Stophy
REMOTE · API.STOPHY.DEV · 3 COMPONENTS
Search, read, and act on the web. The Stophy MCP server for agents.
Available components
Last scanned (13 hours ago)
Scores higher than 45% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Web Scraping
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. How we score → Why this is hard to score →
Endpoint Security66
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability46
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 3171 tokens (~634/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability check failed: schema churn in the 30 days we've observed: 3 tool removals, 0 breaking changes, 0 auth/transport breaks, 5 additions. See how to fix → Fail
Tool Coverage99
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 96% of tool parameters carry a description.Partial
- Structured output schemas are declared (80% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (12)
- TLS certificate
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 0
- “stophy_search” reworded the description of “query” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 20 Nov 26 0
- Tool “stophy_scrape” rewrote its description, which is the text the model reads security
- “stophy_map” added an optional parameter “deduplicateSimilarURLs” cosmetic
- 19 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “stophy_parse” rewrote its description, which is the text the model reads security
- Tool “stophy_map” rewrote its description, which is the text the model reads security
- Tool “stophy_search” rewrote its description, which is the text the model reads security
- Tool “stophy_scrape” rewrote its description, which is the text the model reads security
- “stophy_search” reworded the description of “scrapeOptions” cosmetic
- 18 Nov 26 −14
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “stophy_search_endpoints” was removed ▼ security
- Tool “stophy_call” was removed ▼ security
- Tool “stophy_crawl” was removed ▼ security
- Tool “stophy_describe_endpoint” was removed ▼ security
- Tool “stophy_extract” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “stophy_parse” rewrote its description, which is the text the model reads security
- Tool “stophy_search” rewrote its description, which is the text the model reads security
- Tool “stophy_map” rewrote its description, which is the text the model reads security
- Tool “stophy_scrape” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- Schema quality: 734 → 615 ▲ functional
- Schema quality: 734 → 609 ▲ functional
- Tool coverage: 67% → 80% ▲ functional
- Schema quality: 734 → 605 ▲ functional
- Destructive annotations: 0 → pass functional
- New tool “stophy_parse” functional
- “stophy_search” added an optional parameter “scrapeLimit” cosmetic
- “stophy_scrape” reworded the description of “includeTags” cosmetic
- “stophy_scrape” reworded the description of “lockdown” cosmetic
- “stophy_scrape” reworded the description of “maxAge” cosmetic
- “stophy_scrape” reworded the description of “maxChars” cosmetic
- “stophy_scrape” reworded the description of “minAge” cosmetic
- “stophy_scrape” reworded the description of “mobile” cosmetic
- “stophy_scrape” reworded the description of “offset” cosmetic
- “stophy_scrape” reworded the description of “onlyCleanContent” cosmetic
- “stophy_scrape” reworded the description of “onlyMainContent” cosmetic
- “stophy_scrape” reworded the description of “parsers” cosmetic
- “stophy_scrape” reworded the description of “profile” cosmetic
- “stophy_scrape” reworded the description of “proxy” cosmetic
- “stophy_scrape” reworded the description of “query” cosmetic
- “stophy_scrape” reworded the description of “redactPII” cosmetic
- “stophy_scrape” reworded the description of “removeBase64Images” cosmetic
- “stophy_scrape” reworded the description of “skipTlsVerification” cosmetic
- “stophy_scrape” reworded the description of “timeout” cosmetic
- “stophy_scrape” reworded the description of “waitFor” cosmetic
- “stophy_scrape” reworded the description of “zeroDataRetention” cosmetic
- “stophy_search” reworded the description of “categories” cosmetic
- “stophy_search” reworded the description of “country” cosmetic
- “stophy_search” reworded the description of “highlights” cosmetic
- “stophy_search” reworded the description of “lang” cosmetic
