# SocialCrawl (remote · mcp.socialcrawl.dev)

One API for 65 platforms and 572 endpoints: social, commerce, retail, jobs, finance, web scraping.

- Trust score: 64/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.socialcrawl.dev`: 64/100 (this document), [markdown](https://verifymcp.io/servers/ridiodevelopment-socialcrawl/mcp.md), [page](https://verifymcp.io/servers/ridiodevelopment-socialcrawl/mcp)
- npm · `socialcrawl-mcp`: 77/100, [markdown](https://verifymcp.io/servers/ridiodevelopment-socialcrawl/socialcrawl-mcp.md), [page](https://verifymcp.io/servers/ridiodevelopment-socialcrawl/socialcrawl-mcp)

## Channel facts

- Endpoint: `https://mcp.socialcrawl.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.10.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (socialcrawl_monitors).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5393 tokens (~539/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 50/100
  - Injection-marker check failed: the description of parameter "max_pages_per_identity" on tool "socialcrawl_cohorts" contains an instruction override, the text "ignore anything above", at byte 153 of that field.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the SocialCrawl MCP server?

SocialCrawl is a hosted endpoint at https://mcp.socialcrawl.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ridiodevelopment-socialcrawl 'https://mcp.socialcrawl.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ridiodevelopment-socialcrawl": {
      "url": "https://mcp.socialcrawl.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ridiodevelopment-socialcrawl": {
      "type": "http",
      "url": "https://mcp.socialcrawl.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ridiodevelopment-socialcrawl]
url = "https://mcp.socialcrawl.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ridiodevelopment-socialcrawl": {
      "type": "remote",
      "url": "https://mcp.socialcrawl.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ridiodevelopment-socialcrawl --url 'https://mcp.socialcrawl.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ridiodevelopment-socialcrawl:
    url: "https://mcp.socialcrawl.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ridiodevelopment-socialcrawl": {
      "Transport": "http",
      "Url": "https://mcp.socialcrawl.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ridiodevelopment-socialcrawl -t streamable-http -u 'https://mcp.socialcrawl.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ridiodevelopment-socialcrawl": {
      "type": "http",
      "url": "https://mcp.socialcrawl.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 62, +1)

- [security] Tool “socialcrawl_request” rewrote its description, which is the text the model reads
- [security] Tool “socialcrawl_get_docs” rewrote its description, which is the text the model reads
- [security] Tool “socialcrawl_list_endpoints” rewrote its description, which is the text the model reads
- [security] Tool “socialcrawl_list_platforms” rewrote its description, which is the text the model reads
- [security] Tool “socialcrawl_pricing” rewrote its description, which is the text the model reads
- [functional] Server version: 1.10.0 → 1.12.0
- [cosmetic] “socialcrawl_pricing” added an optional parameter “rows”
- [cosmetic] “socialcrawl_list_endpoints” added an optional parameter “hydrating”
- [cosmetic] “socialcrawl_pricing” added an optional parameter “include”
- [cosmetic] “socialcrawl_get_docs” reworded the description of “topic”
- [cosmetic] “socialcrawl_pricing” reworded the description of “action”

### 2026-09-13 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 59, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-08 (score 59)

First indexed and scored.

## MCP tools (10)

### `socialcrawl_list_platforms` (~175 tokens)

List SocialCrawl Platforms

List all 65 platforms available through SocialCrawl (575 endpoints — social media, commerce, marketplaces & product reviews, retail (Amazon, Walmart, Target, Home Depot, eBay, Klarna, AliExpress, Etsy, Sephora, H&M, Kohl's, Wayfair, Gumtree, Google Shopping), app stores, places, travel & local (Tripadvisor, Yelp, Google Business), business & software reputation (Trustpilot, G2), jobs & salaries, markets & finance, US congressional trading, news, web research and full scraping/browser automation, on-page SEO audits, prediction markets, search trends, Korean search (Naver), content analysis, and cross-platform Prism composites). Grouped by category, with each platform's endpoint count, credit range, and available data. No API key required.

