Kiro MCP Server

Kiro MCP server configuration

kiro_mcp_config

Read and manage Kiro MCP configuration: list servers and check status, add HTTP servers, or remove entries; write actions require KIRO_MCP_ALLOW_CONFIG_WRITES.

Instructions

Read Kiro's MCP configuration: list (kiro-cli mcp list, optional scope) and status (kiro-cli mcp status --name), parsed from text with the raw text alongside. add (HTTP servers only: an https URL, or http to localhost) and remove need KIRO_MCP_ALLOW_CONFIG_WRITES. Stdio (command) servers and mcp import are withheld because they run arbitrary commands. For live server status in a session, use kiro_session_state include mcp.

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_mcp_config"
  }
}

Input Schema

Name	Required	Description
`cwd`	No	Workspace directory inside KIRO_MCP_ROOTS for workspace scope (default: the first root).
`url`	No
`name`	No
`agent`	No
`force`	No
`scope`	No
`action`	Yes
`command`	No	Not accepted: stdio servers are withheld.
`disabled`	No
`timeout_ms`	No

Output Schema

Name	Required	Description	Default
`raw`	Yes
`note`	Yes
`action`	Yes
`status`	Yes
`servers`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations (which merely say readOnly=false, openWorld=true, destructive=false) by naming the required environment variable KIRO_MCP_ALLOW_CONFIG_WRITES for mutations, restricting `add` to HTTP/HTTPS-localhost URLs, and explaining why stdio servers are excluded. It also discloses output behavior (parsed fields with the raw text alongside), which is exactly the kind of context annotations cannot convey.

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?

Tight, front-loaded, and uses backticked action names to make scanning easy; the alternative-tool pointer is placed last, which is appropriate. The single long sentence packs several clauses and could be split for readability, but no sentence is wasteful.

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?

An output schema exists, so return values need not be re-explained, and the description correctly limits itself to action semantics, write gating, and the withheld capability. The remaining shortfall is the four parameters with no documented meaning anywhere in the definition.

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 description coverage is only 20%, yet the description adds real meaning for `action`, `url`, `name`, and `scope`, and explains why `command` is rejected. However, `agent`, `force`, `disabled`, and `timeout_ms` remain undocumented in both the schema and the description, leaving a meaningful gap for a 10-parameter tool.

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 resource (Kiro's MCP configuration) and enumerates the four actions with their underlying CLI equivalents (`kiro-cli mcp list`, `mcp status --name`). It also explicitly separates read actions (`list`, `status`) from write actions (`add`, `remove`), so an agent can distinguish it from siblings without opening the schema.

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?

Explicitly routes the agent to `kiro_session_state include mcp` for live server status, and discloses that stdio/command servers and `mcp import` are withheld. It does not give guidance on choosing between actions or on the optional `scope` beyond implying list takes it.

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