Skip to main content
Glama
chrischall

Kia Access MCP

by chrischall
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

kia_start_climate

Idempotent

Start remote climate preconditioning for your Kia: after explicit confirmation, send the start command and check vehicle status until the climate system reports running.

Instructions

Start remote climate control / preconditioning (Kia rems/start, live-verified). Asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call makes NO network call and returns a preview plus a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE). Once confirmed it sends the command and re-reads cmm/gvi until the NESTED climate.airCtrl reads true (there is no flat airCtrlOn field). On an EV engine stays false while climate runs — ign3 is the ignition proxy and is reported alongside. commandAccepted (Kia took the request) and stateConfirmed (the car actually reads running) are separate; state changes were observed to take 30–60s. TEMPERATURE IS BEST-EFFORT AND UNCONFIRMED: per docs/KIA-API.md a start requesting 70°F still read back 72°F, so the car may report its own last-set target rather than the requested one — do not promise the user a specific cabin temperature. Seat and steering-wheel/rear-window heating are not sent at all: the request body deliberately omits heatVentSeat (Kia validates seat capability per car) and leaves every heatingAccessory field at 0.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vinKeyYesThe vehicle key (`vehicleKey` from the vehicle-list tool), used as the `vinkey` header. Not the VIN.
defrostNoRun front defrost (default false).
temperatureNoTarget cabin temperature in °F, 62–82, or the sentinel "LOW"/"HIGH" for the ends of the range (default 70). A quoted whole number ("72") is accepted and treated as the number. BEST-EFFORT / UNCONFIRMED — see docs/KIA-API.md.
waitSecondsNoHow long to keep re-reading cmm/gvi for proof the command landed (default 30). Observed changes took 30–60s, so an unconfirmed result is common — re-read the vehicle status rather than re-sending the command. Values above ~45 can outlast an MCP client's own request timeout (often 60s), which then reports a failure for a command that WAS sent. 0 checks once and returns immediately — the command may still land afterwards.
confirmTokenNoONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.
durationMinutesNoMinutes the ignition stays on (default 5).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.1.0
    • removedInput schema / properties / confirm
      Removed value: -{
-  "description": "Must be true to proceed. Without this, the tool returns a preview.",
-  "type": "boolean"
-}
    • addedInput schema / properties / confirmToken
      Added value: +{
+  "description": "ONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 \"confirmation-required\" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.",
+  "type": "string"
+}
  2. Changed2 schema fields changedv1.0.3
    • changedInput schema / properties / waitSeconds / default
      Previous value: -60New value: +30
    • changedInput schema / properties / waitSeconds / description
      Previous value: -"How long to keep re-reading cmm/gvi for proof the command landed (default 60). Observed changes took 30–60s. 0 checks once and returns immediately — the command may still land afterwards."New value: +"How long to keep re-reading cmm/gvi for proof the command landed (default 30). Observed changes took 30–60s, so an unconfirmed result is common — re-read the vehicle status rather than re-sending the command. Values above ~45 can outlast an MCP client's own request timeout (often 60s), which then reports a failure for a command that WAS sent. 0 checks once and returns immediately — the command may still land afterwards."
  3. Changed1 schema field changedv0.9.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  4. Changed2 schema fields changedv0.6.1
    • changedInput schema / properties / temperature / anyOf
      Previous value: -[
-  {
-    "maximum": 82,
-    "minimum": 62,
-    "type": "integer"
-  },
-  {
-    "enum": [
-      "LOW",
-      "HIGH"
-    ],
-    "type": "string"
-  }
-]New value: +[
+  {
+    "maximum": 82,
+    "minimum": 62,
+    "type": "integer"
+  },
+  {
+    "enum": [
+      "LOW",
+      "HIGH"
+    ],
+    "type": "string"
+  },
+  {
+    "pattern": "^\\d+$",
+    "type": "string"
+  }
+]
    • changedInput schema / properties / temperature / description
      Previous value: -"Target cabin temperature in °F, 62–82, or the sentinel \"LOW\"/\"HIGH\" for the ends of the range (default 70). BEST-EFFORT / UNCONFIRMED — see docs/KIA-API.md."New value: +"Target cabin temperature in °F, 62–82, or the sentinel \"LOW\"/\"HIGH\" for the ends of the range (default 70). A quoted whole number (\"72\") is accepted and treated as the number. BEST-EFFORT / UNCONFIRMED — see docs/KIA-API.md."
  5. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, it discloses major behaviors: the first call may make no network call, a repeat call with confirmToken is required, the tool re-reads cmm/gvi until nested climate.airCtrl is true, EV ignition behaves differently, and temperature is best-effort. It also documents that seat and accessory heating are deliberately omitted from the request.

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

Conciseness5/5

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

The description is long but every clause earns its place, covering confirmation, verification, EV quirks, timing, temperature fidelity, and omitted features. The core action is front-loaded and the supporting caveats are ordered logically without repetition.

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?

Given the tool's complexity, the lack of an output schema, and the need to safely handle confirmation and idempotency, this description is unusually complete. It explains response phases, acceptance-vs-confirmation semantics, timing expectations, and what the tool does not do, so an agent has enough context to invoke it correctly.

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

Parameters4/5

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

Schema coverage is 100% and the schema fields are already richly described. The description adds extra semantic nuance on top: temperature is unconfirmed, waitSeconds above ~45 can outlast client timeouts, and confirmToken must only be reused after explicit user approval. This goes beyond the baseline, though not every parameter receives extra description-level detail.

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?

The opening sentence states a specific verb and resource: "Start remote climate control / preconditioning (Kia `rems/start`, live-verified)." This clearly distinguishes it from siblings like kia_stop_climate and kia_start_charge by domain, action, and endpoint.

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?

The description gives strong operational guidance: when to expect a preview and confirmToken, when to re-read instead of re-sending, and how to handle unconfirmed results. However, it never explicitly names when to choose this over sibling tools, relying on the purpose statement to imply the use case.

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

Deploy Server

Other Tools