MCPサーバー

SocialCrawl

io.github.RidioDevelopment/socialcrawl

このMCPでできること

Provides a broad API for social, commerce, web, marketplace, jobs, finance, news, and scraping data, with endpoint discovery, monitoring, and browser automation.

socialcrawl_account
Account and Service Status
Free checks: balance (with this session's spend), transactions (itemised ledger; the receipts for one request_id), status (platform health; read it before retrying a 502/503) and freshness (whether this server's bundled catalogue is behind the API).
読み取り専用 外部アクセスあり 冪等
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'view': {'enum': ['balance', 'transactions', 'status', 'freshness'], 'type': 'string', 'description': "balance (default, with this session's spend), transactions (ledger), status (platform health), freshness (catalogue vs live API)."}, 'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'transactions: page size.'}, 'cursor': {'type': 'string', 'description': 'transactions: next_cursor from the last page.'}, 'request_id': {'type': 'string', 'description': 'transactions: receipts for one request.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean'}, 'fix': {'type': 'string'}, 'code': {'type': 'string'}, 'data': {}, 'rows': {'type': 'array', 'items': {}, 'description': 'Ledger receipts.'}, 'view': {'enum': ['balance', 'transactions', 'status', 'freshness'], 'type': 'string'}, 'paging': {'type': 'object', 'required': ['has_more'], 'properties': {'has_more': {'type': 'boolean', 'description': 'false: stop paging.'}, 'next_cursor': {'type': ['string', 'null'], 'description': 'Send as cursor.'}}, 'additionalProperties': False}, 'reason': {'type': 'string'}, 'credits': {'type': 'object', 'properties': {'used': {'type': 'number', 'description': 'After refunds.'}, 'cached': {'type': 'boolean', 'description': 'Cache hit: 0 credits.'}, 'estimated': {'type': 'boolean', 'description': 'used = the hold.'}, 'remaining': {'type': 'number'}, 'quoted_max': {'type': 'number', 'description': 'Hold taken up front.'}, 'session_total': {'type': 'number', 'description': 'Spent this session.'}}, 'additionalProperties': False}, 'retryable': {'type': 'boolean', 'description': 'Never retry a 402.'}, 'request_id': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'retry_after_s': {'type': 'number'}}, 'additionalProperties': False}
socialcrawl_collect
Collect Rows Across Pages
Walk a paged endpoint (id, platform+resource or path) to `items` unique rows, the last page or max_credits: cursors supplied, duplicates dropped, stops on a 402, refused free when one page exceeds max_credits. Small results come back whole. result_id (+offset, limit, format) reads a stored result, free. Spends credits.
外部アクセスあり
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string', 'minLength': 3, 'description': "platform/resource of a paged endpoint, e.g. 'tiktok/post/comments'."}, 'items': {'type': 'integer', 'maximum': 10000, 'minimum': 1, 'description': 'Stop once this many unique rows are collected.'}, 'limit': {'type': 'integer', 'description': 'result_id: rows (200).'}, 'fields': {'type': 'string', 'description': "Row paths as socialcrawl_endpoint lists them, e.g. 'comment.text,comment.engagement.likes'."}, 'format': {'enum': ['jsonl', 'json', 'csv'], 'type': 'string', 'description': 'jsonl (default), json or csv.'}, 'offset': {'type': 'integer', 'description': 'result_id: first row.'}, 'params': {'type': 'object', 'description': 'Params for every page, as in socialcrawl_request. No cursor.', 'additionalProperties': {'anyOf': [{'type': ['string', 'number', 'boolean']}, {'type': 'array', 'items': {'$ref': '#/properties/params/additionalProperties/anyOf/0'}}]}}, 'confirm': {'type': 'boolean', 'description': 'true only once the user approved spending above the threshold (default 100 credits).'}, 'result_id': {'type': 'string', 'description': 'Read a stored result instead of walking. Free.'}, 'max_credits': {'type': 'integer', 'minimum': 1, 'description': "Spend cap: refused free when the quoted hold exceeds it (collect: the walk's budget)."