Call Me
REMOTE · SERDAROZTETIK.COM
Your AI rings your iPhone, speaks its question, and gets your spoken answer back as text.
Available components
Last scanned (12 hours ago)
Scores higher than 65% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Communication
Recent critical change
Authorization (12 Aug 2026). See the changelog before you install this server.
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 (call). 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 Usability60
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3267 tokens (~363/item across 9 items; 9 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
- Structured output schemas are declared (100% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
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 →
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.
- 14 Nov 26 0
- “call” reworded the description of “keep_open” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 11 Nov 26 +1
- Stability: 0.97 → pass security
- 10 Nov 26 −1
- Stability: pass → 0.97 functional
- 8 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “call” rewrote its description, which is the text the model reads security
- Tool “say” rewrote its description, which is the text the model reads security
- Schema quality: 304 → 362 ▼ functional
- “call” added an optional parameter “voice” cosmetic
- “play_audio” added an optional parameter “voice” cosmetic
- “say” added an optional parameter “voice” cosmetic
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 5 Nov 26 +4
- Stability: 0.97 → pass security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “call” rewrote its description, which is the text the model reads security
- Tool “hang_up” rewrote its description, which is the text the model reads security
- Tool “poll_result” rewrote its description, which is the text the model reads security
- Tool “say” rewrote its description, which is the text the model reads security
- Tool “setup” rewrote its description, which is the text the model reads security
- Tool “text” rewrote its description, which is the text the model reads security
- Schema quality: 258 → 304 ▼ functional
- Tool coverage: 0% → 100% ▲ functional
- Tool “call” now declares an output schema ▲ functional
- Tool “hang_up” now declares an output schema ▲ functional
- Tool “play_audio” now declares an output schema ▲ functional
- Tool “poll_result” now declares an output schema ▲ functional
- Tool “say” now declares an output schema ▲ functional
- Tool “set_thread_title” now declares an output schema ▲ functional
- Tool “setup” now declares an output schema ▲ functional
- Tool “text” now declares an output schema ▲ functional
- Tool “wait_for_reply” now declares an output schema ▲ functional
- First check of Tool coverage: 100 functional
- Schema quality: good → excellent functional
- “text” reworded the description of “to” cosmetic
- “call” reworded the description of “from_label” cosmetic
- “call” reworded the description of “keep_open” cosmetic
- “call” reworded the description of “language” cosmetic
- “call” reworded the description of “question” cosmetic
- “call” reworded the description of “session_token” cosmetic
- “call” reworded the description of “to” cosmetic
- “hang_up” reworded the description of “call_id” cosmetic
- “hang_up” reworded the description of “goodbye” cosmetic
- “hang_up” reworded the description of “session_token” cosmetic
- “play_audio” reworded the description of “from_label” cosmetic
- “play_audio” reworded the description of “intro” cosmetic
- “play_audio” reworded the description of “language” cosmetic
- “play_audio” reworded the description of “session_token” cosmetic
- “play_audio” reworded the description of “source” cosmetic
- “play_audio” reworded the description of “title” cosmetic
- “play_audio” reworded the description of “to” cosmetic
- “poll_result” reworded the description of “call_id” cosmetic
- “poll_result” reworded the description of “session_token” cosmetic
- “say” reworded the description of “call_id” cosmetic
- “say” reworded the description of “language” cosmetic
- “say” reworded the description of “session_token” cosmetic
- “say” reworded the description of “text” cosmetic
- “set_thread_title” reworded the description of “session_token” cosmetic
- “set_thread_title” reworded the description of “title” cosmetic
- “text” reworded the description of “body” cosmetic
- “text” reworded the description of “from_label” cosmetic
- “text” reworded the description of “session_token” cosmetic
- “wait_for_reply” reworded the description of “cursor” cosmetic
- “wait_for_reply” reworded the description of “session_token” cosmetic
- “wait_for_reply” reworded the description of “wait_s” cosmetic
- 4 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- New tool “play_audio”, which the server declares destructive security
- Schema quality: 1891 → 2327 ▼ functional
- Stability: pass → 0.97 functional
- 30 Oct 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “call” rewrote its description, which is the text the model reads security
- Tool “setup” rewrote its description, which is the text the model reads security
- Tool “text” rewrote its description, which is the text the model reads security
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://serdaroztetik.com/aiphone/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=serdaroztetik.com | CN=YE1,O=Let's Encrypt,C=US | 2 Nov 2026 | 31 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 6f0fdd0491c3dbdd97da31f46dbcbdfabbf |
| SANs: serdaroztetik.com, www.serdaroztetik.com | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| 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 serdaroztetik.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| serdaroztetik.com. | 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://serdaroztetik.com/aiphone/mcp | Verified | 200 | |
| http (plaintext) | http://serdaroztetik.com/aiphone/mcp | HTTPS enforced | 301 | https://serdaroztetik.com/aiphone/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 →
call Call the human ~756
Ring the human's phone (iPhone or Android), read `question` aloud word for word, and return what they say back as text. Waits up to ~30s. status "completed" carries their words in `transcript` (empty if they only listened). "ringing" (not picked up yet) or "in_call" (listening) means the call has not settled: pass call_id to poll_result until it does. An unanswered ring settles as "missed" within about a minute; "declined" means they refused it. Do not retry an unanswered call in a loop: send one `text` instead. By default the line stays open after their answer ("open": true): they hear a soft hold sound while you think, and a voice assistant tells them you are working on it. Reply with `say`, finish with `hang_up`; after about two minutes of silence the line drops by itself. Anything they said while waiting comes back with their next answer as "said_while_waiting". The "language" and "language_name" fields report what the recognizer heard, as information only. `voice` picks who speaks (female first: bella, sarah, jessica, ...; male: roger, eric, brian, ...) and sticks for later calls. Reuse the returned session_token in later calls and texts so the phone keeps one thread. The `from` in the result is your own number: never call or text it. Missing `to` returns setup_required with download links.
