TrueScrape
REMOTE · API.TRUESCRAPE.COM · 2 COMPONENTS
Live context for your agent: competitors, mentions and markets, from public data.
Available components
Last scanned (6 hours ago)
Scores higher than 44% of remote servers
Reachable. Last reached 5 Nov 2026.
Category News and Social
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 Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cancel_watch). See how to fix → View diagnostics → Fail
- 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
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 34170 tokens (~126/item across 271 items; 271 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 Management20
- Stability check failed: schema churn in the 6 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 17 additions. See how to fix → Fail
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 64% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 272 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 16 to 20.
- 4 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “google_shopping” rewrote its description, which is the text the model reads security
- Tool “identity_findSocialProfiles” rewrote its description, which is the text the model reads security
- Tool “google_news” rewrote its description, which is the text the model reads security
- Tool “google_search” rewrote its description, which is the text the model reads security
- Tool “google_jobs” rewrote its description, which is the text the model reads security
- Tool “google_mapsSearch” rewrote its description, which is the text the model reads security
- New tool “bilibili_video” functional
- New tool “flickr_post” functional
- New tool “mashable_video” functional
- New tool “okru_video” functional
- New tool “streamable_video” functional
- New tool “vimeo_video” functional
- 3 Nov 26 +1
- Tool “google_news” rewrote its description, which is the text the model reads security
- Tool “google_search” rewrote its description, which is the text the model reads security
- Tool “google_jobs” rewrote its description, which is the text the model reads security
- Tool “google_shopping” rewrote its description, which is the text the model reads security
- Tool “twitter_tweet” rewrote its description, which is the text the model reads security
- Tool “twitter_userTweets” rewrote its description, which is the text the model reads security
- Tool “google_mapsSearch” rewrote its description, which is the text the model reads security
- “google_mapsSearch” reworded the description of “uule” cosmetic
- “google_news” reworded the description of “tld” cosmetic
- “google_news” reworded the description of “uule” cosmetic
- “google_search” reworded the description of “date_posted” cosmetic
- “google_search” reworded the description of “page” cosmetic
- “google_shopping” reworded the description of “start” cosmetic
- “google_shopping” reworded the description of “tbs” cosmetic
- “google_shopping” reworded the description of “uule” cosmetic
- “twitter_userTweets” reworded the description of “count” cosmetic
- “google_jobs” reworded the description of “start” cosmetic
- “google_jobs” reworded the description of “uule” cosmetic
- 2 Nov 26 0
- Stability: 0.07 → fail ▼ security
- A breaking change shipped without a version bump: still 0.1.0 ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “create_monitor” rewrote its description, which is the text the model reads security
- Tool “create_watch” rewrote its description, which is the text the model reads security
- Tool “get_monitor_mentions” rewrote its description, which is the text the model reads security
- “create_monitor” added a required parameter “agent”, so existing callers break ▼ functional
- “create_watch” added a required parameter “agent”, so existing callers break ▼ functional
- New tool “call_tool” functional
- New tool “check_monitor” functional
- New tool “explore_tools” functional
- New tool “find_mentions” functional
- New tool “request_source” functional
- “get_monitor_mentions” added an optional parameter “platform” cosmetic
- “create_monitor” added an optional parameter “accounts” cosmetic
- “create_monitor” added an optional parameter “max_credits” cosmetic
- “create_monitor” added an optional parameter “schedule” cosmetic
- “create_monitor” added an optional parameter “stop_at” cosmetic
- “create_watch” added an optional parameter “max_credits” cosmetic
- “create_watch” added an optional parameter “stop_at” cosmetic
- “get_monitor_mentions” added an optional parameter “query” cosmetic
- “get_monitor_mentions” added an optional parameter “since” cosmetic
- “get_monitor_mentions” added an optional parameter “source” cosmetic
- “get_monitor_mentions” added an optional parameter “unread_only” cosmetic
- “walmart_category” reworded the description of “category” cosmetic
- 1 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- New tool “delete_monitor”, which the server declares destructive security
- New tool “create_monitor” functional
- New tool “get_monitor_mentions” functional
- New tool “hackernews_search” functional
- New tool “list_monitors” functional
- New tool “bluesky_search” functional
- 31 Oct 26 0
- Tool “instagram_transcript” rewrote its description, which is the text the model reads security
- Stability: unverified → 0.03 ▲ functional
- 30 Oct 26 60
First indexed and scored.
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 5 Nov 2026 · Probed https://api.truescrape.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.truescrape.com | CN=YR1,O=Let's Encrypt,C=US | 27 Oct 2026 | 25 Jan 2027 | RSA 4096 | SHA256-RSA | 53cb26ae4fd8b86eb6851bef5f445c05155 |
| SANs: api.truescrape.com | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.truescrape.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| truescrape.com. | absent | 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://api.truescrape.com/mcp | Verified | 200 | |
| http (plaintext) | http://api.truescrape.com/mcp | HTTPS enforced | 302 | https://api.truescrape.com/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 →
walmart_search walmart: Search Walmart ~94
Search Walmart. Public Walmart search results for a query: position, price, rating and availability per item. Costs 3 credits.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| country_code | string | – | – |
| page | number | – | – |
| query | string | yes | Search terms, e.g. "laptop" |
| tld | string | – | Walmart marketplace, default com. One of: com, ca |
No output schema declared.