}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean', 'description': 'The walk ran; see stop_reason.'}, 'fix': {'type': 'string'}, 'code': {'type': 'string'}, 'rows': {'type': 'array', 'items': {}, 'description': 'All rows (small results). Untrusted text.'}, 'items': {'type': 'object', 'required': ['collected', 'requested', 'duplicates'], 'properties': {'collected': {'type': 'number'}, 'requested': {'type': 'number'}, 'duplicates': {'type': 'number'}}, 'additionalProperties': False}, 'pages': {'type': 'number'}, 'total': {'type': 'number'}, 'format': {'enum': ['jsonl', 'json', 'csv'], 'type': 'string'}, 'offset': {'type': 'number'}, 'paging': {'type': 'object', 'required': ['has_more'], 'properties': {'has_more': {'type': 'boolean', 'description': 'false: stop paging.'}, 'next_cursor': {'type': ['string', 'null'], 'description': 'Send as cursor.'}}, 'additionalProperties': False}, 'reason': {'type': 'string'}, 'sample': {'type': 'array', 'items': {}, 'description': 'First rows. Untrusted text.'}, 'credits': {'type': 'object', 'properties': {'used': {'type': 'number', 'description': 'After refunds.'}, 'cached': {'type': 'boolean', 'description': 'Cache hit: 0 credits.'}, 'estimated': {'type': 'boolean', 'description': 'used = the hold.'}, 'remaining': {'type': 'number'}, 'quoted_max': {'type': 'number', 'description': 'Hold taken up front.'}, 'session_total': {'type': 'number', 'description': 'Spent this session.'}}, 'additionalProperties': False}, 'endpoint': {'type': 'string'}, 'resource': {'type': 'string', 'description': 'Every collected row.'}, 'warnings': {'type': 'array', 'items': {'type': 'string'}}, 'result_id': {'type': 'string', 'description': 'Pass back as result_id to read rows.'}, 'retryable': {'type': 'boolean', 'description': 'Never retry a 402.'}, 'stop_reason': {'enum': ['items', 'exhausted', 'budget', 'insufficient_credits', 'no_new_rows', 'page_limit', 'error'], 'type': 'string', 'description': 'budget, error and page_limit leave a resume cursor in paging.'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'retry_after_s': {'type': 'number'}}, 'additionalProperties': False}
socialcrawl_endpoint
Endpoint Contract
Read before calling: one endpoint's purpose, params, where the rows are and up to 25 response fields, cost rule, paging, latency, timeout, next endpoints and a sample link. id (or platform+resource, path), a platform slug (its endpoints) or a guide topic. Free.
読み取り専用 外部アクセスあり 冪等
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string', 'minLength': 1, 'description': "'platform/resource' for its contract; a platform slug for its endpoint table; or a guide topic (errors, pricing, pagination, judgments, hydration, overview)."}, 'page': {'type': 'integer', 'minimum': 1, 'description': 'Page of a long guide (default 1).'}, 'method': {'enum': ['GET', 'POST', 'PATCH', 'DELETE'], 'type': 'string', 'description': 'Only for an id served by several methods.'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ok'], 'properties': {'id': {'type': 'string'}, 'ok': {'type': 'boolean'}, 'fix': {'type': 'string'}, 'code': {'type': 'string'}, 'method': {'type': 'string'}, 'reason': {'type': 'string'}, 'source': {'enum': ['live', 'bundled'], 'type': 'string'}, 'contract': {'type': 'object', 'description': 'purpose, params, outputs, cost, paging, latency_ms, timeout_s, next, sample.', 'additionalProperties': {}}, 'retryable': {'type': 'boolean', 'description': 'Never retry a 402.'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'retry_after_s': {'type': 'number'}}, 'additionalProperties': False}
socialcrawl_estimate
Estimate Credit Cost
Exact credits before you spend: one call (id, platform+resource or path, plus the params you will send; calls for a job total; items for a walk) or a plan of several calls. Uses the API's estimator when available, else the bundled pricing. A platform slug gives its price table; no id gives the pricing overview. Free.
