Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

UpRock

REMOTE · MCP.UPROCK.AI

Fetch pages, search the web, verify sites, and search video from real devices in real locations.

Available components

+3 this week 74 Trust /100

Last scanned (15 hours ago)

Scores higher than 60% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

Trust breakdown (7 categories)

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 Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability60
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 3496 tokens (~499/item across 7 items; 7 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 Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 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
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

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 →

Changelog

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.

  • 19 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: v0.5.8 → v0.5.9 functional
  • 17 Nov 26 +1
    • Server version: v0.5.7 → v0.5.8 functional
  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1
    • Server version: v0.5.6 → v0.5.7 functional
  • 12 Nov 26 0
    • Server version: v0.5.5 → v0.5.6 functional
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Nov 26 0
    • Server version: v0.5.4 → v0.5.5 functional
    • Server version: v0.5.3 → v0.5.4 functional
  • 9 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
Diagnostics

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://mcp.uprock.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.uprock.ai CN=YE2,O=Let's Encrypt,C=US 14 Oct 2026 12 Jan 2027 ECDSA 256 ECDSA-SHA384 593190239c01c6773851d748a780dcfe0f8
SANs: mcp.uprock.ai
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 insecure

Validation of mcp.uprock.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
uprock.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.uprock.ai/mcp Verified 200
http (plaintext) http://mcp.uprock.ai/mcp HTTPS enforced 301 https://mcp.uprock.ai/mcp
MCP tools · 7 exposed · ~3,290 tokens

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 →

Tool Tokens
crawl_fetch ~564

Use when other fetch/search tools are blocked, rate-limited, return bot-check pages, or when you need results as a real person in a specific country or on a specific device type sees them. Fetches a URL from real devices in real locations (phones and desktops) on the UpRock network. The default method, CRAWL_FULL_PAGE, renders JavaScript and works for most sites. Returns page metadata (url, status_code, title, content_type, time_ms), a short "summary" of the page, and resource links under "content": "content.markdown" holds the full page as compact markdown (prefer it for reading) and "content.html" the raw HTML. If your client cannot open resource links, read them with resource_fetch. A "screenshots.viewport" link is included when a screenshot is available. meta.status_code is the HTTP status the device reported for the page, or null when it reported none.

NameTypeReqDescription
bodystring–Request body for POST/PUT methods. Provide as plain text.
countrystring–Where to execute the crawl FROM (device geographic placement). This controls the device's physical location, NOT the content topic — a crawl from Germany fetches the same URL but may see region-speci…
device_typestring–Device type to use (default: no constraint)
methodstring–HTTP method to use (default: CRAWL_FULL_PAGE). CRAWL_FULL_PAGE renders JavaScript and is the most reliable. GET is faster; use it only for static pages or API endpoints that need no JavaScript. POST…
retriesnumber–Number of speculative retries (default: 2, max: 3). When > 0, a new attempt starts every 7s using a separate device session. First success wins. Default of 2 means up to 3 concurrent sessions per cal…
timeout_secnumber–Timeout in seconds (default: 60, max: 300). For CRAWL_FULL_PAGE, values below 60 are silently raised to 60.
urlstringyesTarget URL to fetch. Auto-prefixed with https:// if no scheme is provided.

No output schema declared.

No examples provided.

resource_fetch ~299

Fetch the full content of an MCP resource URI. Use this when you need to read the actual content from a prior tool result and cannot resolve resource URIs natively (most hosted AI environments do not yet support native MCP resource fetching). This tool accepts crawl:// URIs from crawl_fetch responses, sweep:// URIs from verify results, and sitemaps:// URIs from sitemaps_generate results. For crawl_fetch, responses include a summary for quick analysis, plus crawl:// resource URIs pointing to the full content in markdown and HTML formats. When the summary is sufficient, you do not need this tool. When you need the complete page text — to extract specific data, parse tables, read full articles, etc. — pass the resource URI here to get the full content. For crawl_fetch results, use the markdown resource URI unless you specifically need raw HTML structure. Markdown is significantly more compact and easier to work with. For verify results, pass a sweep:// screenshot URI to retrieve the screenshot for visual inspection. For sitemaps_generate results, pass a sitemaps:// URI to read the llms.txt content for a domain or section.

NameTypeReqDescription
uristringyesA crawl://, sweep://, or sitemaps:// resource URI from a prior tool response (e.g. crawl://jobId/markdown, sweep://sweepId/region/jobIndex/screenshot, or sitemaps://domainId/llms.txt).

No output schema declared.

