# Goose

> Set up Spicrawl in Goose: add the hosted MCP server as a Streamable HTTP extension, 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/goose

Three steps give Goose Spicrawl's tools, the knowledge to write Spicrawl code, and rules for using both well. Goose calls MCP servers extensions. Spicrawl connects as a remote extension of type Streamable HTTP.

## 1. Add the MCP server

Run `goose configure` and answer the prompts:

**Step 1: Choose the extension type**

Select **Add Extension**, then **Remote Extension (Streamable HTTP)**.

**Step 2: Enter the endpoint**

Give the extension a name such as `spicrawl`, and `https://mcp.spicrawl.com/mcp` as the endpoint URI. Set the timeout in seconds (the docs' examples use 300).

**Step 3: Add the auth header**

Answer yes to adding custom headers. Use the header name `Authorization` and the value `Bearer spicrawl_live_...` with your real key.

The extension is saved to `~/.config/goose/config.yaml`. You can also write it by hand:

```yaml title="~/.config/goose/config.yaml"
extensions:
  spicrawl:
    name: Spicrawl
    type: streamable_http
    uri: https://mcp.spicrawl.com/mcp
    headers:
      Authorization: "Bearer spicrawl_live_..."
    enabled: true
    timeout: 300
```

> **Warning:** Goose stores the header value as written, so the key sits in `config.yaml` in plain text. Do not commit or share that file. The Goose docs do not describe `$VAR` substitution for `headers`, so this page does not rely on it.

Spicrawl authenticates with the static header only and does not support OAuth. In Goose Desktop, **Extensions** in the sidebar then **Add custom extension** opens a similar form. See [MCP server](https://docs.spicrawl.com/agents/mcp.md) for the 25 `spicrawl_*` tools.

## 2. Install the skill

Goose supports Agent Skills. It loads them from `.agents/skills/` in the project and `~/.agents/skills/` for every project (it still reads `.goose/skills/` and `.claude/skills/` for backward compatibility):

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

This writes `.agents/skills/spicrawl/SKILL.md`. The `--client` value names the CLI's own target, not the agent that reads it. 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

By default Goose reads `AGENTS.md`, then `.goosehints`, from the project root. Paste this section into `AGENTS.md`. To apply it to every session instead, put it in `~/.config/goose/.goosehints`.

```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.
```

## A first task to try

Start a Goose session in the project (`goose session`) 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 extension fails to load or returns 401                                    | The `Authorization` header is missing, misspelled or holds a placeholder key. Check the value is `Bearer ` followed by the key, with one space. Confirm the key with `curl -i https://mcp.spicrawl.com/mcp -H "Authorization: Bearer $SPICRAWL_API_KEY"`. |
| The extension times out on a slow page                                        | Raise `timeout` (seconds) on the extension.                                                                                                                                                                                                               |
| 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.                                                                                                                                                                                                       |