### `socialcrawl_list_endpoints` (~403 tokens)

List Endpoints for a Platform

List endpoints with their full parameter contract — required + optional params, types, integer ranges, enum values, parameter couplings, CSV limits, pagination style, cache TTL, and per-endpoint pricing (including metered bands). Pass a `platform` for that platform's reference, or a `search` term to find an endpoint across all 65 platforms / 575 endpoints. Filter with `method`, `maxCost`, and `hydrating` (endpoints that can fill their own rows in one call via `include=`). No API key required.

Input parameters:

- `detail` (string): 'full' (default for a single platform) prints every parameter with its type, range, enum values, and couplings. 'compact' prints the summary table only — use it when searching broadly.
- `hydrating` (boolean): Only show endpoints that can fill their own rows in the same call via an `include=` row join (e.g. a search page that can carry engagement counts). Use it to find the one call that answers a question…
- `maxCost` (number): Only show endpoints that cost at most this many credits per call (metered endpoints are judged by their ceiling).
- `method` (string): Only show endpoints served with this HTTP method.
- `page` (integer): Page number (default 1). Output longer than one response is paged, not truncated — the footer says how many pages there are and repeats your filters.
- `platform` (string): Platform slug (e.g., 'tiktok', 'instagram', 'youtube'). Omit it and pass `search` to look for an endpoint across all platforms.
- `search` (string): Free-text search over endpoint names, summaries, descriptions, archetypes, and tags (e.g. 'transcript', 'reviews', 'followers'). Works with or without `platform` — without one it searches all platfor…

### `socialcrawl_request` (~528 tokens)

Make a SocialCrawl API Request

Make an API request to any of the 575 SocialCrawl endpoints. Fetches real-time data (profiles, posts, comments, transcripts, search results, products, offers and price history, reviews, apps, places and stores, jobs and salary ranges, news, market quotes and financial statements, congressional trade disclosures, SEO audits, trends, analytics, and cross-platform Prism composites) from 65 platforms. Most endpoints are GET (pass query params in `params`); batch endpoints (e.g. youtube/videos, prism/profiles) are POST — pass the array/object body in `body`. For web scraping/crawling/browser automation use the `socialcrawl_web` tool instead. Requires a valid SOCIALCRAWL_API_KEY. Validates the platform, resource, required params, oneOf groups, enum values, integer ranges, parameter couplings, and CSV limits locally first, so a malformed call fails free instead of burning credits. Reports the endpoint's price (and metered rule) with every response, and on an endpoint that supports row joins it either quotes the exact hold for the `include=` you sent or tells you the join is available and what it costs. Pass an optional idempotencyKey to make the request retry-safe (replays return the original response and deduct 0 credits).

Input parameters:

- `body` (object): JSON request body for POST batch endpoints (e.g. youtube/videos, prism/profiles). Put array/object params here — e.g. { ids: ['dQw4w9WgXcQ'] } or { items: [{ platform: 'tiktok', handle: '@scout2015'…
- `idempotencyKey` (string): Optional Idempotency-Key header. Lets you safely retry the same request — replays return the original response and deduct 0 credits (24h TTL).
- `params` (object): Query parameters as key-value pairs (e.g., { handle: 'charlidamelio' }). For GET endpoints these are the query string. For POST batch endpoints, put scalar query params here (e.g. { hl: 'en' }) and t…
- `platform` (string, required): Platform slug (e.g., 'tiktok', 'instagram', 'youtube')
- `resource` (string, required): Resource path (e.g., 'profile', 'post/comments', 'search')

### `socialcrawl_check_balance` (~259 tokens)

Check SocialCrawl Credit Balance

Check the credit balance and the credit ledger for the authenticated SocialCrawl account. Default view calls GET /v1/credits/balance (balance + recent-deduction summary); `view: "transactions"` calls GET /v1/credits/transactions for dispute-grade itemised receipts — every deduction and refund with its amount, balance_after, endpoint, and request_id, which is how you confirm what a metered endpoint actually charged after its upfront hold was refunded down. Both cost 0 credits. Requires a valid SOCIALCRAWL_API_KEY.

