io.github.RidioDevelopment/socialcrawl

Est-ce que io.github.RidioDevelopment/socialcrawl est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.RidioDevelopment/socialcrawl » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 7 outils

• socialcrawl_account≈ 618 tokens

  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).

  Paramètres, retour & exemple (4)

  Paramètres

  • view · string · optionnel · balance | transactions | status | freshness
    balance (default, with this session's spend), transactions (ledger), status (platform health), freshness (catalogue vs live API).
  • limit · integer · optionnel
    transactions: page size.
  • cursor · string · optionnel
    transactions: next_cursor from the last page.
  • request_id · string · optionnel
    transactions: receipts for one request.

  Exemple d'appel

  {"name": "socialcrawl_account", "arguments": {"view": "balance", "limit": 1, "cursor": "texte", "request_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "fix": "texte", "code": "texte", "data": "texte", "rows": [], "view": "balance", "paging": {}, "reason": "texte", "credits": {}, "retryable": true, "request_id": "texte", "did_you_mean": []}}

• socialcrawl_collect≈ 1054 tokens

  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.

  Paramètres, retour & exemple (10)

  Paramètres

  • id · string · optionnel
    platform/resource of a paged endpoint, e.g. 'tiktok/post/comments'.
  • items · integer · optionnel
    Stop once this many unique rows are collected.
  • limit · integer · optionnel
    result_id: rows (200).
  • fields · string · optionnel
    Row paths as socialcrawl_endpoint lists them, e.g. 'comment.text,comment.engagement.likes'.
  • format · string · optionnel · jsonl | json | csv
    jsonl (default), json or csv.
  • offset · integer · optionnel
    result_id: first row.
  • params · object · optionnel
    Params for every page, as in socialcrawl_request. No cursor.
  • confirm · boolean · optionnel
    true only once the user approved spending above the threshold (default 100 credits).
  • result_id · string · optionnel
    Read a stored result instead of walking. Free.
  • max_credits · integer · optionnel
    Spend cap: refused free when the quoted hold exceeds it (collect: the walk's budget).

  Exemple d'appel

  {"name": "socialcrawl_collect", "arguments": {"id": "texte", "items": 1, "limit": 1, "fields": "texte", "format": "jsonl", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "fix": "texte", "code": "texte", "rows": [], "items": {}, "pages": 1, "total": 1, "format": "jsonl", "offset": 1, "paging": {}, "reason": "texte", "sample": []}}

• socialcrawl_endpoint≈ 442 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    'platform/resource' for its contract; a platform slug for its endpoint table; or a guide topic (errors, pricing, pagination, judgments, hydration, overview).
  • page · integer · optionnel
    Page of a long guide (default 1).
  • method · string · optionnel · GET | POST | PATCH | DELETE
    Only for an id served by several methods.

  Exemple d'appel

  {"name": "socialcrawl_endpoint", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "ok": true, "fix": "texte", "code": "texte", "method": "texte", "reason": "texte", "source": "live", "contract": {}, "retryable": true, "did_you_mean": [], "retry_after_s": 1}}

• socialcrawl_estimate≈ 710 tokens

  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.

  Paramètres, retour & exemple (7)

  Paramètres

  • id · string · optionnel
    'platform/resource'; a platform slug for its price table; none for the overview.
  • body · object · optionnel
    POST body, for batch endpoints.
  • plan · array · optionnel
    Several calls to total, instead of id.
  • calls · integer · optionnel
    Number of such calls (an array is read as plan).
  • items · integer · optionnel
    Rows wanted (prices a walk).
  • method · string · optionnel · GET | POST | PATCH | DELETE
  • params · object · optionnel
    The exact params you will send.

  Exemple d'appel

  {"name": "socialcrawl_estimate", "arguments": {"id": "texte", "body": {}, "plan": [], "calls": 1, "items": 1, "method": "GET"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "fix": "texte", "code": "texte", "plan": {}, "quote": {}, "reason": "texte", "source": "api", "warnings": [], "retryable": true, "did_you_mean": [], "retry_after_s": 1}}

• socialcrawl_find≈ 620 tokens

  Start here: a task in plain words -> the best endpoints (3 by default) of 646, 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.

  Paramètres, retour & exemple (3)

  Paramètres

  • task · string · optionnel
    The job in plain words; URLs and @handles in it are resolved and filled. Omit to list platforms.
  • limit · integer · optionnel
    Endpoints to return (default 3).
  • platform · string · optionnel
    Only this platform's endpoints (slug, e.g. 'tiktok'); alone, lists them.

  Exemple d'appel

  {"name": "socialcrawl_find", "arguments": {"task": "texte", "limit": 1, "platform": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "fix": "texte", "code": "texte", "note": "texte", "reason": "texte", "source": "api", "results": [], "resolved": [], "warnings": [], "retryable": true, "uncertain": true, "confidence": 1}}

• socialcrawl_manage≈ 471 tokens

  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. rows_new alerts need track (id=monitors).

  Paramètres, retour & exemple (6)

  Paramètres

  • id · string · optionnel
    Monitor, cohort, query, web job/monitor/session or prism job id.
  • area · string · requis · monitors | cohorts | web | jobs
    What to manage.
  • input · object · optionnel
    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.
  • action · string · requis
    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 · boolean · optionnel
  • idempotencyKey · string · optionnel
    For web crawl/batch, cohort writes and job submit.

  Exemple d'appel

  {"name": "socialcrawl_manage", "arguments": {"area": "monitors", "action": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• socialcrawl_request≈ 1328 tokens

  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.

  Paramètres, retour & exemple (11)

  Paramètres

  • body · object · optionnel
    JSON body for POST batch endpoints, e.g. { ids: [...] }.
  • fields · string · optionnel
    Row paths exactly as socialcrawl_endpoint lists them, e.g. 'post.id,post.content.text,post.engagement.*' (or an array). Cuts tokens.
  • format · string · optionnel · json | csv | summary
    json (default), csv (canonical columns) or summary.
  • method · string · optionnel · GET | POST | PATCH | DELETE
    Only for a resource served by several methods (prism/jobs). Inferred: a body selects POST.
  • params · object · optionnel
    Query params, e.g. { handle: 'x', limit: 10 }. Arrays join with commas (label). Sent as strings.
  • confirm · boolean · optionnel
    true only once the user approved spending above the threshold (default 100 credits).
  • platform · string · requis
    Platform slug, e.g. 'tiktok'. An unknown slug gets a did-you-mean.
  • resource · string · requis
    Resource path, e.g. 'post/comments'; path params as 'jobs/{job_id}' + params.job_id, or the concrete path.
  • max_items · integer · optionnel
    Show at most this many rows; the full page stays behind the result link.
  • max_credits · integer · optionnel
    Spend cap: refused free when the quoted hold exceeds it (collect: the walk's budget).
  • idempotencyKey · string · optionnel
    Makes a retry safe: a replay returns the original response for 0 credits (24h).

  Exemple d'appel

  {"name": "socialcrawl_request", "arguments": {"platform": "texte", "resource": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "fix": "texte", "job": {}, "code": "texte", "data": "texte", "hint": "texte", "page": {}, "rows": [], "paging": {}, "reason": "texte", "credits": {}, "partial": true}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.socialcrawl.dev/mcp