SocialCrawl
io.github.RidioDevelopment/socialcrawlVersion 2.2.0One API for social, commerce, travel, jobs, finance and web data, with exact credit pricing.
Status
Responds227 msAnswered our handshake without sign-in.- Last checked
- Nov 14, 2026, 14:41 UTC
- Latency
- 227 ms
- Remotes responding
- 1 of 1
- Sign-in
- No sign-in
- Hosting
- Hosted outside the EU (detected)
- Registry data as of
- Nov 14, 2026, 21:12 UTC
Data from the official MCP Registry, checked by run.zero. How we check
Connect
Streamable HTTP
https://mcp.socialcrawl.dev/mcpResponds227 msNo sign-in
Claude Code
claude mcp add --transport http socialcrawl https://mcp.socialcrawl.dev/mcpClaude Desktop and claude.ai
Settings > Connectors > Add custom connector
Name: socialcrawl
Remote MCP server URL: https://mcp.socialcrawl.dev/mcpCursor
{
"mcpServers": {
"socialcrawl": {
"url": "https://mcp.socialcrawl.dev/mcp"
}
}
}VS Code
code --add-mcp '{"name":"socialcrawl","type":"http","url":"https://mcp.socialcrawl.dev/mcp"}'Streamable HTTP
npm: socialcrawl-mcp 2.2.0Package only
npm (npx)
Replace <YOUR_SOCIALCRAWL_API_KEY> before running.
Built your own server? run.zero hosts MCP servers on European infrastructure.
Tools
7 tools
Read-only | Idempotent | Open world | ||
|---|---|---|---|---|
socialcrawl_accountFree: balance (default, with this session's spend), transactions (ledger), usage (per key per day; from/to YYYY-MM-DD, ≤92 days), status (health; check before retrying a 502/503), freshness (vs live catalogue), notifications (inbox). | No | Yes | Yes | Yes |
socialcrawl_collectWalk 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. | No | No | No | Yes |
socialcrawl_endpointRead 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. | No | Yes | Yes | Yes |
socialcrawl_estimateExact 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. | No | Yes | Yes | Yes |
socialcrawl_findStart here: a task in plain words -> the best endpoints (3 by default) of 733, 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. | No | Yes | Yes | Yes |
socialcrawl_manageBy area + action: monitors, cohorts, web (scrape, crawl, agents, page monitors, sessions), jobs, discover, search_runs (search lists, watches), creator_runs, review_history, events (feed, webhooks). Wrong fields refused free. Managing is free; scrapes, jobs, queries, run_more/include, monitor runs bill.
dry_run: true quotes, creating nothing. rows_new alerts need track. Docs: discover-runs, search-runs. | Yes | No | No | Yes |
socialcrawl_requestCall 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. | No | No | No | Yes |
Details
- Registry status
- Active
- Published
- Nov 8, 2026
- Updated
- Nov 8, 2026
- Website
- Not given
- Categories (suggested)
- Finance and paymentsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
- GDPR
- Not declared