# Kiro

> Set up Spicrawl in Kiro: add the hosted MCP server to .kiro/settings/mcp.json, install the agent skill, and add a steering file so the agent fetches web pages cheaply and handles errors correctly.

Source: https://docs.spicrawl.com/agents/kiro

Three steps give Kiro's agent Spicrawl's tools, the knowledge to write Spicrawl code, and rules for using both well. Set your key first, in the environment Kiro starts from:

```bash
export SPICRAWL_API_KEY=spicrawl_live_...   # add to your shell profile, then restart Kiro
```

## 1. Add the MCP server

Kiro reads MCP servers from `.kiro/settings/mcp.json` in the workspace and `~/.kiro/settings/mcp.json` for every workspace. The workspace file wins when both define a server. In the IDE, open the command palette and run **Kiro: Open workspace MCP config (JSON)** or **Kiro: Open user MCP config (JSON)**. Kiro's docs list the same two files for Kiro CLI.

```json title=".kiro/settings/mcp.json"
{
  "mcpServers": {
    "spicrawl": {
      "url": "https://mcp.spicrawl.com/mcp",
      "headers": { "Authorization": "Bearer ${SPICRAWL_API_KEY}" }
    }
  }
}
```

Kiro expands only environment variables you have approved. When you save the file, it shows a security popup listing `SPICRAWL_API_KEY`. Approve it, or add it in Kiro settings under **Mcp Approved Env Vars**. Saved changes apply without restarting the session, and only changed servers restart.

Check that `spicrawl` is connected and lists 25 `spicrawl_*` tools. See [MCP server](https://docs.spicrawl.com/agents/mcp.md) for each tool.

## 2. Install the skill

Kiro supports Agent Skills in the IDE and the CLI. It loads them from `.kiro/skills/` in the workspace and `~/.kiro/skills/` for every workspace. `spicrawl skill install` has no Kiro target, so install manually:

```bash
mkdir -p .kiro/skills/spicrawl
curl -fsSL https://app.spicrawl.com/skill.md -o .kiro/skills/spicrawl/SKILL.md
```

Kiro matches the skill's `description` against your request, and you can also invoke it with a slash command. See [Agent skill](https://docs.spicrawl.com/agents/skill.md).

## 3. Add a steering file

Steering files give Kiro persistent instructions. Save this as `.kiro/steering/spicrawl.md` (or `~/.kiro/steering/spicrawl.md` for every workspace). With `inclusion: auto` and a `name` and `description`, Kiro loads it when a task involves web data. Use `inclusion: always` to load it in every chat.

```markdown title=".kiro/steering/spicrawl.md"
---
inclusion: auto
name: spicrawl
description: Fetching, scraping or extracting data from web pages with Spicrawl
---

# Web data (Spicrawl)

Use Spicrawl to read web pages: the spicrawl_* MCP tools in chat, or
POST https://api.spicrawl.com/v1/scrape with `Authorization: Bearer $SPICRAWL_API_KEY` in code.
Docs: https://docs.spicrawl.com/llms.txt (append .md to any page URL for Markdown).

- Ask for markdown: `response_format: "markdown"` (API default is html); on spicrawl_scrape, `format: "markdown"`.
- Check the site's status, not only the HTTP status: `X-Target-Status` header, or `status`
  in the JSON envelope (spicrawl_scrape with `format: "json"`). 200 is the page; 404/410
  mean it does not exist; 403/429/503 mean the site refused, so escalate.
- On an error, switch on `code`. Retry only when `retryable` is true, after
  `retry_after_seconds`. Read `diagnostics.hint` and change what it names first.
  Never retry ERR::REQUEST::*, ERR::AUTH::* or ERR::LIMIT::QUOTA_EXCEEDED.
- Escalate one step at a time and stop at the first that works:
  plain fetch (1 credit) -> `js_render: true` (3) -> add the user's own `proxy`
  if they have one. Empty or skeleton content means render; ERR::UPSTREAM::CHALLENGE
  or a 403 target status means retry once, then the user's own proxy.
- Set `max_cost` on every request to the price of the step you intend.
- Keep the cache on (default). Set `cache: false` only for prices, stock or other live data.
- Trim tokens with `main_content_only` (on by default for markdown), `include_tags`, `exclude_tags`.
- For more than 20 URLs, use a batch job (spicrawl_batch_submit / POST /v1/batch).
  Batch items return raw HTML and apply only render, proxy and block_resources settings.
- Never print or commit SPICRAWL_API_KEY. Log `X-Request-Id` for failures.
```

Kiro also reads `AGENTS.md`, and always includes it (no inclusion modes). If you already keep agent instructions there, paste the same section into it instead.

## A first task to try

Start a chat in the Kiro IDE and ask:

```text
Use Spicrawl to read https://example.com/pricing as markdown. List each plan with its monthly price.
If the page comes back empty, retry with rendering.
```

The agent should call `spicrawl_scrape` with `url` and `format: "markdown"`, and add `render: true` only if the first result is empty. For a coding task:

```text
Add a fetchPage(url) function to this project that calls the Spicrawl API for markdown,
following the Web data rules in the Spicrawl steering file. Read the key from process.env.SPICRAWL_API_KEY.
```

Compare the result with the reference implementation in [Best practices](https://docs.spicrawl.com/agents/best-practices.md).

## Troubleshooting

| Symptom                                                                       | Fix                                                                                                                                                                                  |
| ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| The server shows an error or 401                                              | `SPICRAWL_API_KEY` is not approved or not set. Approve it in **Mcp Approved Env Vars**, export it, and restart Kiro from that shell.                                                 |
| Check the key and endpoint outside Kiro                                       | `curl -i https://mcp.spicrawl.com/mcp` answers 401 `Unauthorized: send your Spicrawl API key`. Add `-H "Authorization: Bearer $SPICRAWL_API_KEY"` to see the authenticated response. |
| The agent writes `js_render` on `spicrawl_scrape` and gets "unknown argument" | The tool's argument is `render`. The API field is `js_render`.                                                                                                                       |
| Usage tools return `ERR::AUTH::INSUFFICIENT_SCOPE`                            | Grant the `read` scope to the key in the dashboard.                                                                                                                                  |