Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/aqualia/alph/kiro-mcpgit clone --depth 1 https://github.com/Aqualia/AlphWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/aqualia/alph/kiro-mcp)<a href="https://agentmods.dev/agents/aqualia/alph/kiro-mcp"><img src="https://agentmods.dev/badge/agents/aqualia/alph/kiro-mcp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04017 |
| Opus 5 | $0.00000 | $0.02008 |
| Sonnet 5 | $0.00000 | $0.00803 |
| Haiku 4.5 | $0.00000 | $0.00402 |
Grade B, and why
kiro-mcp scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.kiro/settings/mcp.json How it starts
The opening of the file, as written. The whole thing — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
# Kiro MCP — Integration Report for Alph
Scope: essentials only for **Alph Phase-1** support of **all platforms** and **both local & remote** MCP servers under Kiro.
## 1) What Kiro supports (at a glance)
* **Config format & keys (JSON)** — top-level "mcpServers" map with per-server objects:
* command (string, required), args (array, required), env (object, optional), disabled (bool), autoApprove (array of tool names). ([Kiro][1])
* **Config locations & precedence**
* **User/global**: ~/.kiro/settings/mcp.json
* **Workspace/project**: .kiro/settings/mcp.json
* **Merge rule**: both are merged with **workspace taking precedence**. ([Kiro][1])
* **Transports**
* **Native**: local **STDIO** (spawned via command/args). ([Kiro][1])
* **Remote endpoints**: supported **indirectly** via the mcp-remote wrapper (SSE). ([Kiro][2])
* (General MCP note: protocol defines **STDIO** and **HTTP/SSE** transports.) ([Model Context Protocol][3])
* **Enablement & UX**
* Toggle MCP in **Settings**, manage connections in **MCP Servers** tab, and view **Kiro – MCP Logs** in the Output pane. ([Kiro][4])
* **Security**
* Treat tokens as secrets, prefer env vars, restrict file permissions, be conservative with autoApprove. ([Kiro][5])
## 2) File paths Alph must write
Alph’s file writer should support both scopes and create parent directories.
| Scope | macOS/Linux | Windows (PowerShell) |
| ----------------------- | --------------------------------------- | --------------------------------------- |
| **User (global)** | ~/.kiro/settings/mcp.json | %USERPROFILE%\\.kiro\\settings\\mcp.json |
| **Workspace (project)** | <PROJECT\_DIR>/.kiro/settings/mcp.json | <PROJECT\_DIR>\\.kiro\\settings\\mcp.json |
* These paths and the **workspace-overrides-user** rule are defined by Kiro docs. ([Kiro][1])
**Permissions (recommended by Kiro):**
\# Unix
chmod 600 ~/.kiro/settings/mcp.json
chmod 600 .kiro/settings/mcp.json
([Kiro][5])
## 3) Kiro config object “shape” (canonical)
{
"mcpServers": {
"<server-name>": {
"command": "<executable-or-launcher>",
"args": \["<arg1>", "<arg2>"],
"env": {
"ENV\_VAR1": "value1",
"ENV\_VAR2": "value2"
},
"disabled": false,
"autoApprove": \["tool\_name1", "tool\_name2"]
}
}
}
* Keys/semantics match Kiro’s **Configuration** page. ([Kiro][1])
## 4) Local servers (STDIO) — ready-to-paste examples
### 4.1 Python-based server via **uv/uvx**
**macOS/Linux (user scope):**
{
"mcpServers": {
"aws-docs": {
"command": "uvx",
"args": \["awslabs.aws-documentation-mcp-server@latest"],
"env": { "FASTMCP\_LOG\_LEVEL": "ERROR" },
"disabled": false,
"autoApprove": \[]
}
}
}
**Windows (user scope):**
{
"mcpServers": {
"aws-docs": {
"command": "uv",
"args": \[
"tool","run","--from","awslabs.aws-documentation-mcp-server@latest",
"awslabs.aws-documentation-mcp-server.exe"
],
"env": { "FASTMCP\_LOG\_LEVEL": "ERROR" }
}
}
}
* These are taken from Kiro’s **Servers** guide. ([Kiro][2])
### 4.2 Node server via **npx**
{
"mcpServers": {
"web-search": {
"command": "npx",
"args": \["-y", "@modelcontextprotocol/server-bravesearch"],
"env": { "BRAVE\_API\_KEY": "your-api-key" }
}
}
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 679 lines · 0 tokens per session scan B 01cc14519051
kiro-mcp is an agent published in the GitHub repository Aqualia/Alph (69 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,017 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
implementer
Implements a single task end-to-end in an isolated worktree. Spawned by the orchestrate conductor for each task in a plan.
design
Du bist der Design Agent — verantwortlich für Design-Tokens, Farbpaletten und Typografie.
update
Du bist der Update Agent — deployt Bricks-Elemente auf WordPress.
ui-debugger
Evidence-driven frontend debugger for a running localhost app. Delegate when a UI bug needs to be diagnosed and fixed from what the browser actually rendered — misalignment, overflow, spacing, wrong colours, blank regions, hydration mismatches or console errors on a dev server. Requires the dev server to be running…
frontend-architect
Use this agent when you need to design, implement, or review frontend systems and components. This includes architecting new frontend applications, implementing UI components, establishing frontend patterns and best practices, reviewing frontend code for quality and adherence to standards, optimizing frontend…