- “stophy_search” reworded the description of “limit” cosmetic
- “stophy_search” reworded the description of “location” cosmetic
- “stophy_search” reworded the description of “maxAge” cosmetic
- “stophy_search” reworded the description of “query” cosmetic
- “stophy_search” reworded the description of “scrapeOptions” cosmetic
- “stophy_search” reworded the description of “sources” cosmetic
- “stophy_search” reworded the description of “tbs” cosmetic
- “stophy_search” reworded the description of “timeout” cosmetic
- “stophy_scrape” reworded the description of “linkStyle” cosmetic
- “stophy_map” reworded the description of “ignoreCache” cosmetic
- “stophy_map” reworded the description of “search” cosmetic
- “stophy_map” reworded the description of “sitemap” cosmetic
- “stophy_scrape” reworded the description of “actions” cosmetic
- “stophy_scrape” reworded the description of “blockAds” cosmetic
- “stophy_scrape” reworded the description of “checkPromptInjection” cosmetic
- “stophy_scrape” reworded the description of “excludeTags” cosmetic
- “stophy_scrape” reworded the description of “fastMode” cosmetic
- “stophy_scrape” reworded the description of “formats” cosmetic
- “stophy_scrape” reworded the description of “headers” cosmetic
- 16 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “stophy_search” rewrote its description, which is the text the model reads security
- Tool “stophy_scrape” rewrote its description, which is the text the model reads security
- Tool “stophy_map” rewrote its description, which is the text the model reads security
- Tool “stophy_extract” rewrote its description, which is the text the model reads security
- Tool “stophy_crawl” rewrote its description, which is the text the model reads security
- “stophy_scrape” reworded the description of “actions” cosmetic
- “stophy_scrape” reworded the description of “checkPromptInjection” cosmetic
- “stophy_scrape” reworded the description of “formats” cosmetic
- “stophy_scrape” reworded the description of “parsers” cosmetic
- “stophy_scrape” reworded the description of “profile” cosmetic
- “stophy_scrape” reworded the description of “waitFor” cosmetic
- “stophy_scrape” reworded the description of “zeroDataRetention” cosmetic
- “stophy_search” reworded the description of “scrapeOptions” cosmetic
- “stophy_extract” reworded the description of “zeroDataRetention” cosmetic
- “stophy_extract” reworded the description of “webhook” cosmetic
- “stophy_extract” reworded the description of “enableWebSearch” cosmetic
- “stophy_extract” reworded the description of “allowExternalLinks” cosmetic
- “stophy_crawl” reworded the description of “zeroDataRetention” cosmetic
- 15 Nov 26 0
- Tool “stophy_search” rewrote its description, which is the text the model reads security
- Tool “stophy_scrape” rewrote its description, which is the text the model reads security
- “stophy_search” reworded the description of “categories” cosmetic
- “stophy_search” reworded the description of “sources” cosmetic
- 14 Nov 26 0
- Tool “stophy_scrape” rewrote its description, which is the text the model reads security
- Tool “stophy_search” rewrote its description, which is the text the model reads security
- “stophy_search” reworded the description of “highlights” cosmetic
- “stophy_search” reworded the description of “sources” cosmetic
- “stophy_search” reworded the description of “scrapeOptions” cosmetic
- “stophy_search” reworded the description of “categories” cosmetic
- 13 Nov 26 +1
- Tool coverage: 75% → 97% ▲ functional
- “stophy_extract” added an optional parameter “limit” cosmetic
- “stophy_extract” added an optional parameter “timeout” cosmetic
- “stophy_search” added an optional parameter “lang” cosmetic
- “stophy_crawl” reworded the description of “delay” cosmetic
- “stophy_crawl” reworded the description of “maxDiscoveryDepth” cosmetic
- “stophy_scrape” reworded the description of “actions” cosmetic
- “stophy_scrape” reworded the description of “parsers” cosmetic
- “stophy_scrape” reworded the description of “proxy” cosmetic
- “stophy_scrape” reworded the description of “timeout” cosmetic
- “stophy_search” reworded the description of “highlights” cosmetic
- “stophy_search” reworded the description of “limit” cosmetic
