mcpField
Z
Zensei MCP

Zensei MCP

VerifiedFeaturedRemote
zensei.comFinance0Updated 2d ago

About Zensei MCP

Zensei MCP is a remote server for exploring a US stock-market risk index and sector rotation data in MCP clients. Its read-only tools include market indicators, sector and stock details, historical scores, and optional account-specific watchlists.

Key features

  1. 01Read the 0–100 market risk index
  2. 02Review index indicators and history
  3. 03Compare sector ETFs with the S&P 500
  4. 04Inspect sector and stock details
  5. 05Access a saved watchlist

Use cases

  1. 01Check the latest market risk regime
  2. 02Review historical index scores
  3. 03Compare sector momentum and returns
  4. 04Look up a stock's related sectors

MCP support

The remote MCP server exposes read-only market index, sector, stock, search, and watchlist tools, along with index and sector-map views. Public data is available without an account; some tools require sign-in.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://www.zensei.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

4

This tool takes no parameters.

Details

From the project README

Zensei MCP server

The MCP server for Zensei: the Zensei Index and the sector rotation scan, in Claude, ChatGPT and any MCP client.

The Zensei Index is a 0-100 risk score for the US stock market. Lower is healthier. The sector scan compares every US sector ETF with the S&P 500.

  • URL: https://www.zensei.com/mcp
  • Transport: Streamable HTTP
  • Auth: optional OAuth 2.1. Public data works without an account. Tools that need an account ask the user to sign in.
  • Docs: https://www.zensei.com/mcp

This repository holds the server metadata and the plugin packages. The server runs on zensei.com.

Tools

All tools are read-only.

ToolReturnsAccess
zensei_index_aboutWhat the index is, how to read the 0-100 score, and how it is built.Free
zensei_index_todayToday's final score, its regime label, and the three layer scores.Free
zensei_index_indicatorsThe ten indicators behind the score, each with its status, group, weight and explanation.Free
zensei_index_summaryThe latest written market summary, with its date and a stale flag.Free
zensei_index_historyDaily scores with their regime.One month free, up to ten years with Premium
zensei_sectors_scanEvery sector ETF against the S&P 500: quadrant, momentum, relative strength, returns.11 broad sectors free, 100+ with Premium
zensei_sector_detailOne sector in depth, with its largest holdings.Broad sectors free
zensei_stock_detailHow a stock does against the sectors that hold it.Broad sectors free
zensei_searchFind sector ETFs and stocks by ticker or name.Premium
zensei_my_watchlistThe user's saved symbols on Zensei.Zensei account

Interactive views

In apps that support MCP Apps (Claude, ChatGPT), two tools come with a view:

  • zensei_index_today shows the regime card. Expand it to see the full dashboard, with each indicator's chart.
  • zensei_sectors_scan shows the rotation map. Expand it to see the rankings, and open a sector to see its holdings.

The views call two app-only tools, zensei_view_sector and zensei_view_indicators. Apps hide them from the model.

Resources

URIContent
zensei://index/aboutThe explainer as a markdown document.
ui://zensei/index-card.htmlThe Zensei Index view.
ui://zensei/sector-map.htmlThe sector map view.

Setup

Claude

Open Settings → Connectors → Add custom connector. Paste https://www.zensei.com/mcp.

ChatGPT

Turn on developer mode in ChatGPT's app settings, then create an app with the URL https://www.zensei.com/mcp.

Claude Code
claude mcp add --transport http zensei https://www.zensei.com/mcp
Cursor

Add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "zensei": {
      "url": "https://www.zensei.com/mcp"
    }
  }
}
VS Code

Add this to .vscode/mcp.json:

{
  "servers": {
    "zensei": {
      "type": "http",
      "url": "https://www.zensei.com/mcp"
    }
  }
}
Any other client

Point the client at https://www.zensei.com/mcp with the Streamable HTTP transport.

Plugin packages

FileFor
plugin.json, mcp.json, assets/The ChatGPT plugin directory (Agent Plugins format, OpenAI listing under extensions.com.openai).
.claude-plugin/plugin.json, .mcp.jsonClaude Code plugins.
.grok-plugin/plugin.json, .mcp.jsonGrok Build plugins.

To build the ZIP for platform.openai.com/plugins:

./scripts/package-openai.sh

The ZIP lands in dist/zensei-chatgpt.zip. SUBMISSION.md lists what each directory asks for.

Registry metadata

To publish to the official registry:

mcp-publisher login github
mcp-publisher publish

Limits

  • US markets only.
  • Not investment advice. Zensei does not predict prices or place trades.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.