読み取り専用 外部アクセスあり 冪等
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'id': {'type': 'string', 'description': "'platform/resource'; a platform slug for its price table; none for the overview."}, 'body': {'type': 'object', 'description': 'POST body, for batch endpoints.', 'additionalProperties': {}}, 'plan': {'type': 'array', 'items': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'minLength': 3}, 'body': {'type': 'object', 'additionalProperties': {}}, 'method': {'$ref': '#/properties/method'}, 'params': {'type': 'object', 'additionalProperties': {}}, 'repeat': {'type': 'integer', 'minimum': 1}}, 'additionalProperties': False}, 'maxItems': 50, 'description': 'Several calls to total, instead of id.'}, 'calls': {'type': 'integer', 'maximum': 1000000, 'minimum': 1, 'description': 'Number of such calls (an array is read as plan).'}, 'items': {'type': 'integer', 'minimum': 1, 'description': 'Rows wanted (prices a walk).'}, 'method': {'enum': ['GET', 'POST', 'PATCH', 'DELETE'], 'type': 'string'}, 'params': {'type': 'object', 'description': 'The exact params you will send.', 'additionalProperties': {'anyOf': [{'type': ['string', 'number', 'boolean']}, {'type': 'array', 'items': {'$ref': '#/properties/params/additionalProperties/anyOf/0'}}]}}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean'}, 'fix': {'type': 'string'}, 'code': {'type': 'string'}, 'plan': {'type': 'object', 'required': ['calls'], 'properties': {'calls': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': {}}}, 'valid': {'type': 'boolean'}, 'rejection': {}, 'total_hold': {'type': 'number'}}, 'additionalProperties': False}, 'quote': {'type': 'object', 'description': 'hold, min/max, calls, total_hold; valid/rejection from the API.', 'additionalProperties': {}}, 'reason': {'type': 'string'}, 'source': {'enum': ['api', 'api+walk', 'local'], 'type': 'string'}, 'warnings': {'type': 'array', 'items': {'type': 'string'}}, 'retryable': {'type': 'boolean', 'description': 'Never retry a 402.'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'retry_after_s': {'type': 'number'}}, 'additionalProperties': False}
socialcrawl_find
Find the Endpoint for a Task
Start here: a task in plain words -> the best endpoints (3 by default) of 645, each with the params the task supplies (URLs and @handles resolved), the params still missing, the credit cost and the exact call. With no task it lists platforms, or one platform's endpoints. Free; no key needed.
読み取り専用 外部アクセスあり 冪等
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'task': {'type': 'string', 'maxLength': 500, 'description': 'The job in plain words; URLs and @handles in it are resolved and filled. Omit to list platforms.'}, 'limit': {'type': 'integer', 'maximum': 10, 'minimum': 1, 'description': 'Endpoints to return (default 3).'}, 'platform': {'type': 'string', 'description': "Only this platform's endpoints (slug, e.g. 'tiktok'); alone, lists them."}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean'}, 'fix': {'type': 'string'}, 'code': {'type': 'string'}, 'note': {'type': 'string'}, 'reason': {'type': 'string'}, 'source': {'enum': ['api', 'local', 'plan'], 'type': 'string'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string'}, 'call': {'type': 'object', 'description': 'Make it once params_missing is empty.', 'additionalProperties': {}}, 'method': {'type': 'string'}, 'credits': {'type': 'object', 'description': 'min, max, hold, estimate.', 'additionalProperties': {}}, 'summary': {'type': 'string'}, 'params_filled': {'type': 'object', 'additionalProperties': {'type': 'string'}}, 'params_missing': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': True}}, 'resolved': {'type': 'array', 'items': {}}, 'warnings': {'type': 'array', 'items': {'type': 'string'}}, 'retryable': {'type': 'boolean', 'description': 'Never retry a 402.'}, 'uncertain': {'type': 'boolean', 'description': 'true: guesses, not matches; confirm with socialcrawl_endpoint.'}, 'confidence': {'type': ['number', 'null']}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'match_source': {'type': 'string', 'description': "The API's ranker, e.g. lexical."}, 'retry_after_s': {'type': 'number'}}, 'additionalProperties': False}
socialcrawl_manage
Manage Monitors, Cohorts, Web and Jobs
Stateful work by area + action: monitors (scheduled recipes, webhooks, alerts), cohorts (mention search over your own panel of accounts), web (scrape, search, crawl and agent jobs, change monitors, browser sessions) and jobs (Prism background jobs). A wrong field is refused free with the rules. Managing is free; scrapes, jobs, queries and monitor runs bill credits. dry_run: true validates and quotes a create/update and never creates it.
