ScrapingBot MCP server
io.scrapingbot/scrapingbot
We checked this server on 2 November 2026 with McpStamp Check engine 1.2.0. It scored 70 of 100 (grade C), higher than 11.0% of the 33,003 registry servers that responded over HTTPS that day. Ready for Claude and MCP Registry. Not ready for ChatGPT and Gemini.
Measured facts
- Score
- 70C
- Sign-in
- API key or other
- Tools listed
- 23
- Protocol version
- 2025-11-25
Store readiness
| Store | Status | Reason |
|---|---|---|
| Claude Connectors Directory | Ready | No blocking check failed. |
| ChatGPT app directory | Not ready | Blocked by Sign-in method the store supports (OAuth or none), Protected resource metadata (RFC 9728), Authorization server metadata (RFC 8414 / OIDC) and Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT). |
| Gemini Connected Apps | Not ready | Blocked by Sign-in method the store supports (OAuth or none) and Authorization server metadata (RFC 8414 / OIDC). |
| Official MCP Registry | Ready | No blocking check failed. |
MCP Registry ready means a valid public remote for the registry, not that the server is listed in a store.
8 checks to fix
- Fails
Protected resource metadata (RFC 9728)
auth_prmBlocks ChatGPT.
Measured
Not found: https://scrapingbot.io/.well-known/oauth-protected-resource/api/mcp -> 404; https://scrapingbot.io/.well-known/oauth-protected-resource -> 404Serve RFC 9728 metadata at /.well-known/oauth-protected-resource (plus the path-suffixed form) with "resource" and "authorization_servers".
- Fails
Authorization server metadata (RFC 8414 / OIDC)
auth_as_metadataBlocks ChatGPT and Gemini.
Measured
Not found: https://scrapingbot.io/.well-known/oauth-authorization-server -> 404; https://scrapingbot.io/.well-known/openid-configuration -> 404Serve RFC 8414 metadata at <issuer>/.well-known/oauth-authorization-server with authorization_endpoint, token_endpoint and response_types_supported ["code"].
- Fails
Sign-in method the store supports (OAuth or none)
auth_methodBlocks ChatGPT and Gemini.
Measured
unknown method: HTTP 401 and no working OAuth discovery: the server expects a credential such as an API key or static tokenChatGPT and Gemini cannot send a static API key or token: add MCP OAuth (protected resource metadata and authorization server metadata), or serve the tools without auth. Claude accepts a static credential in a request header only in a beta
- Fails
Explicit readOnlyHint, destructiveHint and openWorldHint (ChatGPT)
tool_open_worldBlocks ChatGPT.
Measured
23/23 tools miss an explicit hint: listCapabilities, scrapeWebsite, extractStructuredData, getScrapeJob, pollJobUntilDone and 18 moreSet readOnlyHint, destructiveHint and openWorldHint to explicit true/false on every tool (OpenAI app review requires all three).
- Fails
401 carries WWW-Authenticate resource_metadata
auth_challengeMeasured
unknown method: HTTP 401 without WWW-AuthenticateOn 401, send WWW-Authenticate: Bearer resource_metadata="<protected resource metadata URL>".
- Warning
Tool descriptions
tool_descriptionsMeasured
2 under 60 chars: getScrapeJob, pollJobUntilDoneKeep each tool description between 60 and 2000 characters: when to use it, what it returns, key limits.
- Warning
initialize latency
latencyMeasured
1644 msBring initialize under 1.5 s: avoid cold starts and upstream calls in the handshake.
- Warning
JSON-RPC error for unknown method
jsonrpc_errorsMeasured
HTTP 401 instead of a JSON-RPC errorRoute the method first and answer unknown methods with JSON-RPC error -32601 before the auth check, or return a JSON-RPC error body with the 401.
13 checks passed, 6 did not run
Passed. Served over HTTPS, initialize over Streamable HTTP, Supported protocol version negotiated, JSON or SSE response Content-Type, GET answers SSE or 405, serverInfo name and version, Server instructions, tools capability declared, tools/list returns tools, inputSchema is an object schema, Tool names are valid and portable, readOnlyHint or destructiveHint on every tool, Human-readable title on every tool.
Not run. Resource metadata "resource" equals the server URL, First metadata URL Gemini tries answers 200 with the required fields, issuer equals the authorization_servers entry; token_endpoint_auth_methods_supported (ChatGPT), PKCE S256 advertised, Client registration (DCR or Client ID Metadata Documents), refresh_token grant advertised. These need an OAuth sign-in flow the check could not reach.
Run a fresh check
This page is the 2 November 2026 snapshot. If you maintain this server and have shipped fixes since then, re-check it. The live check and the badge show the current result, and the next snapshot will pick up the change.
README badge
The badge shows the latest score for this URL and links to this report.
Markdown
[](https://www.mcpstamp.com/r/io-scrapingbot-scrapingbot/)
HTML
<a href="https://www.mcpstamp.com/r/io-scrapingbot-scrapingbot/"><img src="https://www.mcpstamp.com/badge?url=https%3A%2F%2Fscrapingbot.io%2Fapi%2Fmcp" alt="McpStamp score" height="20"></a>
About this server
Public web data for AI agents: scrape any page, plus Google, TikTok, Instagram and Amazon as JSON.
The description above is the server's own text from the official MCP Registry. If a result looks wrong, run a fresh check and email support@zovo.one with the report link.
More grade C servers
- SocialDataX 今日头条 70
- xrpldashboard 70
- Autosophia Solana Lens 70
- Emberverse 69
- Court of Common Pleas (Peregrini) 69
- Scry 69
All grade C servers · All server reports · State of MCP readiness, November 2026