- “stophy_search” reworded the description of “scrapeOptions” cosmetic
- “stophy_crawl” dropped the optional parameter “alexandria” cosmetic
- “stophy_crawl” dropped the optional parameter “auditMetadata” cosmetic
- “stophy_crawl” dropped the optional parameter “domainTools” cosmetic
- “stophy_crawl” dropped the optional parameter “ignoreRobotsTxt” cosmetic
- “stophy_crawl” dropped the optional parameter “robotsUserAgent” cosmetic
- “stophy_crawl” dropped the optional parameter “threatProtection” cosmetic
- “stophy_extract” dropped the optional parameter “alexandria” cosmetic
- “stophy_extract” dropped the optional parameter “auditMetadata” cosmetic
- “stophy_extract” dropped the optional parameter “domainTools” cosmetic
- “stophy_extract” dropped the optional parameter “ignoreRobotsTxt” cosmetic
- “stophy_extract” dropped the optional parameter “robotsUserAgent” cosmetic
- “stophy_extract” dropped the optional parameter “threatProtection” cosmetic
- “stophy_map” dropped the optional parameter “alexandria” cosmetic
- “stophy_map” dropped the optional parameter “auditMetadata” cosmetic
- “stophy_map” dropped the optional parameter “domainTools” cosmetic
- “stophy_map” dropped the optional parameter “ignoreRobotsTxt” cosmetic
- “stophy_map” dropped the optional parameter “robotsUserAgent” cosmetic
- “stophy_map” dropped the optional parameter “threatProtection” cosmetic
- “stophy_scrape” dropped the optional parameter “alexandria” cosmetic
- “stophy_scrape” dropped the optional parameter “auditMetadata” cosmetic
- “stophy_scrape” dropped the optional parameter “domainTools” cosmetic
- “stophy_scrape” dropped the optional parameter “ignoreRobotsTxt” cosmetic
- “stophy_scrape” dropped the optional parameter “robotsUserAgent” cosmetic
- “stophy_scrape” dropped the optional parameter “threatProtection” cosmetic
- “stophy_scrape” dropped the optional parameter “toolDetail” cosmetic
- “stophy_search” dropped the optional parameter “domainTools” cosmetic
- “stophy_search” dropped the optional parameter “enterprise” cosmetic
- “stophy_search” dropped the optional parameter “threatProtection” cosmetic
- “stophy_search” dropped the optional parameter “toolDetail” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://api.stophy.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.stophy.dev | CN=YE2,O=Let's Encrypt,C=US | 25 Sept 2026 | 24 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 5b208f1a536d36a6e92dff20f3fbad5a1f2 |
| SANs: api.stophy.dev | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.stophy.dev. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | DS published | 60074 | 8 | Verified |
| stophy.dev. | DS published | 2371 | 13 | Verified |
| api.stophy.dev. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.stophy.dev/mcp | Verified | 200 | |
| http (plaintext) | http://api.stophy.dev/mcp | HTTPS enforced | 301 | https://api.stophy.dev/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
stophy_map Web Map ~256
Free without authentication, within limits. The prices below apply to authenticated calls. Scrape the list of pages on a website. $0.50 per 1,000 calls.
| Name | Type | Req | Description |
|---|---|---|---|
| deduplicateSimilarURLs | boolean | – | Send false to list distinct addresses such as /docs/a, /docs/a/ and... |
| ignoreCache | boolean | – | Send true to build the list again instead of reusing one made in the... |
| ignoreQueryParameters | boolean | – | List each page once, without its ?query part. |
| includeSubdomains | boolean | – | Also list pages on subdomains, such as docs.bun.com for bun.com. |
| limit | integer | – | The most addresses to return, up to 100000. |
| location | object | – | Where to read the page from. The default is the United States. |
| search | string | – | Keep only addresses that mention these words, best matches first... |
| sitemap | string | – | include uses the site's sitemaps and its pages. only lists just what... |
| timeout | integer | – | Stop looking after this many milliseconds and return what was found. |
| url | string | yes | Any page of the site to map, such as https://bun.com. |
| Name | Type | Req | Description |
|---|---|---|---|
| costUsd | number | yes | – |
| creditsUsed | number | yes | – |
| requestId | string | yes | – |
| success | boolean | – | – |
No examples provided.
