Skip to content

Causara Economic Control

by mahadrehman239-del · remote · no sign-in to list tools · v0.1.0 · published by GitHub user mahadrehman239-del

Economic exposure and control decisions for autonomous AI actions in Shadow Mode.

Changes · 1
CompareRegistry entry

3 tools: 1 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http causara-economic-control https://causara.floot.app/_api/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 1Claude Code: ask
  • evaluate_agent_actionRun a proposed autonomous AI action through Causara's frozen Shadow Mode economic-control engine.No findings

    Why it is in this group

    • The name "evaluate_agent_action" says "evaluate": a word for a change.
    Description, as the server wrote it
    Run a proposed autonomous AI action through Causara's frozen Shadow Mode economic-control engine. Returns downstream dependency path, economic exposure, potential loss, confidence, and an ALLOW/REVIEW/ESCALATE/BLOCK recommendation. Causara does not execute or block the proposed business action. The evaluation is recorded in Causara's Shadow risk ledger.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 2Claude Code: allow
  • get_control_modelReturn the live Causara V2.0 Shadow Mode model metadata, including supported action routes and frozen validation status.No findings

    Why it is in this group

    • The name "get_control_model" says "get": a word for reading.
    Description, as the server wrote it
    Return the live Causara V2.0 Shadow Mode model metadata, including supported action routes and frozen validation status. Use this before evaluation when you need to check whether an action type is supported.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • normalize_business_contextValidate and normalize a structured business-context CSV into Causara's canonical economic context.No findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate and normalize a structured business-context CSV into Causara's canonical economic context. This does not evaluate or execute an AI action. Use it when source data is available as a field/value or single-row CSV export.

    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 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http causara-economic-control https://causara.floot.app/_api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__causara-economic-control__get_control_model",
      "mcp__causara-economic-control__normalize_business_context"
    ],
    "ask": [
      "mcp__causara-economic-control__evaluate_agent_action"
    ],
    "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 causara-economic-control. Review it before you use it.