# Kilo Code

> Set up Spicrawl in Kilo Code: add the hosted MCP server to kilo.jsonc, install the agent skill, and add AGENTS.md rules so the agent fetches web pages cheaply and handles errors correctly.

Source: https://docs.spicrawl.com/agents/kilo-code

Three steps give Kilo Code Spicrawl's tools, the knowledge to write Spicrawl code, and rules for using both well. Kilo Code (VS Code extension and `kilo` CLI) keeps MCP servers in its `kilo.jsonc` config. Set your key first, in the environment Kilo starts from:

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

Roo Code is archived. Kilo Code is the maintained alternative, so use this page in its place.

## 1. Add the MCP server

Add Spicrawl under the top-level `mcp` key of `kilo.jsonc`: `.kilo/kilo.jsonc` (or `kilo.jsonc` in the project root) for one project, or `~/.config/kilo/kilo.jsonc` for every project. Project config wins over global. Kilo replaces `{env:SPICRAWL_API_KEY}` with the variable's value, so the file is safe to commit:

```jsonc title=".kilo/kilo.jsonc"
{
  "mcp": {
    "spicrawl": {
      "type": "remote",
      "url": "https://mcp.spicrawl.com/mcp",
      "headers": { "Authorization": "Bearer {env:SPICRAWL_API_KEY}" },
      "enabled": true
    }
  }
}
```

Remote servers try Streamable HTTP first and fall back to SSE. Kilo starts an OAuth flow when a remote server supports it. Spicrawl does not use OAuth, only the bearer key, so if you see an OAuth prompt, add `"oauth": false` to the server.

You can also open Kilo's settings (gear icon in the sidebar toolbar), choose **Agent Behaviour**, then **MCP Servers**, and click **Add Server**. Choose **Remote (HTTP)** and enter the URL and headers. The UI writes the same file. Check with `kilo mcp list` in the CLI, or in that settings panel: `spicrawl` should list 25 `spicrawl_*` tools. See [MCP server](https://docs.spicrawl.com/agents/mcp.md) for each tool.

## 2. Install the skill

Kilo loads skills from `.kilo/skills/`, `.agents/skills/` and `.claude/skills/` in the project, and from `~/.kilo/skills/` and `~/.agents/skills/` for every project. `.agents/skills/` is what the CLI's `codex` client writes:

```bash
spicrawl skill install --client codex
```

This writes `.agents/skills/spicrawl/SKILL.md`. Without the CLI:

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

See [Agent skill](https://docs.spicrawl.com/agents/skill.md).

## 3. Add rules to AGENTS.md

Kilo reads `AGENTS.md` at the project root. Paste this section into it:

```markdown title="AGENTS.md"
## 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.
```

To keep the rule in its own file, save it as `.kilo/rules/spicrawl.md` and list it in `kilo.jsonc`. Kilo also still reads existing `.kilocode/rules/` folders.

```jsonc title=".kilo/kilo.jsonc"
{
  "instructions": [".kilo/rules/spicrawl.md"]
}
```

## A first task to try

Open a Kilo Code chat 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 AGENTS.md. 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` was not set when VS Code started, so the header was empty. Export it and restart VS Code from that shell. |
| Kilo asks you to authenticate with OAuth                                      | Add `"oauth": false` to the `spicrawl` entry. Spicrawl authenticates with the bearer header only.                            |
| The server is listed but has no tools                                         | Toggle it off and on in **Agent Behaviour → MCP Servers**, then open a new chat.                                             |
| 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.                                                                          |