Kiro MCP Server

Kiro workflows

kiro_workflow

Destructive

Manage workflow recipes and runs: list, invoke with validated inputs, inspect, pause, resume, cancel, retry, or delete runs, and track lifecycle events.

Instructions

Kiro workflows (_kiro/workflow/*), like /workflow: list_recipes, list runs, invoke a recipe with inputs (checked against the recipe's declared input names), and inspect, pause, resume, cancel, retry (optionally from node_id), or delete a run. Lifecycle notifications appear as workflow events in kiro_events. For /goal, invoke the goal or iterate recipe when one is listed; otherwise prompt in autonomous mode with explicit acceptance criteria.

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": {
      "action": "<action>",
      "session_id": "<session_id>"
    },
    "name": "kiro_workflow"
  }
}

Input Schema

Name	Required	Description
`action`	Yes
`inputs`	No
`recipe`	No
`node_id`	No
`session_id`	Yes	Kiro session id (sess_<uuid>).
`workflow_id`	No

Output Schema

Name	Required	Description	Default
`action`	Yes
`result`	Yes
`workflow_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, non-idempotent, and open-world, so the safety profile is carried for the agent. The description adds real context beyond that: inputs are validated against the recipe's declared input names, retry can target a node_id, and workflow lifecycle notifications appear in kiro_events. It never states what delete or cancel actually remove, whether they are recoverable, or what permissions invoke requires, which is a notable gap for a destructive tool.

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?

A single dense paragraph that front-loads the resource and then enumerates actions; almost every clause carries information. The parentheticals and the trailing /goal sentence make it slightly harder to scan than a bulleted action list would be, but there is little waste.

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

Completeness3/5

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

An output schema exists, so return values need not be described, and the annotations cover the safety posture. However, for a nine-action tool with six parameters and 17% schema coverage, the description leaves the action-to-parameter mapping undocumented, which is the single most important thing an agent needs to invoke it correctly.

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

Parameters2/5

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

Schema description coverage is only 17% (only session_id is documented), so the description must compensate and largely does not. It never explains that 'invoke' needs recipe and inputs, that inspect/pause/resume/cancel/retry/delete need workflow_id, or what distinguishes 'list' from 'list_recipes'. The only parameter meaning added is that inputs are checked against the recipe's declared input names and node_id is an optional retry target.

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

Purpose4/5

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

The description names the concrete resource (_kiro/workflow/*) and enumerates the operations, which map almost one-to-one onto the action enum (list_recipes, list, invoke, inspect, pause, resume, cancel, retry, delete). It also distinguishes itself from kiro_events by noting that lifecycle notifications surface there instead. It stops short of a crisp one-line statement of what the tool is for, but an agent can still tell what it does.

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

Usage Guidelines3/5

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

Usage guidance exists only for the special /goal case (invoke the goal or iterate recipe if listed, otherwise prompt in autonomous mode) and for the kiro_events hand-off. There is no guidance on when to pick 'list' versus 'list_recipes', or which actions require recipe/workflow_id. Useful hints, but the when-to-use decisions across the nine actions are largely left implicit.

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