scrapeloop-mcp 0.27.0 → 0.30.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapeloop-mcp",
-  "version": "0.27.0",
+  "version": "0.30.0",
   "description": "Scrapeloop MCP server  -  set up and run Scrapeloop end-to-end (integrations, scraping, lead database, verification, cleaners, enrichment, strategies, Instantly campaigns) from any MCP client (Claude Desktop, Cursor, ChatGPT, …).",
   "type": "module",
   "scripts": {

package/src/index.js

@@ -591,14 +591,14 @@ const TOOLS = {
     run: (a) => api('GET', `/plans/${enc(a.plan_id)}/budget`),
   },
   set_scrape_plan_budget: {
-    def: { description: 'Save reviewed credit limits and Table ownership for a paused complete-search plan with a ready-email goal. Include Raw, Email ready and every check Table. One Table belongs to one budget. Preserve expected_revision from the current budget; omit it only for the first save. A lost reply requires readback before retry. This starts no work and does not enable checks. owner_website explicitly permits the free bounded system Owner name finder; it still needs a saved job and attempt. review_history permits only the system Google review stats preset with source explicitly outscraper and a separate review_budget in USD, default zero. Select an existing connection from get_scrape_plan_budget.review_connections. Omitted review_budget preserves saved settings. Each row reserves 0.147 USD; recorded units use the published ceiling, not a confirmed account invoice. Unknown requests stay held and never retry. Google-first, custom recipes and other paid vendors remain blocked. Use review_complete_scrape_plan to check readiness before requesting exact launch approval.', inputSchema: obj({
+    def: { description: 'Save reviewed credit limits and Table ownership for a paused complete-search plan with a ready-email goal. Monthly lead credits always need a numeric cap. Explicit null removes only the extra lifetime lead or monthly/lifetime verify cap; omission is rejected. Zero blocks spending. No-cap checks still require allowed tools, bounded jobs and available workspace credits. Never infer no cap without approval. Include Raw, Email ready and every check Table. One Table belongs to one budget. Preserve expected_revision from the current budget; omit it only for the first save. A lost reply requires readback before retry. This starts no work and does not enable checks. website_language permits the free bounded Website languages preset with a saved attempt. owner_website explicitly permits the free bounded system Owner name finder; it still needs a saved job and attempt. review_history permits only the system Google review stats preset with source explicitly outscraper and a separate review_budget in USD, default zero. Select an existing connection from get_scrape_plan_budget.review_connections. Omitted review_budget preserves saved settings. Each row reserves 0.147 USD; recorded units use the published ceiling, not a confirmed account invoice. Unknown requests stay held and never retry. Google-first, custom recipes and other paid vendors remain blocked. Use review_complete_scrape_plan to check readiness before requesting exact launch approval.', inputSchema: obj({
       plan_id: { ...S, format: 'uuid' }, expected_revision: { ...S, format: 'uuid' },
       limits: obj({
         monthly_lead_credits: { type: 'integer', minimum: 0, maximum: 1000000000 },
-        lifetime_lead_credits: { type: 'integer', minimum: 0, maximum: 1000000000 },
-        monthly_verify_credits: { type: 'integer', minimum: 0, maximum: 1000000000 },
-        lifetime_verify_credits: { type: 'integer', minimum: 0, maximum: 1000000000 },
-        allowed_checks: { type: 'array', items: { ...S, enum: ['verify_email', 'verify_catchall', 'verify_phone', 'owner_website', 'review_history'] }, maxItems: 5 },
+        lifetime_lead_credits: { type: ['integer', 'null'], minimum: 0, maximum: 1000000000 },
+        monthly_verify_credits: { type: ['integer', 'null'], minimum: 0, maximum: 1000000000 },
+        lifetime_verify_credits: { type: ['integer', 'null'], minimum: 0, maximum: 1000000000 },
+        allowed_checks: { type: 'array', items: { ...S, enum: ['verify_email', 'verify_catchall', 'verify_phone', 'owner_website', 'review_history', 'website_language'] }, maxItems: 6 },
         review_budget: obj({ monthly_usd: { type: 'number', minimum: 0, maximum: 1000000, multipleOf: 0.001 }, lifetime_usd: { type: 'number', minimum: 0, maximum: 1000000, multipleOf: 0.001 }, credential_id: { type: ['string', 'null'], format: 'uuid' } }, ['monthly_usd', 'lifetime_usd', 'credential_id']),
       }, ['monthly_lead_credits', 'lifetime_lead_credits', 'monthly_verify_credits', 'lifetime_verify_credits', 'allowed_checks']),
       list_ids: { type: 'array', items: { ...S, format: 'uuid' }, minItems: 1, maxItems: 20 },
@@ -1029,6 +1029,10 @@ const TOOLS = {
     def: { description: 'Read the versioned draft GHL setup guide. Pass check_account=true for four free GET checks of the exact connected account, draft workflow names, contact fields and setting formats. No installs, saves, contacts, sender writes or paid calls. This is not an importable snapshot. Workflow steps, per-intake identity, outcome returns and owned-contact proof remain separate and launch_ready is always false.', inputSchema: obj({ campaign_id: S, check_account: B }, ['campaign_id']) },
     run: (a) => a.campaign_id ? api('GET', `/campaigns/${enc(a.campaign_id)}/ghl-package${qs({ check_account: a.check_account })}`) : { ok: false, status: 400, error: { detail: 'campaign_id is required.' } },
