crw-mcp 0.23.0 → 0.24.0
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/package.json +6 -6
- package/skills/SKILL.md +28 -4
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "crw-mcp",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"description": "MCP server for CRW web scraper — scrape, crawl, map, search, and PDF-parse tools for AI agents",
|
|
3
|
+
"version": "0.24.0",
|
|
4
|
+
"description": "MCP server for CRW web scraper — scrape, crawl, map, extract, search, and PDF-parse tools for AI agents",
|
|
5
5
|
"license": "AGPL-3.0",
|
|
6
6
|
"homepage": "https://github.com/us/crw",
|
|
7
7
|
"repository": {
|
|
@@ -32,9 +32,9 @@
|
|
|
32
32
|
"skills/SKILL.md"
|
|
33
33
|
],
|
|
34
34
|
"optionalDependencies": {
|
|
35
|
-
"crw-mcp-darwin-x64": "0.
|
|
36
|
-
"crw-mcp-darwin-arm64": "0.
|
|
37
|
-
"crw-mcp-linux-x64": "0.
|
|
38
|
-
"crw-mcp-linux-arm64": "0.
|
|
35
|
+
"crw-mcp-darwin-x64": "0.24.0",
|
|
36
|
+
"crw-mcp-darwin-arm64": "0.24.0",
|
|
37
|
+
"crw-mcp-linux-x64": "0.24.0",
|
|
38
|
+
"crw-mcp-linux-arm64": "0.24.0"
|
|
39
39
|
}
|
|
40
40
|
}
|
package/skills/SKILL.md
CHANGED
|
@@ -24,10 +24,11 @@ Use this skill when:
|
|
|
24
24
|
## Installation
|
|
25
25
|
|
|
26
26
|
```bash
|
|
27
|
-
crw
|
|
27
|
+
npx crw-mcp@latest install # installs the skill + MCP server into detected agents
|
|
28
|
+
npx crw-mcp@latest init # skill only
|
|
28
29
|
```
|
|
29
30
|
|
|
30
|
-
|
|
31
|
+
`install` sets up the CRW skill and MCP server for all detected AI agents (Claude Code, Cursor, Gemini CLI, Codex, OpenCode, Windsurf, Roo Code).
|
|
31
32
|
|
|
32
33
|
## Authentication
|
|
33
34
|
|
|
@@ -82,7 +83,7 @@ Returns: `{ "status": "scraping|completed|failed", "data": [...] }`
|
|
|
82
83
|
|
|
83
84
|
### crw_search
|
|
84
85
|
|
|
85
|
-
Search the web
|
|
86
|
+
Search the web for current information, news, facts, or docs. Use whenever the answer may depend on up-to-date or external information. Returns ranked results (url/title/description/snippet); optionally scrape each result inline. Always available in proxy/cloud mode; in embedded mode only when a search backend is configured.
|
|
86
87
|
|
|
87
88
|
Parameters:
|
|
88
89
|
- `query` (required) — The search query
|
|
@@ -90,7 +91,7 @@ Parameters:
|
|
|
90
91
|
- `lang` — Language code for results (e.g. `"en"`, `"tr"`)
|
|
91
92
|
- `tbs` — Time filter: `qdr:h|qdr:d|qdr:w|qdr:m|qdr:y` (past hour/day/week/month/year)
|
|
92
93
|
- `sources` — If set, group results by source: `web`, `news`, `images`
|
|
93
|
-
- `categories` —
|
|
94
|
+
- `categories` — Category bias; e.g. `"pdf"`, `"github"`, `"research"`, `"news"`, `"images"`
|
|
94
95
|
- `scrapeOptions` — Options for scraping each result page (e.g. `{"formats": ["markdown"]}`)
|
|
95
96
|
|
|
96
97
|
### crw_map
|
|
@@ -106,6 +107,29 @@ Parameters:
|
|
|
106
107
|
|
|
107
108
|
Returns: `{ "links": ["url1", "url2", ...] }`
|
|
108
109
|
|
|
110
|
+
### crw_extract
|
|
111
|
+
|
|
112
|
+
Extract structured JSON from one or more URLs via a prompt and/or JSON schema. Async job, poll with `crw_check_extract_status`. Needs an LLM.
|
|
113
|
+
|
|
114
|
+
Parameters:
|
|
115
|
+
- `urls` (required) — URLs to extract from
|
|
116
|
+
- `prompt` — Free-text extraction objective (required unless `schema` is given)
|
|
117
|
+
- `schema` — JSON schema constraining the extracted output
|
|
118
|
+
- `llmApiKey` — BYOK LLM API key
|
|
119
|
+
- `llmProvider` — LLM provider (used with `llmApiKey`)
|
|
120
|
+
- `llmModel` — LLM model (used with `llmApiKey`)
|
|
121
|
+
|
|
122
|
+
Returns: `{ "id": "job-uuid" }` — use this ID with crw_check_extract_status.
|
|
123
|
+
|
|
124
|
+
### crw_check_extract_status
|
|
125
|
+
|
|
126
|
+
Poll an async extract job for results.
|
|
127
|
+
|
|
128
|
+
Parameters:
|
|
129
|
+
- `id` (required) — The extract job ID from `crw_extract`
|
|
130
|
+
|
|
131
|
+
Returns: status and, when complete, a per-URL results array.
|
|
132
|
+
|
|
109
133
|
### crw_parse_file
|
|
110
134
|
|
|
111
135
|
Parse a local file (PDF) into markdown or structured output without fetching from the web.
|