Kiro MCP Server

Kiro settings

kiro_settings

Idempotent

Read, get, set, or delete Kiro CLI settings as JSON, with writes gated by an allow flag and sensitive keys withheld. Query all settings or specific keys.

Instructions

Read Kiro settings (kiro-cli settings list --format json, with all: true for every available setting); get returns only the given keys. set and delete need KIRO_MCP_ALLOW_CONFIG_WRITES; keys under chat.agentEngine and acp.*, and any key naming a token, secret, API key, or password, are withheld. Use set chat.defaultModel for /model set-current-as-default.

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>"
    },
    "name": "kiro_settings"
  }
}

Input Schema

Name	Required	Description
`all`	No
`cwd`	No	Workspace directory inside KIRO_MCP_ROOTS for workspace settings (default: the first root).
`key`	No
`keys`	No
`value`	No
`action`	Yes
`workspace`	No

Output Schema

Name	Required	Description	Default
`note`	Yes
`action`	Yes
`output`	Yes
`settings`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Adds substantial context beyond the annotations: set and delete require KIRO_MCP_ALLOW_CONFIG_WRITES, and keys under chat.agentEngine, acp.*, or naming a token/secret/API key/password are withheld. That withheld-key disclosure is exactly the kind of behavior an agent cannot infer from the schema. Minor tension: destructiveHint=false is set while a delete action plainly removes configuration.

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?

Dense and front-loaded: the read path is stated first, then the write preconditions, then the redaction rule, then the practical tip. The semicolon-chained clauses are efficient, though the opening reads as if the tool were read-only until the third clause.

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 no explanation, and the permission/redaction rules are well covered. What is missing is parameter-level coverage for a 7-parameter tool with 14% schema coverage, plus any signal separating this from kiro_mcp_config or explaining global versus workspace scope.

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 14% across 7 parameters, so the description carries most of the burden. It clarifies all and implies keys ('get returns only the given keys'), but says nothing about value, key versus keys, or when workspace:true applies, leaving the write path's parameters undocumented in both places.

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?

Names the resource (Kiro settings) and enumerates the four action verbs it multiplexes (list, get, set, delete), with the underlying CLI call shown. The opening verb 'Read' slightly undersells the write actions, and it never distinguishes itself from the sibling kiro_mcp_config, which an agent could easily confuse with settings.

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?

Offers one concrete routing tip ('Use set chat.defaultModel for /model set-current-as-default') and explains that all:true expands the list, which is genuinely actionable. It gives no guidance on when to prefer this over kiro_mcp_config, nor when to pass workspace:true versus the default global scope.

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