kite-connect-mcp

Engage the kill switch

engage_kill_switch

Idempotent

Stops all write operations immediately by creating a server-side kill-switch file; write tools are refused until a person deletes the file, while dry runs still work.

Instructions

Stop every write at once: creates the kill-switch file, after which all write tools are refused (dry runs still work and say so). Only a person can switch it off again, by deleting the file on the server.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "reason": "<reason>"
    },
    "name": "engage_kill_switch"
  }
}

Input Schema

Name	Required	Description	Default
`reason`	Yes	why writes are being stopped

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations: annotations only say destructiveHint=false and idempotent=true, while the description reveals the concrete side effect (a file is created), the blast radius (all write tools refused), the exception (dry runs still work and report it), and the critical constraint that the acting agent cannot reverse it — only a person deleting the file on the server can. That irreversibility disclosure is the highest-value behavior an agent could know here.

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

Conciseness4/5

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

Two tight sentences, front-loaded with the effect and then the escape hatch. The parenthetical about dry runs is well placed, though the final sentence could be marginally tighter.

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

Completeness5/5

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

For a one-parameter, no-output-schema control tool, the description covers everything an agent needs: what happens, what is blocked, what still works, and that recovery is out of its hands. No return-value description is needed given there is no output schema and the effect is stated instead.

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

Parameters3/5

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

Schema coverage is 100% and the single 'reason' parameter is already documented as 'why writes are being stopped' with length bounds, so the description needn't repeat it. However, the description says nothing about the reason field — e.g. whether it is surfaced in the audit log or shown to operators — so it adds no meaning over the schema.

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

Purpose5/5

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

States a specific verb and effect ('Stop every write at once') plus the mechanism ('creates the kill-switch file'). This is unmistakably distinct from every sibling tool, which are per-order or read operations; no agent could confuse place_order with this global circuit breaker.

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

Usage Guidelines4/5

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

Gives a clear usage condition (to halt all writes at once) and implicitly a strong caveat that it is for emergencies, since only a human can undo it. It stops short of naming concrete scenarios or explicitly warning against using it for routine maintenance, so it is not a full when/when-not/alternatives statement.

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