Input parameters:

- `cursor` (string): transactions: opaque keyset cursor from a previous response's next_cursor.
- `limit` (integer): transactions: page size (1-100, default 50).
- `requestId` (string): transactions: fetch the receipt(s) for one request id (e.g. 'req-a1b2c3d4e5f6').
- `view` (string): 'balance' (default) returns the current credit balance and recent-deduction summary. 'transactions' returns the itemised credit ledger — every deduction and refund keyed by request_id, which is how y…

### `socialcrawl_monitors` (~632 tokens)

Manage SocialCrawl Monitors

Create and manage stateful monitors that re-run any SocialCrawl recipe (a registry endpoint or a Prism composite) on a cadence (hourly/daily/weekly/cron), deliver each result to a signed webhook, raise alerts on metric thresholds/changes, and accumulate a per-run time-series. 'Prism answers once; monitors watch it for you.' Actions: create, list, get, runs, timeseries, pause, resume, delete. Managing monitors costs 0 credits; each scheduled run bills the underlying recipe's normal cost plus a 1-credit scheduling premium. Requires a valid SOCIALCRAWL_API_KEY.

Input parameters:

- `action` (string, required): Monitor operation: 'create' a scheduled monitor, 'list' your monitors, 'get' one, 'runs' for its run history, 'timeseries' for its metric series, 'pause'/'resume' it, or 'delete' it.
- `alert_rules` (array): create: optional alert rules on the recipe's computed metrics — e.g., [{ metric: 'negative_share', op: 'pct_change_gt', value: 25 }].
- `cadence` (string): create: 'hourly', 'daily', 'weekly', or a cron expression (e.g., '0 9 * * 1').
- `cursor` (string): list/runs: pagination cursor.
- `from` (string): runs/timeseries: ISO start of the time window.
- `id` (string): Monitor id. Required for get/runs/timeseries/pause/resume/delete.
- `include` (string): runs: set to 'result' to include each run's full stored result envelope.
- `limit` (integer): list/runs: page size (1-100, default 20).
- `metric` (string): timeseries: comma-separated metric keys to project (defaults to all stable computed keys).
- `name` (string): create: optional human-readable label.
- `output_schema` (object): create: optional JSON schema to shape the delivered payload.
- `params` (object): create: parameters passed to the recipe on every run (e.g., { keyword: 'acme' }).
- `recipe` (string): create: the recipe to run each cadence — any registered endpoint or Prism composite as 'platform/resource' (e.g., 'prism/brand-mentions', 'tiktok/profile').
- `status` (string): Filter. For list: 'active' | 'paused' | 'all'. For runs: 'ok' | 'partial' | 'failed' | 'skipped'.
- `suppress_webhook_unless_alert` (boolean): create: only fire the webhook when an alert rule trips (default false).
- `to` (string): runs/timeseries: ISO end of the time window.
- `webhook_secret` (string): create: optional signing secret (8-200 chars); otherwise one is generated and returned once.
- `webhook_url` (string): create: HTTPS URL that receives each run's signed (HMAC-SHA256) result.

### `socialcrawl_web` (~534 tokens)

SocialCrawl Web Scraping & Browser Automation

Full web scraping, search, and browser automation (Firecrawl-backed). Sync reads: 'scrape' (URL → markdown/HTML/screenshot/links), 'search' (web search with page content), 'map' (discover a site's URLs), 'extract' (LLM structured data from a page). Async jobs (submit, then poll with job_get/job_list, stop with job_cancel): 'crawl' a whole site, 'batch_scrape' many URLs, 'agent' (autonomous multi-step web task). Change detection: monitor_create/list/get/update/delete/checks (re-check a URL on a cadence → webhook). Interactive browser: session_create/get/list, session_execute (run code in the live page), session_close. Pricing varies by action (scrape 1cr, search 2cr, extract/session_create 5cr, agent 25cr; jobs/monitors/sessions management 0cr) — see the 'web' get_docs topic. Requires a valid SOCIALCRAWL_API_KEY.