No examples provided.

sweep ~490

Deprecated: use the verify tool instead. sweep is the old name of verify, kept so existing setups keep working, and will be removed in a later release. It takes the same inputs and returns the same output. Verify a site works: load a URL on real devices in many regions and return status, load speed (Core Web Vitals) and screenshots, plus a shareable report link. Use this after deploying a website or service to verify it is up, responsive, and performing well from different parts of the world. Loads the target URL from multiple regions simultaneously, capturing performance metrics from each check. All checks (regions x tries) run concurrently, so the total operation time is approximately equal to the timeout value. Each completed check returns Core Web Vitals (TTFB, FCP, LCP, CLS), load times, transfer size, and HTTP protocol. Screenshots are captured and available as resource links in the response for visual verification if needed, but can be ignored if you only need the metrics. A run may complete with some failed checks. Inspect the failed_jobs count and per-job error fields in the response to identify issues. If the timeout passes before every region finishes, the checks that did finish are still returned with status "partial"; each region without a completed check has a status ("no_device" when no device in that region was available, otherwise "incomplete") and an "error" saying why. The response includes a "report_url" field with a link to a human-readable report page that can be shared with others for visual review of the results.

NameTypeReqDescription
devicestring–Device type (default: mobile). Options: mobile, desktop.
regionsarray–Geographic regions to test from: NA (North America), EU (Europe), APAC (Asia Pacific), LATAM (Latin America), MEA (Middle East & Africa). Default: [NA, EU, APAC] — these three regions have the fastes…
timeoutnumber–Global timeout in seconds for the entire run (default: 60). All checks run concurrently, so total wall-clock time is approximately this value.
triesnumber–Number of checks per region (default: 5). All checks across all regions run concurrently.
urlstringyesTarget URL to test.

No output schema declared.

No examples provided.

verify ~445

Verify a site works: load a URL on real devices in many regions and return status, load speed (Core Web Vitals) and screenshots, plus a shareable report link. Use this after deploying a website or service to verify it is up, responsive, and performing well from different parts of the world. Loads the target URL from multiple regions simultaneously, capturing performance metrics from each check. All checks (regions x tries) run concurrently, so the total operation time is approximately equal to the timeout value. Each completed check returns Core Web Vitals (TTFB, FCP, LCP, CLS), load times, transfer size, and HTTP protocol. Screenshots are captured and available as resource links in the response for visual verification if needed, but can be ignored if you only need the metrics. A run may complete with some failed checks. Inspect the failed_jobs count and per-job error fields in the response to identify issues. If the timeout passes before every region finishes, the checks that did finish are still returned with status "partial"; each region without a completed check has a status ("no_device" when no device in that region was available, otherwise "incomplete") and an "error" saying why. The response includes a "report_url" field with a link to a human-readable report page that can be shared with others for visual review of the results.

NameTypeReqDescription
devicestring–Device type (default: mobile). Options: mobile, desktop.
regionsarray–Geographic regions to test from: NA (North America), EU (Europe), APAC (Asia Pacific), LATAM (Latin America), MEA (Middle East & Africa). Default: [NA, EU, APAC] — these three regions have the fastes…
timeoutnumber–Global timeout in seconds for the entire run (default: 60). All checks run concurrently, so total wall-clock time is approximately this value.
triesnumber–Number of checks per region (default: 5). All checks across all regions run concurrently.
urlstringyesTarget URL to test.

No output schema declared.

No examples provided.

video_moment ~629

Fetch transcribed, time-stamped moments for a specific video URL. This is a CURSOR over the video pre-computed sliding-window moments (~30s windows on a ~25s grid, ~5s overlap) -- NOT a summary or sample of a time range. A call returns up to max_moments consecutive windows starting at start_s, in chronological order. To cover a long span you PAGINATE: read a page, then call again with start_s = next_start_s until has_more is false. If the video is not yet indexed, indexing starts automatically and the response tells you how long to wait. Moment text is model-generated from video frames plus verbatim ASR and may contain transcription artifacts. The response includes has_more / next_start_s for pagination and a stable moment_key per moment for dedupe. When following a video_search hit, pass its url, t0, and t1 as the url, start_s, and end_s of this tool. When include_images is set (not "none"), decoded keyframe IMAGES for each moment are returned inline as base64 ImageContent blocks, downscaled to 448px and re-encoded (WebP by default; JPEG if the server is configured with VIDEO_FRAME_FORMAT=jpeg -- the actual format is reported in the frame_format field). The frames_returned / frames_truncated / frame_format fields describe what was delivered so you can narrow scope (fewer moments, or a lower tier) for full fidelity. Frames always follow their moments in order. Only request images if you can view them.

