scrapeloop-mcp 0.38.1 → 0.39.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapeloop-mcp",
-  "version": "0.38.1",
+  "version": "0.39.0",
   "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

@@ -601,14 +601,14 @@ 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. All four credit answers are required. A number is a limit; explicit null means no plan limit for that one (then only the workspace balance stops the plan), and 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({
+    def: { description: 'Save reviewed credit limits and Table ownership for a paused complete-search plan with a ready-email goal. All four credit answers are required. A number is a limit; explicit null means no plan limit for that one (then only the workspace balance stops the plan), and 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. business_email_finder permits a Business email finder column that was made with confirmed_only on (create_table_native_column options). Such a column keeps only an address the email check called real, holds 3 verify credits per row and charges 1 per check that got an answer. A Business email finder column without confirmed_only stays blocked, because it can keep an address nobody confirmed. 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', 'null'], minimum: 0, maximum: 1000000000 },
         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 },
+        allowed_checks: { type: 'array', items: { ...S, enum: ['verify_email', 'verify_catchall', 'verify_phone', 'owner_website', 'review_history', 'website_language', 'business_email_finder'] }, maxItems: 7 },
         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 },
@@ -1740,7 +1740,7 @@ const TOOLS = {
   create_table_native_column: {
     def: {
       description:
-        `Attach one native Scrapeloop tool as a real Smart Table column: ${NATIVE_TABLE_TOOLS.join(', ')}. These are Scrapeloop's first-party tools, several of which superseded legacy presets, so they are addressed by tool key here rather than by preset slug through create_table_preset_column (which refuses a superseded slug for a new column). Each bills MANAGED VERIFICATION CREDITS per row, never dollars and never the customer's own vendor keys: verify_email reserves 1 credit per selected row, verify_phone reserves 5, each email finder reserves 3, linkedin_finder reserves 5, linkedin_activity reserves 3, and google_profile reserves 1. Settlement charges only fresh vendor checks and returns the unused reservation; missing inputs, cached rows, and skipped rows are free. linkedin_finder charges its 5 credits only for a row where it found the owner's LinkedIn profile; a row with no owner found is free. linkedin_activity reads each row's personal LinkedIn profile and newest post and labels it Active, Maybe or Weak (cell text), so LinkedIn invites go to people likely to answer; it charges 3 credits only for a profile it read, and rows with no personal profile, cached rows and profiles that no longer exist are free. google_profile finds a business on Google Maps for a lead that did not come from Google Maps (a Yelp lead, an imported list): it searches the business name in its town, accepts a result only when the phone, the website or the exact name in the same town matches, and saves place_id, gbp_url, rating and reviews_count on the cell (status found, not_found or unclear) and the place ID on a lead that had none; it charges 1 credit only for a profile found, and a business not on Google, more than one matching profile and cached rows are free. Filter on col.<key>.reviews_count to keep small businesses; a business with no reviews yet is saved as 0, and an unknown count has no number and never passes a numeric rule. Creating a column is always free. auto_run defaults false and queues nothing; when auto_run would backfill existing rows the API returns a 409 estimate whose cost.total_credits is the real charge, and you confirm it with confirm_auto_run plus confirmed_credits (CREDITS, not dollars - estimated_cost_usd is our vendor cost and is far smaller than what the workspace is billed). An auto_run that exceeds the workspace verify-credit balance returns 402 with {credit_kind, required, available} before anything is created. The Table master auto-run switch and workspace budget caps stay fail-closed. options are per tool and only the documented names are accepted - call get_table_native_tools for the current list. Owner email finder needs an owner first name plus the company website; point options.owner_name_column at an Owner name finder column to source the name, which auto_run requires. Business email finder is a SEPARATE column - create it with its own call and set options.owner_email_column to run it behind an owner finder. The Catch-all verifier is NOT creatable here: it needs a Verify email column that has already RUN and returned Catch All or Unknown, so use verify_catchall per address, or add the column from the Table's add-column menu.`,