No examples provided.
youtube_channel youtube: Channel details ~63
Channel details. Public details for a YouTube channel: subscribers, video count, description, links. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| handle | string | yes | Handle (@mrbeast), channel id (UC...), or full URL |
No output schema declared.
No examples provided.
youtube_channelCommunityPosts youtube: Channel community posts ~103
Channel community posts. A channel's Posts tab (what YouTube used to call Community). Images, multi-image carousels, shared videos and polls all come back as posts; poll options are under `raw`. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| handle | string | yes | Handle (@mrbeast), channel id (UC…), or full URL |
No output schema declared.
No examples provided.
youtube_channelLives youtube: Channel live streams ~118
Channel live streams. A channel's Live tab: streams that are live now, scheduled, or finished and still on the tab. `viewCount` is concurrent viewers while a stream is live and total views once it ends. YouTube swaps the label, and we surface whichever it gave us. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| handle | string | yes | Handle (@mrbeast), channel id (UC…), or full URL |
No output schema declared.
No examples provided.
youtube_channelPlaylists youtube: Channel playlists ~92
Channel playlists. Playlists a channel has made public. Pass an `id` from here to /v1/youtube/playlist for the videos in it. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| handle | string | yes | Handle (@mrbeast), channel id (UC…), or full URL |
No output schema declared.
No examples provided.
youtube_channelShorts youtube: Channel shorts ~182
Channel shorts. A channel's Shorts grid, newest first, about 48 per page. Shorts carry no duration or publish date on this surface, because YouTube does not render either, so both are null rather than guessed. With `extra_fetch=true`, each Short is fetched individually to fill its exact view count, publish date and duration. Costs 1 credit per item fetched, up to the page size. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| extra_fetch | string | – | When true, fetches each item's own page to fill fields the list page leaves null. Costs 1 extra credit per page fetched, up to the page size. |
| handle | string | yes | Handle (@mrbeast), channel id (UC…), or full URL |
No output schema declared.
No examples provided.
youtube_channelVideos youtube: Channel videos ~162
Channel videos. Recent public uploads for a channel. Use `tab` to switch between videos and shorts. With `extra_fetch=true`, each item is fetched individually to fill its exact view count, publish date and duration. Costs 1 credit per item fetched, up to the page size. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| extra_fetch | string | – | When true, fetches each item's own page to fill fields the list page leaves null. Costs 1 extra credit per page fetched, up to the page size. |
| handle | string | yes | Handle (@mrbeast), channel id, or full URL |
| tab | string | – | – |
No output schema declared.
No examples provided.
youtube_commentReplies youtube: Comment replies ~181
Comment replies. Replies to one comment thread. Takes a `cursor` from the `replyCursors` list on `/v1/youtube/video/comments`, or (as a convenience) a video `url` plus `comment_id`, in which case we locate the thread on the first comment page for you. Costs 1 credit. Pass either `cursor` (from `replyCursors` on /v1/youtube/video/comments), or both `url` and `comment_id`.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| comment_id | string | – | Top-level comment id (Ugx…) to fetch replies for |
| cursor | string | – | Reply cursor from `/v1/youtube/video/comments`, or `pagination.cursor` to page deeper |
| url | string | – | Video URL or id. Required only when using `comment_id` |
No output schema declared.
No examples provided.
youtube_communityPost youtube: Community post details ~80
Community post details. One community post by id or permalink, with its full text, attachments, like count and exact comment count. Poll questions and options are under `raw`. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| url | string | yes | Post URL (youtube.com/post/Ugk…) or bare post id |
No output schema declared.
No examples provided.
youtube_playlist youtube: Playlist contents ~91
Playlist contents. The videos in a public playlist, in playlist order, 100 per page. Playlist metadata (title, description, owner) comes back alongside the items. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| playlist_id | string | yes | Playlist id (PL…), or any URL containing `list=` |
No output schema declared.
No examples provided.
youtube_search youtube: Search videos ~74
Search videos. Public YouTube search results for a query: videos and Shorts in YouTube’s ranking order, with a cursor for the next page. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| query | string | yes | – |
No output schema declared.
No examples provided.
youtube_searchHashtag youtube: Search by hashtag ~110
Search by hashtag. Videos or Shorts carrying a hashtag, as YouTube ranks them on the hashtag landing page. `type=shorts` switches to the Shorts tab, which is a different result set rather than a filter over the same one. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| hashtag | string | yes | Hashtag, with or without the leading # |
| type | string | – | – |
No output schema declared.
