Show & Tell
REMOTE · PLAYSHOWANDTELL.COM
Daily photo game: you see a secret word, show it in photos, and your AI guesses it.
Available components
Last scanned (3 hours ago)
Scores higher than 15% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Entertainment and Games
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 Security81
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata. View diagnostics → Pass
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 401, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- 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
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability0
- Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http. See how to fix → View diagnostics → Unverified
Schema Quality & AI Usability0
- Schema blocked by authentication: the endpoint requires auth we don't have to read it. See how to fix → Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Tool Safety0
- Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Capabilities0
- Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. See how to fix → Unverified
Unverified: 6 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm. Claim this server and supply a read-only token to verify it and lift the score.
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.
- 25 Oct 26 −42
- Endpoint reachability: reachable → behind authorisation ▼ security
- Stability: 0.57 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → unverified ▼ security
- Authorization: partial → pass ▲ security
- First check of Authorization: pass security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- 24 Oct 26 0
- Resource “card” now points somewhere else: ui://show-and-tell/card-d1efa5de74.html → ui://show-and-tell/card-195c20474f.html security
- New tool “sign_in” functional
- 23 Oct 26 +1
- Resource “card” now points somewhere else: ui://show-and-tell/card-4dc23faf36.html → ui://show-and-tell/card-d1efa5de74.html security
- 22 Oct 26 0
- Resource “card” now points somewhere else: ui://show-and-tell/card-4073217feb.html → ui://show-and-tell/card-4dc23faf36.html security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “start_round” rewrote its description, which is the text the model reads security
- Schema quality: 382 → 428 ▼ functional
- “call_foul” added an optional parameter “mode” cosmetic
- “submit_guess” added an optional parameter “mode” cosmetic
- “use_lifeline” added an optional parameter “mode” cosmetic
- “get_status” reworded the description of “mode” cosmetic
- “start_round” reworded the description of “mode” cosmetic
- 21 Oct 26 +1
- Resource “card” now points somewhere else: ui://show-and-tell/card-73d810dfd3.html → ui://show-and-tell/card-4073217feb.html security
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +1
- Resource “card” now points somewhere else: ui://show-and-tell/card-6641d62da1.html → ui://show-and-tell/card-73d810dfd3.html security
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
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://playshowandtell.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=playshowandtell.com | CN=WE1,O=Google Trust Services,C=US | 6 Oct 2026 | 4 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | db339c26f8ebce881316a74a5d20a638 |
| SANs: playshowandtell.com, www.playshowandtell.com, *.www.playshowandtell.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of playshowandtell.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| playshowandtell.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On connection |
| HTTP status | 401 |
WWW-Authenticate challenge Bearer resource_metadata="https://playshowandtell.com/.well-known/oauth-protected-resource/mcp", scope="play"
Bearer resource_metadata="https://playshowandtell.com/.well-known/oauth-protected-resource/mcp", scope="play" | Header | Value |
|---|---|
| www-authenticate | Bearer resource_metadata="https://playshowandtell.com/.well-known/oauth-protected-resource/mcp", scope="play" |
Protected resource metadata
| Document | https://playshowandtell.com/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://playshowandtell.com/mcp |
| Authorisation server | https://playshowandtell.com/oauth |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://playshowandtell.com/mcp | Auth required | 401 | |
| http (plaintext) | http://playshowandtell.com/mcp | Inconclusive | 401 |
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 →
call_foul Call a Show & Tell foul ~336
Call a foul when words, not the picture, would do the telling: writing made for the game (a note, letter tiles), a screen held up to show something, a hint the user types about the word, or your guess is written in the photo. Writing that's already in the world (a label, a logo, a sign) is not a foul unless your guess is written in it. The photo doesn't count and no shot is used. In Get Out & Go, pass the star if you know it. In a friends challenge, pass its challenge code.
| Name | Type | Req | Description |
|---|---|---|---|
| challenge | string | – | A friends challenge code, like "K7QFX", when this call is for that challenge instead of the daily word. |
| mode | string | – | Which star game this photo is for, when the user has both Get Out & Go and a course in play: "go" or "courses". Leave it out to use the one they played last. |
| player | string | yes | The player code from start_round, e.g. "brave-otter-4821". The same code in every chat keeps the streak going. |
| reason | string | yes | "writing": writing made for the game. "screen": a screen stands in for the real thing. "typed_hint": the user typed a hint. "guess_in_photo": your guess is written in the photo. |
| star | integer | – | Get Out & Go only: which of the five words this is for, 1 to 5 stars. The user says it, or the card sends "Next photo's for the ★★★ word." |
No output schema declared.
