Zensei Index
by wegravel · remote · no sign-in to list tools · v1.0.0 · published by GitHub user wegravel
Today's Zensei Index: a 0-100 US market risk score, its ten indicators and the latest summary.
4 tools: 4 change things.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things4Claude Code: ask: see these tools
- Only reads0Claude Code: allow
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http zensei https://www.zensei.com/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
4 tools
Changes things 4Claude Code: ask
zensei_index_aboutWhat the Zensei Index is, how to read the score, how it is built, and what this server serves.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it What the Zensei Index is, how to read the score, how it is built, and what this server serves. Same wording as the website FAQ. Call it once before interpreting any score.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
zensei_index_indicatorsThe ten indicators behind today's Zensei Index, each with its current status, the layer it scores into, its weight in that layer, and the same explanation the website shows.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The ten indicators behind today's Zensei Index, each with its current status, the layer it scores into, its weight in that layer, and the same explanation the website shows. Use it to explain why the index sits where it does. Indicator statuses run from healthiest to most stressed: Clear or Inactive (no stress), Watch (early warning), Stress (confirmed stress), Activated or Danger (full signal). Calibrating means not enough data yet; Unknown means no data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
zensei_index_summaryThe latest written summary of the Zensei Index, with the score and regime it was written for.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The latest written summary of the Zensei Index, with the score and regime it was written for. A summary is rewritten only when the indicators change. Check `stale` and `ageDays` before quoting it as today's view, and prefer zensei_index_today for the current number. The Zensei Index is a RISK score from 0 to 100: LOWER IS HEALTHIER. 0-20 Supportive, 20-40 Vulnerable, 40-70 Stressed, 70-100 Restrictive. A rising score means conditions are deteriorating, not improving.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
zensei_index_todayToday's Zensei Index for U.S.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Today's Zensei Index for U.S. equities: the final score, its regime label, and the three layer scores (structural conditions, tactical filters, regime confirmations). The Zensei Index is a RISK score from 0 to 100: LOWER IS HEALTHIER. 0-20 Supportive, 20-40 Vulnerable, 40-70 Stressed, 70-100 Restrictive. A rising score means conditions are deteriorating, not improving. Call zensei_index_indicators to see why the score sits where it does.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http zensei https://www.zensei.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__zensei__zensei_index_about",
"mcp__zensei__zensei_index_today",
"mcp__zensei__zensei_index_indicators",
"mcp__zensei__zensei_index_summary"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as zensei. Review it before you use it.
