Kiro MCP Server

Steer a running Kiro turn

kiro_steer

Queues a steering message into a session's running turn, injecting it at the next step so you can redirect work mid-run. Use when a turn is active; start a new prompt otherwise.

Instructions

Send a steering message into the session's running turn (_session/steer), like Kiro's steer mode: Kiro queues it and injects it at the next step (watch for steering events in kiro_events). Fails with NO_ACTIVE_TURN when nothing is running; send a new kiro_prompt instead.

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": {
      "session_id": "<session_id>",
      "text": "<text>"
    },
    "name": "kiro_steer"
  }
}

Input Schema

Name	Required	Description	Default
`text`	Yes
`session_id`	Yes	Kiro session id (sess_<uuid>).

Output Schema

Name	Required	Description	Default
`cursor`	Yes
`turn_id`	Yes
`accepted`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, open-world, so the bar is lower, and the description still adds real value: the message is queued and injected at the next step rather than altering the current step. The NO_ACTIVE_TURN error contract is useful behavioral context; queue depth, ordering across repeated steers, and any size limits are not covered.

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?

Two sentences, front-loaded with the action and mechanism, followed by the queueing behavior and then the fallback. No filler, and the endpoint reference is compactly parenthesized.

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

Completeness4/5

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

With an output schema present, return values need not be explained, and the description covers the essential async semantics and the error path. What remains thin is timing detail — when exactly 'next step' occurs and whether queued steers can be withdrawn.

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 50% — session_id is documented in the schema while text is not — so the description partly compensates by framing the second argument as a mid-turn steering message rather than a fresh instruction. It adds no guidance on content, size (maxLength 100000), or how multiple steered texts interact.

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 resource ('Send a steering message into the session's running turn') plus the backing endpoint (_session/steer), which makes the mechanism unambiguous. It is clearly separable from the prompt-creating siblings because it operates on an already-running turn.

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

Usage Guidelines5/5

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

Explicitly scopes usage to a running turn, names the exact failure mode (NO_ACTIVE_TURN when nothing is running) and redirects to the correct alternative, kiro_prompt, for that case. It also points at kiro_events for observing the result of the steer.

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