| Name | Type | Req | Description |
|---|---|---|---|
| from_label | string | – | Who is calling, shown on their phone and spoken: e.g. "Claude on my laptop". |
| keep_open | – | – | The line always stays up after their answer so you can reply with `say`; end it with `hang_up`. Kept for older clients: false no longer makes a one-shot call. |
| language | string | – | The language you are speaking, e.g. "tr", "pt-BR" or "Turkish". The call's own short lines (thanks, goodbye) follow it. Empty means English, or on `say` keeps the current one. |
| question | string | yes | What to say, read aloud word for word, up to 2000 characters (about two minutes). It need not be a question: a status update or a summary works too. |
| session_token | – | – | A session_token from an earlier result, to stay in that thread. Omit on first contact. |
| to | – | – | The human's 10-digit Call Me number, from My Number in the app (not a regular phone number). Local clients read it from ~/.aiphone/config.json user_number. In a host without file access, reuse a numb… |
| voice | string | – | Who speaks, female first (default "bella"). female: bella, sarah, jessica, matilda, laura, alice (british), lily (british); neutral: river; male: roger, eric, chris, brian, will, liam, bill, george (… |
| Name | Type | Req | Description |
|---|---|---|---|
| audio_error | – | – | play_audio: why the recording could not be played. |
| audio_id | – | – | play_audio: the recording that was offered. |
| call_id | – | – | Pass to poll_result, say and hang_up. |
| duration_s | – | – | play_audio: its length in seconds. |
| finished | – | – | play_audio: whether they heard it to the end. |
| from | – | – | Your own agent number. Never call or text it. |
| language | – | – | Language code the recognizer heard, information only. |
| language_name | – | – | That language's name. |
| listened | – | – | play_audio: whether they chose to listen. |
| listened_s | – | – | play_audio: seconds they listened. |
| next | – | – | What to do next when the call has not settled. |
| open | – | – | True while the line stays up for say or hang_up. |
| said_while_waiting | – | – | What they said while you were thinking. |
| session_token | – | – | Reuse in later calls and texts to stay in one thread. |
| status | string | yes | "completed" (answered), "ringing" or "in_call" (not settled: poll_result), "missed", "declined", "ended", "hanging_up", "playing" (play_audio), or "setup_required" when no number was given. |
| title | – | – | play_audio: the recording's title. |
| transcript | – | – | What the human said; empty if they only listened. |
| turn | – | – | Index of the answer within a conversation. |
No examples provided.
hang_up Hang up ~126
End a call you placed. In an open conversation `goodbye` is spoken first; leave it empty to just hang up. A call that already ended reports its final status.
| Name | Type | Req | Description |
|---|---|---|---|
| call_id | integer | yes | The call_id from the call or play_audio result. |
| goodbye | string | – | Spoken before the line drops in an open conversation, e.g. "Thanks, I'll get on it." Empty just hangs up. |
| session_token | string | yes | The session_token from an earlier result. It keeps every call and text in one thread on their phone. |
| Name | Type | Req | Description |
|---|---|---|---|
| call_id | – | – | The call that was ended. |
| open | – | – | Always false: the line is down. |
| session_token | – | – | This session's token. |
| status | string | yes | "ended", or "hanging_up" while the goodbye is spoken. |
No examples provided.
play_audio Play long audio ~694
Bigger and longer audio goes here. Calls the human and plays a recording to them as a phone call: a podcast, a long narration you rendered, a voice memo, music. `source` is a link (YouTube, SoundCloud, a podcast page, or a direct .mp3/.m4a/.wav/.ogg/.flac/... link) or the audio_id of a file uploaded with `curl --data-binary @file.m4a "https://callmemcp.com/audio?to=<number>&filename=file.m4a"` (up to 300 MB / 3 hours, kept for a day). The voice says your `intro`, the title and the length, then asks if they want to listen now; on a yes the file plays as plain sound (no voice model) until it ends or they hang up. Returns once they answer the offer: status "playing" (they said yes), "completed" with listened:false (no, or nothing), or missed/declined. poll_result later reports listened_s and finished. Use `call` for text under ~2000 characters. `language` ("tr", "de") is the language of your intro; the offer and the call's own lines follow it.
