@spicrawl/mcp 0.1.3 → 0.1.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +6 -2
- package/README.md +12 -12
- package/package.json +4 -4
package/CHANGELOG.md
CHANGED
|
@@ -3,6 +3,10 @@
|
|
|
3
3
|
All notable changes to `@spicrawl/mcp` are documented here. This project follows
|
|
4
4
|
[Semantic Versioning](https://semver.org/).
|
|
5
5
|
|
|
6
|
+
## 0.1.4 — 2026-10-05
|
|
7
|
+
|
|
8
|
+
The repository moved to https://github.com/OfficialSpicrawl/mcp, and `mcpName` is now `io.github.OfficialSpicrawl/mcp`. No code or tool changes.
|
|
9
|
+
|
|
6
10
|
## 0.1.3 — 2026-10-01
|
|
7
11
|
|
|
8
12
|
- `spicrawl_scrape` on the ChatGPT endpoint (`/chatgpt/mcp`) is now annotated `readOnlyHint: true`. That surface only ever sends an HTTP GET with no method, body, headers or actions, so it cannot change anything on a site. On `/mcp` it stays not read-only, because `method` and `actions` can submit forms.
|
|
@@ -20,11 +24,11 @@ All notable changes to `@spicrawl/mcp` are documented here. This project follows
|
|
|
20
24
|
Documentation and package metadata only; the server and its 25 tools are unchanged.
|
|
21
25
|
|
|
22
26
|
- README rewritten for npmjs.com: hosted endpoint first, one-click install links for Cursor and VS Code, per-client setup for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI and Codex, tool tables by group, a "which tool to use" guide, environment variables, self-hosting, FAQ and troubleshooting. Every link is absolute so it works on npm.
|
|
23
|
-
- `package.json`: `mcpName` (`io.github.
|
|
27
|
+
- `package.json`: `mcpName` (`io.github.OfficialSpicrawl/mcp`) for the official MCP registry, a new `description` and `keywords`, and `homepage` now points at https://docs.spicrawl.com/agents/mcp.
|
|
24
28
|
|
|
25
29
|
## 0.1.0 — 2026-10-01
|
|
26
30
|
|
|
27
|
-
First public release of the Spicrawl MCP server, published to npm as `@spicrawl/mcp` from https://github.com/
|
|
31
|
+
First public release of the Spicrawl MCP server, published to npm as `@spicrawl/mcp` from https://github.com/OfficialSpicrawl/mcp with an npm provenance attestation.
|
|
28
32
|
|
|
29
33
|
- `npx -y @spicrawl/mcp` runs the stdio server for any MCP client (Claude Code, Claude Desktop, Cursor, VS Code, Codex, …), keyed by `SPICRAWL_API_KEY`. Installed globally, the command is `spicrawl-mcp` (`spicrawl-mcp-server` is an alias).
|
|
30
34
|
- `spicrawl-mcp --http` (or `node dist/http.js`) runs the Streamable HTTP server behind the hosted endpoint at https://mcp.spicrawl.com/mcp: per-caller bearer-token auth validated against the API, sessions pinned to the key that opened them, idle-session eviction and a `/healthz` liveness route.