NameTypeReqDescription
end_snumber–Upper bound of the range. <=0 (default) = a single moment at start_s; >0 = consecutive windows overlapping [start_s, end_s].
include_imagesstring–Return decoded keyframe IMAGES for each moment inline (base64, downscaled to 448px; re-encoded as WebP by default or JPEG per server config -- check frame_format in the response for the actual format…
max_momentsnumber–PAGE SIZE -- max windows returned per call (default 5; hard cap 10). Bounds how far FORWARD you read (~max_moments x 25s); it does NOT sample the whole range -- paginate for more.
start_snumber–Where to start reading / the pagination cursor (default 0).
urlstringyesRequired. Video URL (https:// auto-added).

No output schema declared.

No examples provided.

video_search ~234

Semantic search over indexed video moments. Finds the most relevant moments (time-stamped segments) across indexed videos for a natural-language query. Each result includes the source video, the moment's start/end timestamps, a relevance score, and the moment transcript when available. Results are ordered best-first and limited to the top 10 moments. Each result's url, t0, and t1 are the exact inputs to video_moment (pass them as its url, start_s, and end_s).

NameTypeReqDescription
order_by_recencyboolean–Sort results newest-first by publish date, with relevance as the tiebreak (default: false).
published_afternumber–Only include moments published at or after this unix timestamp (seconds, UTC).
published_beforenumber–Only include moments published at or before this unix timestamp (seconds, UTC).
querystringyesNatural-language search query.
tagsobject–Optional key/value facet filters.
unique_videosboolean–Return one (best) result per distinct video instead of per-moment hits (default: true).

No output schema declared.

No examples provided.

web_research ~629

Use when other fetch/search tools are blocked, rate-limited, return bot-check pages, or when you need results as a real person in a specific country or on a specific device type sees them. Searches the web with several engines (Bing, DuckDuckGo, Yahoo, plus regional engines) from real devices in real locations, and returns deduplicated results with url, title and description. suggested_countries sets where the search runs FROM, not what it is ABOUT: - Geography is the topic ('Paris hotels', 'history of the Berlin Wall') → keep it in the query and omit suggested_countries. - Geography is the perspective (what Europeans see when searching for beach holidays) → query='best beach destinations', suggested_countries=['EU']. - Both ('what Germans think about Italian food') → query='Italian food', suggested_countries=['EU']. To compare regions, make one call per region; do not combine them in one call. Deduplication can return fewer results than max_results; request 2-3x your target. Results are ordered by relevance, best first: pages ranked highly by several engines or regions come first. Each result has a "score" and the engine/country "sources" that returned it.

NameTypeReqDescription
max_resultsnumber–Maximum number of results to return (default: 12, max: 50). Actual count may be lower due to cross-source deduplication.
num_sourcesnumber–Maximum number of countries to query (default: 5, max: 20). Each country generates sources for all eligible providers, so the actual number of provider+country combinations may be higher. When sugges…
querystringyesSearch query terms. Include geographic terms only when they describe the TOPIC you are searching for (e.g., 'Tokyo tourist spots,' 'Brazilian coffee'). Do NOT add geographic terms to target a search…
suggested_countriesarray–Where to search FROM (the searcher's geographic perspective), NOT what to search ABOUT. When omitted, the server automatically selects optimal countries for broad global coverage — this is the correc…

No output schema declared.

No examples provided.

Install

How do I install the UpRock MCP server?

UpRock is a hosted endpoint at https://mcp.uprock.ai/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 · mcp.uprock.ai

# add to Claude Code
claude mcp add --transport http ai-uprock-mcp 'https://mcp.uprock.ai/mcp'
Common questions

What is the UpRock MCP server?

UpRock is an MCP server listed in the public MCP registry as ai.uprock/mcp. Fetch pages, search the web, verify sites, and search video from real devices in real locations. This page covers its hosted endpoint (https://mcp.uprock.ai/mcp).

Is the UpRock MCP server safe to use?

UpRock scores 74 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 UpRock MCP server expose?

UpRock exposes 7 tools: crawl_fetch, resource_fetch, sweep, verify, video_moment, and 2 more. Their descriptions and schemas cost roughly 3,290 tokens of context every time the server is loaded.

Does the UpRock MCP server require authentication?

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

Is the UpRock MCP server still maintained?

UpRock 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 UpRock MCP server?

VerifyMCP ran 13 checks on UpRock, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.