stophy_parse Web Parse ~618
Free without authentication, within limits. The prices below apply to authenticated calls. Turn a PDF, Word, Excel, PowerPoint or HTML file, or a picture of text, into markdown. $0.50 per 1,000 pages or files whose text comes from a text layer, and $2.50 per 1,000 pages or pictures read from their picture, up to maxPages; summary and json with a schema or a prompt add $3 per 1,000 each; zero data retention adds $2 per 1,000 calls. metadata.costUsd shows what the call cost in dollars.
| Name | Type | Req | Description |
|---|---|---|---|
| blockAds | – | – | Ad blocking. Accepted so a client that always sends it works; a file... |
| excludeTags | array | – | For an HTML file: drop what these CSS selectors match. |
| fastMode | – | – | Page-read speed. Accepted so a client that always sends it works; a... |
| file | string | – | The file's bytes as base64, up to 36 MB: a PDF, a Word .docx, an... |
| filename | string | – | The file's name, such as report.docx. |
| formats | array | – | What to return. Each entry is a name, or an object for options and fields. |
| headers | – | – | Page request headers. Accepted so a client that always sends it... |
| includeTags | array | – | For an HTML file: keep only what these CSS selectors match. |
| location | – | – | Page country and languages. Accepted so a client that always sends it... |
| maxPages | integer | – | Read at most this many PDF pages, sheets or slides; isTruncated says... Pages of a PDF with no text layer are read from their picture, up to 20 of them, at $2.50 per 1,000 pages. |
| mobile | – | – | Mobile page view. Accepted so a client that always sends it works; a... |
| onlyMainContent | boolean | – | For an HTML file: send false to keep navigation and footers. |
| options | object | – | How to read the file and what to send back, with the same names... |
| parsers | array | – | How to read PDF pages. Other files ignore it. |
| profile | – | – | Saved browser profile. Accepted so a client that always sends it... |
| proxy | – | – | Page proxy. Accepted so a client that always sends it works; a file... |
| removeBase64Images | boolean | – | For an HTML file: send false to keep images that carry their data in... |
| skipTlsVerification | – | – | TLS checks of a page. Accepted so a client that always sends it... |
| timeout | – | – | Page load time. Accepted so a client that always sends it works; a... |
| uploadRef | string | – | Not available over MCP. Send the file as base64 in file. |
| zeroDataRetention | boolean | – | Send true to keep nothing from this call: no stored result is read or... Adds $2 per 1,000 pages. |
| Name | Type | Req | Description |
|---|---|---|---|
| costUsd | number | yes | – |
| creditsUsed | number | yes | – |
| requestId | string | yes | – |
| success | boolean | – | – |
No examples provided.