|
package/README.md
CHANGED
|
@@ -4,10 +4,10 @@ The Spicrawl MCP server is a Model Context Protocol server that gives AI agents
|
|
|
4
4
|
|
|
5
5
|
[](https://www.npmjs.com/package/@spicrawl/mcp)
|
|
6
6
|
[](https://www.npmjs.com/package/@spicrawl/mcp)
|
|
7
|
-
[](https://github.com/
|
|
8
|
-
[](https://github.com/OfficialSpicrawl/mcp/blob/main/LICENSE)
|
|
8
|
+
[](https://github.com/OfficialSpicrawl/mcp/actions/workflows/ci.yml)
|
|
9
9
|
|
|
10
|
-
**[Docs](https://docs.spicrawl.com/agents/mcp)** · **[Get an API key](https://app.spicrawl.com/signup)** · **[TypeScript SDK](https://github.com/
|
|
10
|
+
**[Docs](https://docs.spicrawl.com/agents/mcp)** · **[Get an API key](https://app.spicrawl.com/signup)** · **[TypeScript SDK](https://github.com/OfficialSpicrawl/sdk)** · **[CLI](https://github.com/OfficialSpicrawl/cli)** · **[Agent plugins](https://github.com/OfficialSpicrawl/agent-plugins)** · **[Changelog](https://github.com/OfficialSpicrawl/mcp/blob/main/CHANGELOG.md)**
|
|
11
11
|
|
|
12
12
|
<p>
|
|
13
13
|
<a href="https://cursor.com/en/install-mcp?name=spicrawl&config=eyJ1cmwiOiJodHRwczovL21jcC5zcGljcmF3bC5jb20vbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyICR7ZW52OlNQSUNSQVdMX0FQSV9LRVl9In19"><img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add Spicrawl MCP server to Cursor" height="32" /></a>
|
|
@@ -114,7 +114,7 @@ Both transports serve the same 25 `spicrawl_*` tools, and every call runs under
|
|
|
114
114
|
|
|
115
115
|
### Coming soon
|
|
116
116
|
|
|
117
|
-
`spicrawl_browser_connect_url` will mint a single-use CDP WebSocket URL for driving a Spicrawl-hosted browser from Puppeteer or Playwright; remote browsers are not available yet. The schemas also accept `ai_extract`, `stealth`, `extract_preset`, `premium_proxy`, `proxy_country` and `sticky_key` ahead of launch. Agents should not send them yet. To list only what works today, set `SPICRAWL_MCP_HIDE_UNAVAILABLE=1` (see [Environment variables](https://github.com/
|
|
117
|
+
`spicrawl_browser_connect_url` will mint a single-use CDP WebSocket URL for driving a Spicrawl-hosted browser from Puppeteer or Playwright; remote browsers are not available yet. The schemas also accept `ai_extract`, `stealth`, `extract_preset`, `premium_proxy`, `proxy_country` and `sticky_key` ahead of launch. Agents should not send them yet. To list only what works today, set `SPICRAWL_MCP_HIDE_UNAVAILABLE=1` (see [Environment variables](https://github.com/OfficialSpicrawl/mcp#environment-variables)).
|
|
118
118
|
|
|
119
119
|
## Example prompts
|
|
120
120
|
|
|
@@ -156,7 +156,7 @@ To share it with a team, commit `.mcp.json` at the project root. Claude Code exp
|
|
|
156
156
|
Or install the plugin, which bundles the MCP server and the Spicrawl agent skill:
|
|
157
157
|
|
|
158
158
|
```bash
|
|
159
|
-
claude plugin marketplace add
|
|
159
|
+
claude plugin marketplace add OfficialSpicrawl/agent-plugins
|
|
160
160
|
claude plugin install spicrawl@spicrawl-plugins
|
|
161
161
|
```
|
|
162
162
|
|
|
@@ -420,7 +420,7 @@ There is no single crawl tool. Scrape a page with `links: true` to get its links
|
|
|
420
420
|
Not on `/mcp`: it accepts Spicrawl API keys only, so turn OAuth off for it in clients that try it on a `401`. The separate [ChatGPT endpoint](#chatgpt-endpoint-oauth) at `/chatgpt/mcp` takes OAuth access tokens only, when the operator turns it on.
|
|
421
421
|
|
|
422
422
|
### Should I use the MCP server, the SDK or the CLI?
|
|
423
|
-
Use the MCP server when an AI agent should call Spicrawl as tools. Use [`@spicrawl/sdk`](https://github.com/
|
|
423
|
+
Use the MCP server when an AI agent should call Spicrawl as tools. Use [`@spicrawl/sdk`](https://github.com/OfficialSpicrawl/sdk) in your own TypeScript or JavaScript code, [`@spicrawl/cli`](https://github.com/OfficialSpicrawl/cli) in a terminal or shell script, and the [REST API](https://docs.spicrawl.com/quickstart) from any other language.