Input parameters:

- `action` (string, required): Web operation. Sync (returns data now): scrape, search, map, extract. Async jobs: crawl, batch_scrape, agent → then job_get/job_list/job_cancel to poll, and job_errors for a job's per-page failure fe…
- `id` (string): Job / monitor / session id. Required for *_get, *_cancel, *_delete, *_update, *_checks, *_execute, and job_errors actions. Returned by the matching *_create / *_list action.
- `idempotencyKey` (string): Optional Idempotency-Key for the async job submitters (crawl, batch_scrape). Replays return the original job and deduct 0 credits.
- `input` (object): Operation parameters. For sync/GET actions these are query params (e.g. { url: 'https://example.com', formats: 'markdown,screenshot' } for scrape; { query: 'ai agents', limit: 10 } for search). For P…

### `socialcrawl_cohorts` (~1049 tokens)

SocialCrawl Cohorts — Audience-Filtered Mention Search

Answer 'which of THESE specific public identities is talking about my keywords?' — the opposite of open social listening. You upload a panel of up to 10,000 platform-qualified public handles (instagram, tiktok, youtube, twitter, threads, bluesky, truth-social, kwai, twitch, linkedin), submit a keyword query bounded to a recent window, and read back the matching posts per member PLUS a coverage record for every member, including the ones that matched nothing — so a partial crawl can never read as 'nobody talked about you'. Actions: create, add_members (1,000 per call, upsert on external_id so a nightly re-push is safe), estimate_cost (local, no API call — sizes the reservation before you commit), query (async, returns 202), query_status, query_results (paged, carries `items` + `coverage`), query_cancel, get, delete. Matching is deterministic: literal, whole-word, Unicode-normalized — no stemming, fuzzy matching, or alias inference. Every lifecycle call costs 0 credits; only the query is metered — it reserves a worst-case ceiling at submission and refunds down to the pages that actually succeeded. SocialCrawl only ever receives platform + handle + your opaque external_id, encrypted at rest. Requires a valid SOCIALCRAWL_API_KEY.

Input parameters:

- `action` (string, required): Cohort operation. Lifecycle order: 'create' a cohort → 'add_members' (up to 1,000 per call, 10,000 per cohort) → 'estimate_cost' locally to size max_credits → 'query' (async, 202) → 'query_status' un…
- `cohort_id` (string): Cohort id from 'create'. Required for get/delete/add_members/query.
- `cursor` (string): query_results: pass `next_cursor` back verbatim. Keep going until it is null.
- `date_from` (string): query (required): a full RFC3339 timestamp (e.g. '2026-08-01T00:00:00.000Z'), not a bare calendar date. It bounds how far back each crawl reaches.
- `date_to` (string): query: optional RFC3339 upper bound on the window.
- `idempotencyKey` (string): UUIDv4 for the write actions (create/add_members/query), which the API requires. Omit it and one is generated and echoed back — but supply your own (or reuse the echoed one) to make a retry replay th…
- `keywords` (array): query (required): up to 20 terms. Matching is literal and whole-word after Unicode NFKC case-folding — no stemming, fuzzy matching, or brand-alias inference. Pass 'Acme' and 'AcmeCo' separately if yo…
- `limit` (integer): query_results: page size, 1-500 (default 100). It governs the coverage list too.
- `max_credits` (integer): query (required, no default): your own safety limit. Submission fails with a 400 before any credit is held if the computed ceiling exceeds it — run action 'estimate_cost' first to size it.
- `max_items_per_identity` (integer): query (required, no default): item budget per member, 1-1,000.
- `max_pages_per_identity` (integer): query (required, no default) and estimate_cost: page budget per member, 1-20. Twitter, Bluesky, Threads and Twitch serve one fixed page per identity and ignore anything above 1.
- `members` (array): add_members (or estimate_cost): up to 1,000 identities per call, 10,000 per cohort. Rows are FLAT — a member with identities on several platforms is several rows sharing one external_id, not a nested…
- `name` (string): create: human-readable label, up to 120 characters.
- `platform_counts` (object): estimate_cost: the panel's platform mix as { instagram: 4000, youtube: 1000, ... } when you want a ceiling without passing the identities themselves.
- `platforms` (array): query: restrict the run to a subset of the platforms present in the cohort. Omit to query them all.
- `query_id` (string): Query id from 'query'. Required for query_status/query_results/query_cancel.
- `retention_days` (integer): create: 7-90, default 30. When it elapses the cohort and everything under it is purged. Uploading members or submitting a query renews the clock.

