firecrawl-mcp 3.22.1 → 3.22.2
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/dist/index.js +7 -0
- package/package.json +1 -1
package/dist/index.js
CHANGED
|
@@ -1495,6 +1495,13 @@ Goal guidance:
|
|
|
1495
1495
|
- If the user says they do not care about something, include that explicitly. It is okay to ask whether they want to ignore specific noise when it is likely to matter.
|
|
1496
1496
|
- Do not invent page-specific sections, thresholds, entities, or business rules unless the user mentioned them.
|
|
1497
1497
|
|
|
1498
|
+
Query guidance (web monitors): \`queries\` control recall (what search retrieves) and \`goal\` controls precision (which results alert) \u2014 tune both.
|
|
1499
|
+
- Write keywords, not sentences: \`OpenAI new model release\`, not \`tell me when OpenAI releases a new model\`.
|
|
1500
|
+
- Quote multi-word entities (\`"Llama 4"\`); group synonyms with \`OR\` (\`launch OR release OR announcement\`).
|
|
1501
|
+
- Keep each query tight (~2-6 terms). One broad query usually beats several narrow ones \u2014 extra queries split the \`maxResults\` budget. Use one query per distinct entity; do not emit one per facet of a single subject.
|
|
1502
|
+
- Keep \`site:\` operators out of queries \u2014 use \`includeDomains\` / \`excludeDomains\`.
|
|
1503
|
+
- A healthy web monitor mostly returns \`new: 0\` and alerts only on genuinely new, on-goal results. Many \`ignored\` results \u21D2 queries too broad (tighten them); nothing for long stretches \u21D2 queries too narrow or window too tight (broaden); dismissed alerts \u21D2 goal too broad (add an intent-specific Ignore). Aim for high precision with enough recall.
|
|
1504
|
+
|
|
1498
1505
|
Full \`body\` requests require: \`name\`, \`schedule\` (with \`cron\` or \`text\`), and \`targets\` (one or more \`{ type: 'scrape', urls: [...] }\`, \`{ type: 'crawl', url: '...' }\`, or \`{ type: 'search', queries: [...], searchWindow?, maxResults?, includeDomains?, excludeDomains? }\`). Optional: \`goal\` (required when any search target is present), \`judgeEnabled\`, \`webhook\`, \`notification\`, \`retentionDays\`.
|
|
1499
1506
|
|
|
1500
1507
|
**Markdown-mode (default):** Each check produces a unified text diff of the page's markdown. No extra configuration needed.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "firecrawl-mcp",
|
|
3
|
-
"version": "3.22.
|
|
3
|
+
"version": "3.22.2",
|
|
4
4
|
"description": "MCP server for Firecrawl — search, scrape, and interact with the web. Supports both cloud and self-hosted instances. Features include web search, scraping, page interaction, batch processing, and LLM-powered content analysis.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"mcpName": "io.github.firecrawl/firecrawl-mcp-server",
|