only difference. Also returns observed_capabilities: the evidence label per ca
software_list_signalsList software supply chain signals across the panel, with filters. Panel-wide, not per robot: requires an access right on at least one robot.
software_get_robot_signalsActive supply chain signals affecting one robot's software stack. Requires an access right on the robot requested.
software_get_block_analysisAnalyse one software block (OS, middleware, runtime, control, fleet), for a single robot at a time. Requires an access right on the robot named, or on at least one robot when none is.
software_compare_robotsCompare 2 to 5 robots side by side on software BOM, TCO, jurisdiction exposure, lock-in and export control risk. Requires an access right on EVERY robot listed; if one is missing the call returns a refusal naming it, and compares nothing.
software_get_dependency_profileJurisdiction and supply chain dependency analysis for one robot, built on its software stack: jurisdiction concentration, lock-in, export control, cloud dependency. Requires an access right on the robot requested.
software_get_robot_softwareSoftware bill of materials for one robot: OS, middleware, AI runtime, motion control, fleet management. Requires an access right on the robot requested; without it the call returns a refusal naming that robot.
get_access_manifestWhat THIS connection can call right now: tools callable without any purchase, tools that need an access right, the robots you already hold, and the ones that can be unlocked. Free for everyone, no key and no account. Call it FIRST: it removes the need to discover your own access
get_robot_capabilitiesWhat one robot has actually been seen doing, and the evidence for each capability: a label per capability (in production, attested by a customer or third party, shown by the manufacturer, claimed only, published failure, no evidence found) and every dated observation behind it, f
get_robot_supportAfter-sales support profile of one robot, for a buyer in Europe: warranty duration, start and exclusions, spare parts with dated offers (seller, price in original currency, availability, lead time), maintenance required of the operator, software updates and subscriptions, service
prepare_pilotGuides a buyer, one question at a time, through the G.R.O.U.N.D. method to a needs sheet for a first humanoid robot pilot: their need structured, what the market has proven on their task (counted across the panel, no robot named), and the vigilance points their answers trigger. S
build_pilot_decision_filePaid follow-up of prepare_pilot. From the buyer's dossier (as returned by prepare_pilot) and 1 to 5 robots chosen by the buyer (robot_ids, from list_robots), returns the full pre-pilot decision file in markdown: decision memo, the robots' announced facts, an evidence matrix per r
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 14, 2026
The registry name was verified against the domain roboselect360.com (the registry checks domain ownership)
Code last changed 5 days ago
Not applicable: a cloud server run by the owner of roboselect360.com; you don't run code from the repo
Responded in 333 ms (HTTP 200)
No sign-in needed
Read 32 tool descriptions and found no hidden instructions to the AI
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
No reviews yet
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 4 of 4 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed 5 days ago, and the latest version (1.0.4) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).
In the same category: World Monitor, Claude Flow, Windmill
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 97 tools.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Independent intelligence on humanoid robots - proven capabilities, real cost, supply chain and bills of materials - available as an [MCP](https://modelcontextprotocol.io) server.
Humanoid robots are moving from the lab to the factory, but the information needed to decide remains scattered, unverifiable or written by the manufacturers themselves. RoboSelect360 is an independent player in the humanoid robot ecosystem: it helps industrial leaders, buyers, integrators and developers move from demonstration to deployment.
| Question | What RoboSelect360 answers with |
|---|---|
| What can this robot actually do? | Observed capabilities, each backed by a dated source - failures included, manufacturer claims never taken as proof |
| What does it really cost? | Specs, pricing, availability and viability scoring; buyer-side TCO and ROI |
| What is inside, and from where? | Semiconductor, mechanical and software bills of materials, with supply-chain and geopolitical dependency risk |
| What does regulation require? | Regulatory alerts by country of the site in the pilot preparation tool; readiness dossiers by country (EU, France, UK, US, China, India) |
Connect an MCP-compatible client and query the data directly - see Client support below.
No key, no account, no install. Paste one address into your MCP client.
https://mcp.roboselect360.com/mcp
Claude Desktop or claude.ai - Settings, Connectors, Add custom connector, paste the address. Leave the OAuth fields empty. All 32 tools appear immediately: 11 answer for free, the others name the robot to buy to access them.
Other MCP clients - same address, no header. Clients without a connector screen can go through mcp-remote (requires Node.js):
npx -y mcp-remote https://mcp.roboselect360.com/mcp
A free rbs_ key is still needed for the REST API (api.roboselect360.com, header X-API-Key). Request one at roboselect360.com/en/contact.html.
See QUICKSTART.md for step-by-step instructions and examples/ for sample calls.
Verified with real users: Claude (desktop and web) connects with no key, no account and no configuration file: the full connector URL is all that is required. ChatGPT (custom connector) and Codex (codex mcp add roboselect --url https://mcp.roboselect360.com/mcp) work the same way on the free tier, and so does Kimi. The URL must carry the /mcp path: the bare hostname returns 404 and the connector fails at "Connect to the server".
For paid access with an rbs_ key, Claude is the verified client (key in the connector's X-API-Key header). Passing the key from ChatGPT or Codex has not been validated yet. Perplexity connects on the free tier through OAuth (verified 2026-10-18): it receives public data only, so purchased robots cannot be opened from it.
The server is standard MCP over Streamable HTTP, so any client that accepts an unauthenticated remote server should work. If you get it running elsewhere, tell us at contact@roboselect360.com and we will document it.
All 32 tools are listed; 11 answer without a key - the robot catalogue, profiles and system status across the three teardown layers, plus the access manifest and the pilot preparation tool:
*_list_robots - the full robot catalogue*_get_robot - full commercial profile of one robot, with its observed-capability labels (the strength of the best evidence per capability)*_get_system_status - dataset coverage and freshnessget_access_manifest - what is open to you, and how to open the restprepare_pilot - the G.R.O.U.N.D. method: a needs sheet for a first humanoid robot pilot, one question at a time(where * is hardware_, mechanical_ or software_).
Paid access unlocks the deep layers - bill-of-materials teardowns, dependency profiles, geopolitical and critical-material risk, cross-robot comparison, the observed capabilities of each robot with every dated observation, and its after-sales support profile. It is sold per robot, €390 excl. VAT, at roboselect360.com/en/tarifs.html, and opens that robot's full analysis. You receive an rbs_ key: add it as the X-API-Key header of your connector, on the same address. The same key works on the REST API.
The pilot decision file (build_pilot_decision_file, the paid follow-up of prepare_pilot) opens with its own access right, separate from robot access: request it at roboselect360.com/en/prepare-a-robot-pilot.html.
Connector headers can only be set when the connector is created: to add your key, delete the free connector and create it again with the header. Keep a single RoboSelect360 connector - two connectors expose the same tool names and leave your client unable to tell which one to call.
https://api.roboselect360.com (same X-API-Key)Example code in this repository is released under the MIT License. The RoboSelect360 dataset, scoring methodology and teardown analyses are proprietary and are not included here - they are served through the API.
*RoboSelect360 - independent humanoid robot intelligence.*