No examples provided.
youtube_searchTypeahead youtube: Search typeahead ~102
Search typeahead. YouTube's own search suggestions for a partial query, the autocomplete list the search box shows. Useful as a keyword-research signal: these are ranked by what people actually search for. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| language | string | – | Interface language |
| query | string | yes | Partial search query |
| region | string | – | ISO 3166-1 alpha-2 country code |
No output schema declared.
No examples provided.
youtube_transcript youtube: Video transcript ~91
Video transcript. Full transcript for a YouTube video, as one text block plus timed cues. Returns the requested language when available, otherwise the default track. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| language | string | – | BCP-47 language code, e.g. "en", "es" |
| url | string | yes | Video URL or 11-character video id |
No output schema declared.
No examples provided.
youtube_trendingShorts youtube: Trending shorts ~196
Trending shorts. Shorts YouTube is currently surfacing, by region. Note that YouTube retired the global Trending feed (/feed/trending now serves the ordinary home feed), so this reads the ranked Shorts surface instead, which is what still exists. Results differ per request; it is deliberately not subscribable. With `extra_fetch=true`, each Short is fetched individually to fill its exact view count, publish date and duration. Costs 1 credit per item fetched, up to the page size. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| extra_fetch | string | – | When true, fetches each item's own page to fill fields the list page leaves null. Costs 1 extra credit per page fetched, up to the page size. |
| region | string | – | ISO 3166-1 alpha-2 country code |
No output schema declared.
No examples provided.
youtube_video youtube: Video or Short details ~58
Video or Short details. Public metadata for a YouTube video or Short, including view/like counts. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| url | string | yes | Video URL or 11-character video id |
No output schema declared.
No examples provided.
youtube_videoComments youtube: Video comments ~144
Video comments. Top-level comments on a video, about 20 per page. Pass `pagination.cursor` back as `cursor` for the next page. Each item that has replies also appears in `replyCursors`; feed that cursor to `/v1/youtube/video/comment-replies`. Use `order=newest` when polling for new comments, since `top` is re-ranked by YouTube and will churn. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| cursor | string | – | `pagination.cursor` from a previous response |
| order | string | – | – |
| url | string | yes | Video URL or 11-character video id |
No output schema declared.
No examples provided.
youtube_videoSponsors youtube: Video sponsors (inferred) ~113
Video sponsors (inferred). Brands, promo codes and affiliate links inferred from a video's description, plus YouTube's own paid-promotion disclosure. Every signal carries the description line it was read from and a confidence, because this is inference over prose. YouTube publishes no structured sponsor data. Experimental: expect to check `evidence` before acting on `low` confidence. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| url | string | yes | Video URL or 11-character video id |
No output schema declared.
No examples provided.
zillow_agent zillow: Zillow agent profile ~69
Zillow agent profile. Public Zillow agent/team profile: brokerage, license, rating and review count, where published. Costs 1 credit.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| url | string | yes | Zillow agent profile URL, e.g. https://www.zillow.com/profile/<username> |
No output schema declared.
No examples provided.
zillow_property zillow: Zillow listing details ~115
Zillow listing details. Public details for a Zillow listing: price, status, beds/baths, area, address and an inline photo set. Costs 1 credit. Pass either `zpid` or `url`.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| url | string | – | Zillow listing URL, e.g. https://www.zillow.com/homedetails/<slug>/<zpid>_zpid/ |
| zpid | string | – | Zillow property id (zpid), e.g. "120900080" |
No output schema declared.
No examples provided.
zillow_search zillow: Search Zillow listings by location ~109
Search Zillow listings by location. Public Zillow search results for a location, as full listing records. Costs 1 credit. Pass either `location` or `url`.
| Name | Type | Req | Description |
|---|---|---|---|
| cache_max_age | string | – | – |
| listing_type | string | – | – |
| location | string | – | City/state or ZIP, e.g. "Austin, TX" |
| page | number | – | – |
| url | string | – | Zillow search URL, e.g. https://www.zillow.com/austin-tx/ |
No output schema declared.
No examples provided.
How do I install the TrueScrape MCP server?
TrueScrape is a hosted endpoint at https://api.truescrape.com/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.truescrape.com
claude mcp add --transport http truescrape-truescrape 'https://api.truescrape.com/mcp'
What is the TrueScrape MCP server?
TrueScrape is an MCP server listed in the public MCP registry as io.github.TrueScrape/truescrape. Live context for your agent: competitors, mentions and markets, from public data. This page covers its hosted endpoint (https://api.truescrape.com/mcp).
Is the TrueScrape MCP server safe to use?
TrueScrape 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 TrueScrape MCP server expose?
TrueScrape exposes 271 tools: amazon_offers, amazon_product, amazon_search, amazon_shop, appleMusic_album, and 266 more. Their descriptions and schemas cost roughly 33,261 tokens of context every time the server is loaded.
Does the TrueScrape MCP server require authentication?
No. We connected to TrueScrape without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the TrueScrape MCP server still maintained?
TrueScrape is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.