crw-mcp 0.25.2 → 0.26.0
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 +5 -5
- package/skills/SKILL.md +3 -3
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "crw-mcp",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.26.0",
|
|
4
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",
|
|
@@ -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": "0.26.0",
|
|
36
|
+
"crw-mcp-darwin-arm64": "0.26.0",
|
|
37
|
+
"crw-mcp-linux-x64": "0.26.0",
|
|
38
|
+
"crw-mcp-linux-arm64": "0.26.0"
|
|
39
39
|
}
|
|
40
40
|
}
|
package/skills/SKILL.md
CHANGED
|
@@ -45,7 +45,7 @@ Scrape a single URL and return clean content.
|
|
|
45
45
|
|
|
46
46
|
Parameters:
|
|
47
47
|
- `url` (required) — The URL to scrape
|
|
48
|
-
- `formats` — Output formats: `markdown` (default), `html`, `links`
|
|
48
|
+
- `formats` — Output formats: `markdown` (default), `html`, `links`, `images`
|
|
49
49
|
- `onlyMainContent` — Strip navs/footers/sidebars. Default: `true`
|
|
50
50
|
- `includeTags` — Only include content matching these CSS selectors (e.g. `["article", "main"]`)
|
|
51
51
|
- `excludeTags` — Exclude content matching these CSS selectors (e.g. `["nav", "footer"]`)
|
|
@@ -119,7 +119,7 @@ Parameters:
|
|
|
119
119
|
- `llmProvider` — LLM provider (used with `llmApiKey`)
|
|
120
120
|
- `llmModel` — LLM model (used with `llmApiKey`)
|
|
121
121
|
|
|
122
|
-
Returns: `{ "id": "job-uuid" }` — use
|
|
122
|
+
Returns: `{ "success": true, "id": "job-uuid", "status": "processing", "urls": 1 }` — use the ID with crw_check_extract_status.
|
|
123
123
|
|
|
124
124
|
### crw_check_extract_status
|
|
125
125
|
|
|
@@ -148,7 +148,7 @@ Parse a local file (PDF) into markdown or structured output without fetching fro
|
|
|
148
148
|
Parameters:
|
|
149
149
|
- `contentBase64` (required) — Base64-encoded file contents
|
|
150
150
|
- `filename` — Original filename (optional, e.g. `"report.pdf"`)
|
|
151
|
-
- `formats` — Output formats: `markdown` (default), `plainText`, `links`, `json`, `summary` (json/summary need a server LLM)
|
|
151
|
+
- `formats` — Output formats: `markdown` (default), `plainText`, `links`, `images`, `json`, `summary` (json/summary need a server LLM)
|
|
152
152
|
- `jsonSchema` — JSON schema for LLM extraction (when `formats` includes `json`)
|
|
153
153
|
- `parsers` — Document parsers to apply. Default: `["pdf"]`
|
|
154
154
|
- `maxLength` — Truncate output to this many chars. `0` = unbounded. Default: ~15 000
|