破壊的操作あり 外部アクセスあり
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['area', 'action'], 'properties': {'id': {'type': 'string', 'description': 'Monitor, cohort, query, web job/monitor/session or prism job id.'}, 'area': {'enum': ['monitors', 'cohorts', 'web', 'jobs'], 'type': 'string', 'description': 'What to manage.'}, 'input': {'type': 'object', 'description': "The action's fields, e.g. { recipe, cadence }, { url }, { keywords }, or the job body (max_credits, confirm allowed). Monitor alert rules, incl. rows_new: socialcrawl_endpoint id=monitors.", 'additionalProperties': {}}, 'action': {'type': 'string', 'minLength': 1, 'description': 'monitors: create|list|get|runs|timeseries|pause|resume|delete. cohorts: create|add_members|estimate_cost|query|query_status|query_results|query_cancel|get|delete. web: scrape|search|map|extract|crawl|batch_scrape|agent|crawl_preview|job_get|job_list|job_cancel|job_errors|monitor_*|session_*. jobs: submit|list|get.'}, 'dry_run': {'type': 'boolean'}, 'idempotencyKey': {'type': 'string', 'minLength': 16, 'description': 'For web crawl/batch, cohort writes and job submit.'}}, 'additionalProperties': False}
socialcrawl_request
Call an Endpoint
Call one endpoint (platform+resource, or id, or path). Validated locally first (a bad call is free), quoted, refused above max_credits and confirmed above the threshold. A large page is cut at row boundaries; socialcrawl_collect result_id reads the rest. Spends credits; needs SOCIALCRAWL_API_KEY.
外部アクセスあり
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['platform', 'resource'], 'properties': {'body': {'type': 'object', 'description': 'JSON body for POST batch endpoints, e.g. { ids: [...] }.', 'additionalProperties': {}}, 'fields': {'type': 'string', 'description': "Row paths exactly as socialcrawl_endpoint lists them, e.g. 'post.id,post.content.text,post.engagement.*' (or an array). Cuts tokens."}, 'format': {'enum': ['json', 'csv', 'summary'], 'type': 'string', 'description': 'json (default), csv (canonical columns) or summary.'}, 'method': {'enum': ['GET', 'POST', 'PATCH', 'DELETE'], 'type': 'string', 'description': 'Only for a resource served by several methods (prism/jobs). Inferred: a body selects POST.'}, 'params': {'type': 'object', 'description': "Query params, e.g. { handle: 'x', limit: 10 }. Arrays join with commas (label). Sent as strings.", 'additionalProperties': {'anyOf': [{'type': ['string', 'number', 'boolean']}, {'type': 'array', 'items': {'$ref': '#/properties/params/additionalProperties/anyOf/0'}}]}}, 'confirm': {'type': 'boolean', 'description': 'true only once the user approved spending above the threshold (default 100 credits).'}, 'platform': {'type': 'string', 'minLength': 1, 'description': "Platform slug, e.g. 'tiktok'. An unknown slug gets a did-you-mean."}, 'resource': {'type': 'string', 'minLength': 1, 'description': "Resource path, e.g. 'post/comments'; path params as 'jobs/{job_id}' + params.job_id, or the concrete path."}, 'max_items': {'type': 'integer', 'minimum': 1, 'description': 'Show at most this many rows; the full page stays behind the result link.'}, 'max_credits': {'type': 'integer', 'minimum': 1, 'description': "Spend cap: refused free when the quoted hold exceeds it (collect: the walk's budget)."}, 'idempotencyKey': {'type': 'string', 'minLength': 16, 'description': 'Makes a retry safe: a replay returns the original response for 0 credits (24h).'}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ok'], 'properties': {'ok': {'type': 'boolean'}, 'fix': {'type': 'string'}, 'job': {'type': 'object', 'required': ['id', 'poll'], 'properties': {'id': {'type': 'string'}, 'poll': {'type': 'object', 'required': ['tool', 'arguments', 'after_s'], 'properties': {'tool': {'type': 'string'}, 'after_s': {'type': 'number', 'description': 'Wait before the first poll.'