|
|
424
424
|
|
|
425
425
|
## Troubleshooting
|
|
426
426
|
|
|
@@ -439,18 +439,18 @@ Use the MCP server when an AI agent should call Spicrawl as tools. Use [`@spicra
|
|
|
439
439
|
|
|
440
440
|
## Related packages
|
|
441
441
|
|
|
442
|
-
- [`@spicrawl/sdk`](https://github.com/
|
|
443
|
-
- [`@spicrawl/cli`](https://github.com/
|
|
444
|
-
- [
|
|
442
|
+
- [`@spicrawl/sdk`](https://github.com/OfficialSpicrawl/sdk): the official TypeScript SDK for the Spicrawl API.
|
|
443
|
+
- [`@spicrawl/cli`](https://github.com/OfficialSpicrawl/cli): the Spicrawl command-line interface.
|
|
444
|
+
- [OfficialSpicrawl/agent-plugins](https://github.com/OfficialSpicrawl/agent-plugins): plugins that bundle this server and the Spicrawl skill for Claude Code, Codex, Cursor, Gemini CLI and more.
|
|
445
445
|
|
|
446
446
|
## Links
|
|
447
447
|
|
|
448
448
|
- Documentation: [docs.spicrawl.com/agents/mcp](https://docs.spicrawl.com/agents/mcp)
|
|
449
449
|
- Docs for LLMs: [docs.spicrawl.com/llms.txt](https://docs.spicrawl.com/llms.txt)
|
|
450
450
|
- Dashboard and API keys: [app.spicrawl.com](https://app.spicrawl.com)
|
|
451
|
-
- Issues: [github.com/
|
|
452
|
-
- Security: [SECURITY.md](https://github.com/
|
|
451
|
+
- Issues: [github.com/OfficialSpicrawl/mcp/issues](https://github.com/OfficialSpicrawl/mcp/issues)
|
|
452
|
+
- Security: [SECURITY.md](https://github.com/OfficialSpicrawl/mcp/blob/main/SECURITY.md). Never commit an API key; revoke a leaked one at [app.spicrawl.com](https://app.spicrawl.com).
|
|
453
453
|
|
|
454
454
|
## License
|
|
455
455
|
|
|
456
|
-
[Apache-2.0](https://github.com/
|
|
456
|
+
[Apache-2.0](https://github.com/OfficialSpicrawl/mcp/blob/main/LICENSE)
|
package/package.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@spicrawl/mcp",
|
|
3
|
-
"version": "0.1.
|
|
4
|
-
"mcpName": "io.github.
|
|
3
|
+
"version": "0.1.4",
|
|
4
|
+
"mcpName": "io.github.OfficialSpicrawl/mcp",
|
|
5
5
|
"description": "The Spicrawl MCP server is a Model Context Protocol server that gives AI agents in Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI and Codex web scraping to Markdown, structured data extraction, screenshots, browser sessions and batch scraping as 25 native tools.",
|
|
6
6
|
"license": "Apache-2.0",
|
|
7
7
|
"author": "Spicrawl",
|
|
8
8
|
"homepage": "https://docs.spicrawl.com/agents/mcp",
|
|
9
9
|
"repository": {
|
|
10
10
|
"type": "git",
|
|
11
|
-
"url": "git+https://github.com/
|
|
11
|
+
"url": "git+https://github.com/OfficialSpicrawl/mcp.git"
|
|
12
12
|
},
|
|
13
13
|
"bugs": {
|
|
14
|
-
"url": "https://github.com/
|
|
14
|
+
"url": "https://github.com/OfficialSpicrawl/mcp/issues"
|
|
15
15
|
},
|
|
16
16
|
"keywords": [
|
|
17
17
|
"spicrawl",
|