stophy_scrape Web Scrape ~1,565
Free without authentication, within limits. The prices below apply to authenticated calls. Scrape any public web page as markdown, HTML, links, a screenshot or JSON. $1 per 1,000 pages, however they are reached. checkPromptInjection adds $2.50 per 1,000 pages when the scan runs, json with a schema or a prompt, summary, highlights, question, product, menu and changeTracking in json mode add $3 per 1,000 pages each when they return something. CSS rules and attributes add nothing. A named parser uses its own price. Any page read or other paid format you ask for is charged separately. A PDF adds $0.50 per 1,000 pages of text from its text layer and $2.50 per 1,000 pages of text read from its picture that come back, so a PDF read with maxChars, offset or query is charged for the share of its pages that it returns, at least 1 page. Browser actions add nothing. An answer from a stored copy within maxAge costs $1 per 1,000 pages like any page. An unreadable page costs nothing. The base page price is waived for a readable 404 or 410. zeroDataRetention adds $2 per 1,000 scraped URLs, not per PDF page. A page that comes back with an error status does not incur the zeroDataRetention surcharge. metadata.costUsd shows what the call cost in dollars. To pull fields from any page, send formats [{"type":"json","schema":{...}}] or [{"type":"json","prompt":"..."}]; a schema or a prompt needs an API key. To get a site's own data as JSON, send the site's page URL with formats [{"type":"json","parser":"<name>"}], where the parser is named for the site and the thing, as in amazon-product, and put extra inputs such as page or filters in options. Some sites can only be read this way. Parsers by site: google: maps, maps-place, maps-reviews, trends, patents, ads, flights, hotels, play-app, play-search, play-reviews; upwork: search, job; craigslist: search, listing; careers: jobs, job; indeed: search, job; realtor: search, property; zillow: search, property; expedia: hotels; booking: search, h…
| Name | Type | Req | Description |
|---|---|---|---|
| actions | array | – | Steps to run on the page before reading it, in order. |
| blockAds | boolean | – | Ads and trackers are not loaded when a page runs in a browser. |
| checkPromptInjection | boolean | – | Send true to scan the page text for instructions aimed at an AI model... The scan adds $2.50 per 1,000 pages when it runs; a page it cannot scan fully comes back with a warning and no charge. |
| excludeTags | array | – | Remove the parts of the page that match these CSS selectors, such as... |
| fastMode | boolean | – | Send true to read the page without opening a browser: the answer... |
| formats | array | – | What to return. Each entry is a name, or an object for options and fields. |
| headers | object | – | Extra request headers to send to the site, such as { "x-plan": "pro"... |
| includeTags | array | – | Keep only the parts of the page that match these CSS selectors, such... |
| linkStyle | string | – | How links appear in the markdown. inline keeps [text](address).... |
| location | object | – | Where to read the page from. The default is the United States. |
| lockdown | boolean | – | Send true to answer only from a stored copy of the page and never... |
| maxAge | integer | – | Accept a stored answer up to this many milliseconds old, at most 30... |
| maxChars | integer | – | Cut the markdown at this many characters; isTruncated says when that... |
| minAge | integer | – | Answer only from a stored copy that is at least this many... |
| mobile | boolean | – | Read the page as a phone would: a phone-sized screen and the mobile... |
| offset | integer | – | Start the markdown this many characters into the page, PDF or file. |
| onlyCleanContent | boolean | – | Send true to have a model remove what onlyMainContent leaves behind... |
| onlyMainContent | boolean | – | Keep only the page's main content, without menus, headers, footers... |
| parsers | array | – | Only the pdf parser exists. Send "pdf" or { "type": "pdf", mode... Each page of text that comes back costs $0.50 per 1,000 pages from its text layer and $2.50 per 1,000 pages from its picture. |
| profile | object | – | Read the page with the cookies and local storage that earlier calls... A call with a profile always loads the page in a browser, costs $1 per 1,000 pages, the same as any page, and is never answered… |
| proxy | string | – | auto: basic first, enhanced once if the site refuses. basic: one... |
| query | string | – | What you are looking for on the page, such as refund window. |
| redactPII | – | – | Send true, or { mode, entities, replaceStyle }, to hide personal data in the markdown and what is made from it. |
| removeBase64Images | boolean | – | Images inside the page that carry their data in the address... |
| skipTlsVerification | boolean | – | Send true to read a page whose certificate is expired, self-signed or... |
| storeInCache | boolean | – | Send false to neither read nor keep a stored copy of this page. |
| timeout | integer | – | How long to keep trying, in milliseconds, from 1 second to 5 minutes... |
| url | string | yes | The page or PDF to read, such as https://bun.com/docs. |
| urls | – | – | – |
| waitFor | integer | – | Extra milliseconds to wait before reading, up to 60000, for pages... A read that waits costs $1 per 1,000 pages, the same as any page. |
| zeroDataRetention | boolean | – | Send true to keep nothing from this call: no stored copy is read or... Adds $2 per 1,000 scraped URLs, not per PDF page. |
| Name | Type | Req | Description |
|---|---|---|---|
| costUsd | number | yes | – |
| creditsUsed | number | yes | – |
| requestId | string | yes | – |
| success | boolean | – | – |
No examples provided.