+        `Attach one native Scrapeloop tool as a real Smart Table column: ${NATIVE_TABLE_TOOLS.join(', ')}. These are Scrapeloop's first-party tools, several of which superseded legacy presets, so they are addressed by tool key here rather than by preset slug through create_table_preset_column (which refuses a superseded slug for a new column). Each bills MANAGED VERIFICATION CREDITS per row, never dollars and never the customer's own vendor keys: verify_email reserves 1 credit per selected row, verify_phone reserves 5, each email finder reserves 3, linkedin_finder reserves 5, linkedin_activity reserves 3, and google_profile reserves 1. Settlement charges only fresh vendor checks and returns the unused reservation; missing inputs, cached rows, and skipped rows are free. linkedin_finder charges its 5 credits only for a row where it found the owner's LinkedIn profile; a row with no owner found is free. linkedin_activity reads each row's personal LinkedIn profile and newest post and labels it Active, Maybe or Weak (cell text), so LinkedIn invites go to people likely to answer; it charges 3 credits only for a profile it read, and rows with no personal profile, cached rows and profiles that no longer exist are free. google_profile finds a business on Google Maps for a lead that did not come from Google Maps (a Yelp lead, an imported list): it searches the business name in its town, accepts a result only when the phone, the website or the exact name in the same town matches, and saves place_id, gbp_url, rating and reviews_count on the cell (status found, not_found or unclear) and the place ID on a lead that had none; it charges 1 credit only for a profile found, and a business not on Google, more than one matching profile and cached rows are free. Filter on col.<key>.reviews_count to keep small businesses; a business with no reviews yet is saved as 0, and an unknown count has no number and never passes a numeric rule. Creating a column is always free. auto_run defaults false and queues nothing; when auto_run would backfill existing rows the API returns a 409 estimate whose cost.total_credits is the real charge, and you confirm it with confirm_auto_run plus confirmed_credits (CREDITS, not dollars - estimated_cost_usd is our vendor cost and is far smaller than what the workspace is billed). An auto_run that exceeds the workspace verify-credit balance returns 402 with {credit_kind, required, available} before anything is created. The Table master auto-run switch and workspace budget caps stay fail-closed. options are per tool and only the documented names are accepted - call get_table_native_tools for the current list. Owner email finder needs an owner first name plus the company website; point options.owner_name_column at an Owner name finder column to source the name, which auto_run requires. Business email finder is a SEPARATE column - create it with its own call and set options.owner_email_column to run it behind an owner finder. Business email finder also has careful options for a Table that runs by itself. confirmed_only keeps an address only when the email check says it is real (verified, or an exact Role answer), tries the next name only when this mailbox does not exist, never keeps a catch all, unknown or full mailbox answer, and saves each answer the way a Verify email column does, so that column gets it for free afterwards. require_mail_server skips a website with no mail server at no charge. max_checks keeps a row to 1, 2 or 3 names. skip_shared_website skips, at no charge, a website that is a shared page or that another lead of the workspace also has. write_to_lead_email writes a confirmed address on a lead that has no email yet, and never an address another lead already has. run_if runs a row only when a condition is true. A Table under a search plan's limits only takes this finder with confirmed_only on. new_rows_only (with auto_run) runs only rows added from now on: rows already in the Table are not run, nothing is queued or held, and no confirmation is needed. The Catch-all verifier is NOT creatable here: it needs a Verify email column that has already RUN and returned Catch All or Unknown, so use verify_catchall per address, or add the column from the Table's add-column menu.`,
       inputSchema: obj(
         {
           table_id: S,
@@ -1754,10 +1754,15 @@ const TOOLS = {
             description:
               'The 409 estimate\'s cost.total_credits, echoed back exactly. Verification credits, not dollars.',
           },
+          new_rows_only: {
+            ...B,
+            description:
+              'With auto_run true: run only rows that are added from now on. Rows already in the Table are not run now, so nothing is queued or held and there is nothing to confirm. Leave confirm_auto_run and confirmed_credits out. Use this on a Table that already has many rows, such as the first Table of a search plan. Good to know: a column that reads another column, in an input or in run_if, still follows that column. When that other column finishes again for an old row, this column runs for that row once.',
+          },
           options: {
             ...O,
             description:
-              'Tool-specific options. verify_phone: phone_col, default_region. email_finder: owner_name_column. business_email_finder: owner_email_column. linkedin_finder: business_col. linkedin_activity: linkedin_col, business_col. google_profile: business_col. An undocumented name is rejected, never ignored.',
+              'Tool-specific options. verify_phone: phone_col, default_region. email_finder: owner_name_column. business_email_finder: owner_email_column, confirmed_only, require_mail_server, max_checks, skip_shared_website, shared_website_max_leads, write_to_lead_email, run_if. linkedin_finder: business_col. linkedin_activity: linkedin_col, business_col. google_profile: business_col. An undocumented name is rejected, never ignored.',
           },
           operation_id: {
             ...S,
@@ -1794,6 +1799,7 @@ const TOOLS = {
         ...(a.confirmed_credits !== undefined
           ? { confirmed_credits: a.confirmed_credits }
           : {}),
+        ...(a.new_rows_only !== undefined ? { new_rows_only: a.new_rows_only } : {}),
         ...(a.options !== undefined ? { options: a.options } : {}),
       };
       return api('POST', `/tables/${enc(a.table_id)}/native-columns`, requestBody, {