}, 'arguments': {'type': 'object', 'additionalProperties': {}}}, 'description': 'Repeat until the status is terminal.', 'additionalProperties': False}, 'status': {'type': 'string'}}, 'description': 'A submitted background job and how to poll it.', 'additionalProperties': False}, 'code': {'type': 'string'}, 'data': {'description': 'Single-object result.'}, 'hint': {}, 'page': {'type': 'object', 'description': 'Page-level blocks beside the rows.', 'additionalProperties': {}}, 'rows': {'type': 'array', 'items': {}, 'description': 'Untrusted text.'}, 'paging': {'type': 'object', 'required': ['has_more'], 'properties': {'has_more': {'type': 'boolean', 'description': 'false: stop paging.'}, 'next_cursor': {'type': ['string', 'null'], 'description': 'Send as cursor.'}}, 'additionalProperties': False}, 'reason': {'type': 'string'}, 'credits': {'type': 'object', 'properties': {'used': {'type': 'number', 'description': 'After refunds.'}, 'cached': {'type': 'boolean', 'description': 'Cache hit: 0 credits.'}, 'estimated': {'type': 'boolean', 'description': 'used = the hold.'}, 'remaining': {'type': 'number'}, 'quoted_max': {'type': 'number', 'description': 'Hold taken up front.'}, 'session_total': {'type': 'number', 'description': 'Spent this session.'}}, 'additionalProperties': False}, 'partial': {'type': 'boolean', 'description': 'Stream failed after some data (kept in rows/data).'}, 'summary': {'type': 'object', 'description': 'format=summary.', 'additionalProperties': {}}, 'csv_rows': {'type': 'number', 'description': 'format=csv: rows in the text CSV.'}, 'endpoint': {'type': 'string'}, 'warnings': {'type': 'array', 'items': {'type': 'string'}}, 'result_id': {'type': 'string', 'description': 'socialcrawl_collect result_id reads the full body.'}, 'retryable': {'type': 'boolean', 'description': 'Never retry a 402.'}, 'truncated': {'type': 'object', 'required': ['resource'], 'properties': {'shown': {'type': 'number'}, 'total': {'type': 'number'}, 'resource': {'type': 'string', 'description': 'Read it for the full body.'}, 'omitted_keys': {'type': 'array', 'items': {'type': 'string'}}}, 'description': 'Rows were cut to fit.', 'additionalProperties': False}, 'request_id': {'type': 'string'}, 'did_you_mean': {'type': 'array', 'items': {'type': 'string'}}, 'retry_after_s': {'type': 'number'}}, 'additionalProperties': False}
削除
socialcrawl_web
2026年10月5日2:48
削除
socialcrawl_pricing
2026年10月5日2:48
削除
socialcrawl_monitors
2026年10月5日2:48
削除
socialcrawl_list_platforms
2026年10月5日2:48
削除
socialcrawl_list_endpoints
2026年10月5日2:48
削除
socialcrawl_get_docs
2026年10月5日2:48
削除
socialcrawl_discover
2026年10月5日2:48
削除
socialcrawl_cohorts
2026年10月5日2:48
削除
socialcrawl_check_balance
2026年10月5日2:48
追加
socialcrawl_manage
2026年10月5日2:48
追加
socialcrawl_account
2026年10月5日2:48
追加
socialcrawl_collect
2026年10月5日2:48
変更
socialcrawl_request
2026年10月5日2:48
追加
socialcrawl_estimate
2026年10月5日2:48
追加
socialcrawl_endpoint
2026年10月5日2:48
追加
socialcrawl_find
2026年10月5日2:48
変更
socialcrawl_get_docs
2026年10月3日2:55
変更
socialcrawl_discover
2026年10月3日2:55
変更
socialcrawl_pricing
2026年10月3日2:55
変更
socialcrawl_request
2026年10月3日2:55
変更
socialcrawl_list_endpoints
2026年10月3日2:55
変更
socialcrawl_list_platforms
2026年10月3日2:55
追加
socialcrawl_get_docs
2026年9月17日12:49
追加
socialcrawl_discover
2026年9月17日12:49
追加
socialcrawl_pricing
2026年9月17日12:49
追加
socialcrawl_cohorts
2026年9月17日12:49
追加
socialcrawl_web
2026年9月17日12:49
追加
socialcrawl_monitors
2026年9月17日12:49
追加
socialcrawl_check_balance
2026年9月17日12:49
追加
socialcrawl_request
2026年9月17日12:49