No examples provided.
get_status Check Show & Tell status ~327
Check the user's Show & Tell day: whether today's word is played, their streak, whether the streak is at risk, and when the next word unlocks. Use it for check-ins and for daily reminders the user asked you to schedule. With mode "go" it checks Get Out & Go instead: whether today's list is open, how far along they are, and after 9 p.m. their results and the photobomb. With a challenge code it checks that friends challenge: who's in, who's done, and the board once it's out. Without one, the daily status also lists the user's challenges in play.
| Name | Type | Req | Description |
|---|---|---|---|
| challenge | string | – | A friends challenge code, like "K7QFX", when this call is for that challenge instead of the daily word. |
| mode | string | – | "go" for Get Out & Go: five words hiding outside, one at each star. "courses" for Courses: a run at a real place, five words written for it, on a clock. Leave it out for the daily word. |
| player | string | yes | The player code from start_round, e.g. "brave-otter-4821". The same code in every chat keeps the streak going. |
| timezone | string | – | The user's IANA timezone, e.g. "America/Los_Angeles". Always send it when you know it: the day changes at the user's local midnight, and Get Out & Go runs from 6 a.m. to 9 p.m. on their clock. Ask fo… |
No output schema declared.
No examples provided.
sign_in Sign in to Show & Tell ~178
Sign the user in to Show & Tell in this app, so every chat here plays as their account, with the same streak in any app they sign in from. Use it when the user asks to sign in, or to keep their streak in every chat. The app may show its own prompt to connect; when they're done, the call carries on. Pass the URL Show & Tell gave for this chat's round, so what they played here comes along.
| Name | Type | Req | Description |
|---|---|---|---|
| platform | string | – | The assistant product you run in: "Claude", "ChatGPT", "Muse", "Grok", "Gemini", or another name. |
| url | string | – | The URL Show & Tell gave in this chat for the user's round, the one only they visit, so what they played here comes along. Pass it as is; don't visit it. |
No output schema declared.
No examples provided.
start_challenge Start a Show & Tell challenge ~413
Set up a friends challenge. The user gets a code and an invite to paste into their group chat (texts, WhatsApp, anything), and everyone who joins plays the same secret word by the daily's rules: six shots, a hint is a shot, fewest shots wins, ties go to the fastest. The user plays their own round right away, like a daily round, with the challenge code on every call. Joining stays open for 2 hours (or 1 or 3, their pick) for up to 8 players, and the board stays hidden until everyone's done or 24 hours pass. Pass rematch with a finished challenge's code to play the same group again with a new word.
| Name | Type | Req | Description |
|---|---|---|---|
| ai_name | string | – | The name the user calls you, e.g. "Boo" or "Claude". |
| join_hours | integer | – | How long friends can join: 1, 2 or 3 hours. 2 unless the user says. |
| name | string | – | The first name the user's friends know them by, shown on challenge boards. Ask once if you don't know it. |
| platform | string | – | The assistant product you run in: "Claude", "ChatGPT", "Muse", "Grok", "Gemini", "Hermes", "Instinct", or another name. |
| player | string | – | The player code from start_round, e.g. "brave-otter-4821". The same code in every chat keeps the streak going. |
| rematch | string | – | A finished challenge's code, for a rematch with the same group and a new word. |
| timezone | string | – | The user's IANA timezone, e.g. "America/Los_Angeles". Always send it when you know it: the day changes at the user's local midnight, and Get Out & Go runs from 6 a.m. to 9 p.m. on their clock. Ask fo… |
No output schema declared.
No examples provided.
start_round Start Show & Tell ~659
Start or resume today's Show & Tell round. Show & Tell is a daily game you play with the user: they get a secret word you're not allowed to know, they send you photos of the real world, and you guess the word from the photos. Everyone gets the same word each day. Use this when the user wants to play or asks about today's word. The result has the score so far and how the user sees their word: on the Show & Tell card in apps that show it, or through a private link for the user. Only the user opens that link: it reveals the word, and opening it yourself voids the round. You start without the word's category; the user can spend a hint to reveal it. Leave player empty for a first-time player, then pass the returned code on every later call, including in new chats, so the streak carries over. With mode "go" it starts or resumes today's Get Out & Go instead: five words hiding outside, one at each star (1 to 5), open from 6 a.m. to 9 p.m. in the user's time zone. The user sees the five words on the card or a private /g/ link, never you. With mode "courses" it starts or resumes a Courses run instead: the result has a private /r/ link where the user checks in at a real place with their location; five words written for that place then start with a clock. With a challenge code it joins that friends challenge instead, or picks the user's round in it back up: the user says "Play Show & Tell challenge K7QFX". Pass name, the first name their friends know them by, for the board.