   },
+  get_campaign_ghl_intake_review: {
+    def: { description: 'Read source candidates for a paused GHL shared journey, or pass lead_id for a free primary contact comparison. Checks current verified mobile, local stops, mapped fields, exact account, phone/email matches, GHL stops and prior intake markers. At most five provider reads, including read-only POST contact searches. No contact, field or workflow writes. Results expire after one minute and never approve sending; additional-address matching and the durable writer remain required. Pass after to read the next source page.', inputSchema: obj({ campaign_id: S, lead_id: S, after: S }, ['campaign_id']) },
+    run: (a) => a.campaign_id ? api('GET', `/campaigns/${enc(a.campaign_id)}/ghl-intake-review${qs({ lead_id: a.lead_id, after: a.after })}`) : { ok: false, status: 400, error: { detail: 'campaign_id is required.' } },
+  },
   get_campaign_ghl_returns: {
     def: { description: 'Review the account-bound receiving address and signed GoHighLevel return counts for a shared journey. A saved address is not live delivery or provider removal proof. Unmatched updates remain saved; missing signed phone identity stays held. Read only.', inputSchema: obj({ campaign_id: S }, ['campaign_id']) },
     run: (a) => a.campaign_id ? api('GET', `/campaigns/${enc(a.campaign_id)}/ghl-returns`) : { ok: false, status: 400, error: { detail: 'campaign_id is required.' } },
@@ -1108,6 +1112,7 @@ const TOOLS = {
       inputSchema: obj(
         {
           name: S,
+          qualification: { ...O, description: 'Optional campaign entry rule: {rule: be_dutch, evidence_column_id, max_age_days: 90}. Use {} for no rule. Read get_campaign_qualification for eligible evidence columns.' },
           sender_options: { ...O, description: "GoHighLevel SMS choices: workflow_id, tags, require_verified_mobile, voip_counts_as_mobile, missing_fields (ask, create, never)." },
           icon: { type: ["string", "null"], description: "One or two emoji, or null to clear." },
           source_list_id: S,
@@ -1141,15 +1146,19 @@ const TOOLS = {
         'allow_risky_emails', 'offload_enabled', 'offload_no_reply_days', 'offload_to_instantly',
         'offload_to_scrapeloop', 'offload_scrapeloop_list_id',
         'drip_daily_count', 'target_active_count', 'cooldown_days', 'resting_period_days',
-        'recycle_mode', 'prioritize_fresh', 'bounce_instantly_list_id', 'sender_options', 'icon',
+        'recycle_mode', 'prioritize_fresh', 'bounce_instantly_list_id', 'sender_options', 'icon', 'qualification',
       ]) {
         if (a[k] !== undefined && a[k] !== null) body[k] = a[k];
       }
       return api('POST', '/campaigns', body);
     },
   },
+  get_campaign_qualification: {
+    def: { description: 'Read the saved entry rule and accessible Website languages columns. This starts no checks. Belgium Dutch rules hold missing, expired, changed or unknown website evidence and excluded regions before upload. Existing sender leads are not removed.', inputSchema: obj({ campaign_id: S }, ['campaign_id']) },
+    run: (a) => api('GET', `/campaigns/${enc(a.campaign_id)}/qualification`),
+  },
   update_campaign: {
-    def: { description: 'Patch a campaign (feed_mode, target_active_count, cooldown_days, external_list_id, …). Switching feed_mode on for an already active campaign runs the same check as campaign_readiness_check: any fail answers 422 with the report under detail.readiness.', inputSchema: obj({ campaign_id: S, patch: { ...O, description: "Campaign settings to change.", properties: { sender_options: { ...O, description: "GoHighLevel SMS settings. Only supplied keys change." }, icon: { type: ["string", "null"], description: "One or two emoji, or null to clear." } }, additionalProperties: true } }, ['campaign_id', 'patch']) },
+    def: { description: 'Patch a campaign (feed_mode, target_active_count, cooldown_days, external_list_id, …). Switching feed_mode on for an already active campaign runs the same check as campaign_readiness_check: any fail answers 422 with the report under detail.readiness.', inputSchema: obj({ campaign_id: S, patch: { ...O, description: "Campaign settings to change. qualification: {} disables the gate; {rule: be_dutch, evidence_column_id: UUID, max_age_days: 90} requires current Dutch website evidence outside Wallonia. This changes future uploads only; it does not remove sender leads or start checks.", properties: { sender_options: { ...O, description: "GoHighLevel SMS settings. Only supplied keys change." }, icon: { type: ["string", "null"], description: "One or two emoji, or null to clear." } }, additionalProperties: true } }, ['campaign_id', 'patch']) },
     run: (a) => api('PATCH', `/campaigns/${enc(a.campaign_id)}`, a.patch || {}),
   },
   duplicate_campaign: {
@@ -2480,7 +2489,7 @@ const TOOLS = {
           limit: N,
           sort: S,
           q: S,
-          filter: { ...O, description: 'FilterExpr JSON (object): server-side row filter; adds total_filtered.' },
+          filter: { ...O, description: 'FilterExpr JSON (object): server-side row filter; adds total_filtered. lead.email_domain derives the exact lowercase domain from the current email, separate from website lead.domain. Use eq/any_of/none_of for exact lists; add not_empty to hold malformed or blank addresses under exclusions. No DNS or provider lookup.' },
           view_id: { ...S, description: 'A saved custom view uuid or a system key (errored_rows/fully_enriched/data_only) from list_table_views. An ad-hoc filter/sort replaces the view\'s.' },
         },
         ['list_id'],