### `socialcrawl_pricing` (~760 tokens)

SocialCrawl Pricing & Credit Costs

Exact credit pricing for every one of the 575 SocialCrawl endpoints. 'overview' returns the tier ladder (329 standard / 211 advanced / 35 premium), every free endpoint, every flat override, all 71 metered endpoints with their min-max band and exact charging rule, cache TTLs, and the full refund matrix. 'endpoint' gives one endpoint's price, metered rule, price-driving parameters, paging cost, and worst case. 'platform' gives a platform's whole cost table. 'list' ranks and filters endpoints by cost (maxCost/minCost/model/search/sort) — e.g. "everything I can call for 1 credit" or "the most expensive endpoints". 'hydration' catalogues every opt-in `include=` row join — what each fills, its per-row rate, its row cap, and what a fully-joined page holds. On 'endpoint', pass the `include` (and `rows`) you intend to send and the band becomes the exact upfront hold, itemised per join. Use this before spending credits. No API key required.

Input parameters:

- `action` (string): 'overview' (default): the tier ladder, every free endpoint, every flat override, every metered band with its rule, cache TTLs, and the refund matrix. 'endpoint': one endpoint's exact price, metered r…
- `include` (string): endpoint: the `include=` row-join tokens you intend to send (comma-separated, e.g. 'engagement' or 'engagement,channel'). Turns the quoted band into the exact hold for that call, itemised per join. C…
- `limit` (integer): list: maximum rows to return (1-200, default 40).
- `maxCost` (number): list: only endpoints that can cost at most this many credits (metered judged by their ceiling).
- `method` (string): HTTP method. Disambiguates the `web` platform, where one resource is served by several methods; also filters the 'list' action.
- `minCost` (number): list: only endpoints that cost at least this many credits (metered judged by their floor).
- `model` (string): list: filter by billing model — 'ladder' (tier rate per request), 'flat' (per-endpoint override), 'metered' (query-dependent, ceiling deducted then refunded down), or 'free' (0 credits).
- `platform` (string): Platform slug. Required for 'endpoint' and 'platform' actions; filters the 'list' action.
- `resource` (string): Resource path for the 'endpoint' action (e.g., 'profile', 'comments', 'jobs/{job_id}').
- `rows` (integer): endpoint: the row cap you intend to send alongside `include` (the endpoint's own `limit`). A row join holds per row, so capping the rows caps the credits — quote it before you spend it.
- `search` (string): list: free-text filter over platform, resource, summary, and archetype.
- `sort` (string): list: sort order (default 'cost_desc' — most expensive first).

### `socialcrawl_discover` (~705 tokens)

SocialCrawl API Self-Discovery (utility endpoints)

The API describing itself, live, at 0 credits — the `/v1/utility/*` family. 'quickstart': everything needed for a first successful call (auth, base URL, response envelope, billing model, the full error taxonomy, rate limits, paging). 'catalog': every endpoint with its live metered-aware price, params, and paging flag — filter by platform/search/method. 'endpoint': one endpoint's complete usage guide — every parameter with type and example, the exact pricing rule, cache TTL, paging recipe, an example response, a copy-paste curl, and related endpoints. 'llms': the agent context corpus for the whole API or one platform. 'freshness': compare the live registry against this server's bundled catalogue to check whether this MCP version has fallen behind the API. 'status': every platform's live circuit-breaker state from the public `GET /v1/status` meta route — read it before retrying a persistent 502/503, since a degraded platform is the breaker holding traffic off a failing upstream. These answer from the live registry at request time, so unlike bundled data they can never drift from what is actually callable — use them when correctness matters more than latency, or when an endpoint looks unknown. Without an API key everything except 'llms' still answers from bundled data ('status' needs no key at all).