| Name | Type | Req | Description |
|---|---|---|---|
| ai_name | string | – | The name the user calls you, e.g. "Boo" or "Claude". Shown in the share grid. |
| challenge | string | – | A friends challenge code, like "K7QFX", when this call is for that challenge instead of the daily word. |
| mode | string | – | "go" for Get Out & Go: five words hiding outside, one at each star. "courses" for Courses: a run at a real place, five words written for it, on a clock. Leave it out for the daily word. |
| name | string | – | The first name the user's friends know them by, shown on challenge boards. Ask once if you don't know it. |
| platform | string | – | The assistant product you run in: "Claude", "ChatGPT", "Muse", "Grok", "Gemini", "Hermes", "Instinct", or another name. It decides the player's team. |
| player | string | – | The player code from start_round, e.g. "brave-otter-4821". The same code in every chat keeps the streak going. |
| timezone | string | – | The user's IANA timezone, e.g. "America/Los_Angeles". Always send it when you know it: the day changes at the user's local midnight, and Get Out & Go runs from 6 a.m. to 9 p.m. on their clock. Ask fo… |
No output schema declared.
No examples provided.
submit_guess Submit a Show & Tell guess ~398
Lock in exactly one single-word guess for the user's newest photo, or for the hint they just spent, based on all of today's photos together. First describe the photo to the user in one sentence (after a hint, say what it changes). One guess per new photo or hint: otherwise the next guess waits for the next photo. Writing that's already in the world is fine, but the guess can't be a word written in the photo. When writing was made for the game, a screen stands in for the real thing, the user types a hint, or your guess is written in the photo, use call_foul instead. Returns how close the guess is: cold, warm, hot, burning, or correct. In Get Out & Go, pass star: which of the five words the photo is for. Use every photo of that word so far. In a friends challenge, pass its challenge code.
| Name | Type | Req | Description |
|---|---|---|---|
| challenge | string | – | A friends challenge code, like "K7QFX", when this call is for that challenge instead of the daily word. |
| guess | string | yes | One word. Up to three words only for a fixed phrase. |
| mode | string | – | Which star game this photo is for, when the user has both Get Out & Go and a course in play: "go" or "courses". Leave it out to use the one they played last. |
| player | string | yes | The player code from start_round, e.g. "brave-otter-4821". The same code in every chat keeps the streak going. |
| read | string | – | One sentence on what you see in the photo (or what the hint changed), kept for the recap. |
| star | integer | – | Get Out & Go only: which of the five words this is for, 1 to 5 stars. The user says it, or the card sends "Next photo's for the ★★★ word." |
No output schema declared.
No examples provided.
use_lifeline Use a Show & Tell hint ~340
Use this only when the user asks for a hint. Reveals the word's category (after the first photo), its length (after 2 shots), or its first letter (after 4 shots). A hint is a shot of its own: right after it, call submit_guess with your guess, using every photo so far plus the hint; no new photo needed. One hint per shot. Each hint adds a 💡 to the user's share grid, and solving with no hints is the brag. In Get Out & Go, pass the star of the word, and kind "where" (where it's usually found), "letters" or "first_letter"; then guess that word right away with the same star. In a friends challenge, pass its challenge code; the hint shows on the board.
| Name | Type | Req | Description |
|---|---|---|---|
| challenge | string | – | A friends challenge code, like "K7QFX", when this call is for that challenge instead of the daily word. |
| kind | string | yes | – |
| mode | string | – | Which star game this photo is for, when the user has both Get Out & Go and a course in play: "go" or "courses". Leave it out to use the one they played last. |
| player | string | yes | The player code from start_round, e.g. "brave-otter-4821". The same code in every chat keeps the streak going. |
| star | integer | – | Get Out & Go only: which of the five words this is for, 1 to 5 stars. The user says it, or the card sends "Next photo's for the ★★★ word." |
No output schema declared.
No examples provided.
How do I install the Show & Tell MCP server?
Show & Tell is a hosted endpoint at https://playshowandtell.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 · playshowandtell.com
claude mcp add --transport http com-playshowandtell-show-and-tell 'https://playshowandtell.com/mcp'
What is the Show & Tell MCP server?
Show & Tell is an MCP server listed in the public MCP registry as com.playshowandtell/show-and-tell. Daily photo game: you see a secret word, show it in photos, and your AI guesses it. This page covers its hosted endpoint (https://playshowandtell.com/mcp).
Is the Show & Tell MCP server safe to use?
Show & Tell scores 32 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 Show & Tell MCP server expose?
Show & Tell exposes 7 tools: start_round, submit_guess, call_foul, use_lifeline, get_status, and 2 more. Their descriptions and schemas cost roughly 2,651 tokens of context every time the server is loaded.
Does the Show & Tell MCP server require authentication?
Yes. Show & Tell asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Show & Tell MCP server still maintained?
Show & Tell 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.