stophy_search Search ~471
Free without authentication, within limits. The prices below apply to authenticated calls. Search the web, news, images, scholarly papers and YouTube videos in one call. $0.001 per block of up to 10 returned results, counted separately for each source and each research or videos list ($1 per 1,000 single-source searches returning 1 to 10 results). With scrapeOptions.formats, page reads and their add-ons use scrape pricing, starting at $1 per 1,000 pages for a standard read.
| Name | Type | Req | Description |
|---|---|---|---|
| categories | array | – | pdf: web results that are PDF files. research: scholarly papers, in a... |
| country | string | – | Two-letter country to search from, like us. uk is read as gb. |
| excludeDomains | array | – | – |
| highlights | boolean | – | Off by default. With true, a web result whose page we already hold... |
| ignoreInvalidURLs | boolean | – | Leave out results whose address cannot be read as a page. |
| includeDomains | array | – | – |
| lang | string | – | Two-letter language preference, like de. |
| limit | integer | – | Most results to return for each source. |
| location | string | – | Where to search from, like Germany or San Francisco,California,United... |
| maxAge | integer | – | Accept a stored answer up to this many milliseconds old, at most 30... |
| query | string | yes | What to search for, up to 1,000 characters. |
| safe | boolean | – | Hide explicit web, news and image results when true. |
| scrapeLimit | integer | – | With scrapeOptions formats: read only the top this many web results... |
| scrapeOptions | object | – | With formats, reads each web and news result, as many as scrapeLimit... With formats, page reads and their add-ons use scrape pricing, starting at $1 per 1,000 pages for a standard read. |
| sources | array | – | What to search: web, news, images. |
| tbs | string | – | Time filter: qdr:d, qdr:w, qdr:m or qdr:y, or... |
| timeout | integer | – | Milliseconds to wait for the sources, from 1,000 to 120,000; more is... |
| Name | Type | Req | Description |
|---|---|---|---|
| costUsd | number | yes | – |
| creditsUsed | number | yes | – |
| requestId | string | yes | – |
| success | boolean | – | – |
No examples provided.
stophy_signup Get a Stophy API key ~72
Needs no key. Returns a claimUrl for your person to approve and a secret code. Call it again with the code to collect the key once they approve. Returns at once, so call again later.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | – | The code from an earlier signup. Send it to collect the key once approved. |
No output schema declared.
No examples provided.
How do I install the Stophy MCP server?
Stophy is a hosted endpoint at https://api.stophy.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.
remote · api.stophy.dev
claude mcp add --transport http stophydotdev-mcp 'https://api.stophy.dev/mcp'
What is the Stophy MCP server?
Stophy is an MCP server listed in the public MCP registry as io.github.stophydotdev/mcp. Search, read, and act on the web. The Stophy MCP server for agents. This page covers its hosted endpoint (https://api.stophy.dev/mcp).
Is the Stophy MCP server safe to use?
Stophy scores 63 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 Stophy MCP server expose?
Stophy exposes 5 tools: stophy_scrape, stophy_search, stophy_map, stophy_parse, stophy_signup. Their descriptions and schemas cost roughly 2,982 tokens of context every time the server is loaded.
Does the Stophy MCP server require authentication?
No. We connected to Stophy without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Stophy MCP server still maintained?
Stophy is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Stophy MCP server?
VerifyMCP ran 12 checks on Stophy, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Stophy: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.