Input parameters:

- `action` (string): 'quickstart' (default): auth, base URL, envelope, billing, the error taxonomy, limits, and a first call — GET /v1/utility/quickstart. 'catalog': the machine-readable list of every endpoint with live…
- `format` (string): llms: 'markdown' (default) returns the corpus text; 'json' returns a structured context object.
- `id` (string): endpoint (required): the endpoint id as 'platform/resource' (e.g. 'tiktok/profile'), a path ('/v1/tiktok/profile'), or a full URL.
- `live` (boolean): Set false to answer from this server's bundled catalogue instead of calling the live API. Default is live whenever an API key is configured; without a key everything except 'llms' falls back to bundl…
- `method` (string): catalog: filter by HTTP method. endpoint: disambiguate a resource registered under more than one method (the stateful `web` family).
- `page` (integer): Page number (default 1). Long output is paged, not truncated.
- `platform` (string): Scope to one platform slug (e.g. 'tiktok'). Applies to quickstart, catalog, and llms.
- `search` (string): catalog: case-insensitive substring filter over endpoint paths and summaries.

### `socialcrawl_get_docs` (~348 tokens)

Get SocialCrawl Documentation

Retrieve SocialCrawl API documentation. Topics: 'overview' (compact intro), 'full' (comprehensive reference for all 575 endpoints), 'authentication', 'credits', 'pricing' (per-endpoint cost for every endpoint), 'errors', 'idempotency', 'pagination' (universal cursor contract), 'caching' (TTLs and free hits), 'hydration' (the opt-in `include=` row joins, what each fills and what it costs), 'response-schema' (the canonical envelope and unified objects), 'limits' (rate, concurrency, timeouts), 'monitors' (scheduled-recipe wrapper), 'cohorts' (audience-filtered mention search over a panel you supply), 'discovery' (the free self-describing utility endpoints), or any platform slug (e.g., 'tiktok', or 'web' for the web-scraping/browser-automation surface). No API key required.

Input parameters:

- `page` (integer): Page number for long topics (default 1). Topics longer than one response are paged rather than truncated — the footer tells you how many pages there are. 'full' and the largest platform topics span s…
- `topic` (string): Documentation topic: 'overview', 'full', 'authentication', 'credits', 'pricing' (per-endpoint costs), 'errors', 'idempotency', 'pagination', 'caching', 'hydration' (opt-in `include=` row joins), 'res…

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ridiodevelopment-socialcrawl/mcp#diagnostics

## Score history

- 2026-09-20: 64
- 2026-09-19: 64
- 2026-09-18: 63
- 2026-09-17: 63
- 2026-09-16: 62
- 2026-09-15: 62
- 2026-09-14: 61
- 2026-09-13: 61
- 2026-09-12: 60
- 2026-09-11: 60
- 2026-09-10: 60
- 2026-09-09: 59
- 2026-09-08: 59

## Common questions

### What is the SocialCrawl MCP server?

SocialCrawl is an MCP server listed in the public MCP registry as io.github.RidioDevelopment/socialcrawl. One API for 65 platforms and 572 endpoints: social, commerce, retail, jobs, finance, web scraping. This page covers its hosted endpoint (https://mcp.socialcrawl.dev/mcp).

### Is the SocialCrawl MCP server safe to use?

SocialCrawl scores 64 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SocialCrawl MCP server expose?

SocialCrawl exposes 10 tools: socialcrawl_list_platforms, socialcrawl_list_endpoints, socialcrawl_request, socialcrawl_check_balance, socialcrawl_monitors, and 5 more. Their descriptions and schemas cost roughly 5,393 tokens of context every time the server is loaded.

### Does the SocialCrawl MCP server require authentication?

No. We connected to SocialCrawl without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SocialCrawl MCP server still maintained?

SocialCrawl is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.socialcrawl.dev/mcp
- Repository: https://github.com/RidioDevelopment/socialcrawl-mcp
- Changelog RSS feed: https://verifymcp.io/servers/ridiodevelopment-socialcrawl/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ridiodevelopment-socialcrawl/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ridiodevelopment-socialcrawl/mcp