| Name | Type | Req | Description |
|---|---|---|---|
| from_label | string | – | Who is calling, shown on their phone and spoken: e.g. "Claude on my laptop". |
| intro | string | – | Spoken before the offer, up to 500 characters: what this is and why they might want it. |
| language | string | – | The language you are speaking, e.g. "tr", "pt-BR" or "Turkish". The call's own short lines (thanks, goodbye) follow it. Empty means English, or on `say` keeps the current one. |
| session_token | – | – | A session_token from an earlier result, to stay in that thread. Omit on first contact. |
| source | string | yes | A link (YouTube, SoundCloud, a podcast page, or a direct .mp3/.m4a/.wav/.ogg/.flac link) or the audio_id of an uploaded file. |
| title | string | – | The recording's title. Empty uses the title read from the link. |
| to | – | – | The human's 10-digit Call Me number, from My Number in the app (not a regular phone number). Local clients read it from ~/.aiphone/config.json user_number. In a host without file access, reuse a numb… |
| voice | string | – | Who speaks, female first (default "bella"). female: bella, sarah, jessica, matilda, laura, alice (british), lily (british); neutral: river; male: roger, eric, chris, brian, will, liam, bill, george (… |
| Name | Type | Req | Description |
|---|---|---|---|
| audio_error | – | – | play_audio: why the recording could not be played. |
| audio_id | – | – | play_audio: the recording that was offered. |
| call_id | – | – | Pass to poll_result, say and hang_up. |
| duration_s | – | – | play_audio: its length in seconds. |
| finished | – | – | play_audio: whether they heard it to the end. |
| from | – | – | Your own agent number. Never call or text it. |
| language | – | – | Language code the recognizer heard, information only. |
| language_name | – | – | That language's name. |
| listened | – | – | play_audio: whether they chose to listen. |
| listened_s | – | – | play_audio: seconds they listened. |
| next | – | – | What to do next when the call has not settled. |
| open | – | – | True while the line stays up for say or hang_up. |
| said_while_waiting | – | – | What they said while you were thinking. |
| session_token | – | – | Reuse in later calls and texts to stay in one thread. |
| status | string | yes | "completed" (answered), "ringing" or "in_call" (not settled: poll_result), "missed", "declined", "ended", "hanging_up", "playing" (play_audio), or "setup_required" when no number was given. |
| title | – | – | play_audio: the recording's title. |
| transcript | – | – | What the human said; empty if they only listened. |
| turn | – | – | Index of the answer within a conversation. |
No examples provided.
poll_result Get call result ~148
Check on a call that came back "ringing", "in_call" or "playing". Waits up to ~25s for it to settle, then returns the same shape as `call`: the final status and transcript once they answer, decline, or the ring times out ("missed", within about a minute). Still not settled: call it again. For play_audio calls it reports listened_s and finished. Rings nothing.
| Name | Type | Req | Description |
|---|---|---|---|
| call_id | integer | yes | The call_id from the call or play_audio result. |
| session_token | string | yes | The session_token from an earlier result. It keeps every call and text in one thread on their phone. |
| Name | Type | Req | Description |
|---|---|---|---|
| audio_error | – | – | play_audio: why the recording could not be played. |
| audio_id | – | – | play_audio: the recording that was offered. |
| call_id | – | – | Pass to poll_result, say and hang_up. |
| duration_s | – | – | play_audio: its length in seconds. |
| finished | – | – | play_audio: whether they heard it to the end. |
| from | – | – | Your own agent number. Never call or text it. |
| language | – | – | Language code the recognizer heard, information only. |
| language_name | – | – | That language's name. |
| listened | – | – | play_audio: whether they chose to listen. |
| listened_s | – | – | play_audio: seconds they listened. |
| next | – | – | What to do next when the call has not settled. |
| open | – | – | True while the line stays up for say or hang_up. |
| said_while_waiting | – | – | What they said while you were thinking. |
| session_token | – | – | Reuse in later calls and texts to stay in one thread. |
| status | string | yes | "completed" (answered), "ringing" or "in_call" (not settled: poll_result), "missed", "declined", "ended", "hanging_up", "playing" (play_audio), or "setup_required" when no number was given. |
| title | – | – | play_audio: the recording's title. |
| transcript | – | – | What the human said; empty if they only listened. |
| turn | – | – | Index of the answer within a conversation. |
No examples provided.
say Say the next line ~435
In a call whose result came back "open": true, speak `text` to the human and return what they answer, in the same shape as `call`. Only after their previous answer is in. Waits up to ~30s; on "in_call", follow up with poll_result. "open": false means the call has ended. Pass `language` only to switch the language of the call's own lines; empty keeps it. `voice` switches who speaks from this line on (female first: bella, sarah, ...; male: roger, eric, ...); empty keeps it. Anything they said while you were thinking comes back as "said_while_waiting". End the call with `hang_up` once you are done.
| Name | Type | Req | Description |
|---|---|---|---|
| call_id | integer | yes | The call_id from the call or play_audio result. |
| language | string | – | The language you are speaking, e.g. "tr", "pt-BR" or "Turkish". The call's own short lines (thanks, goodbye) follow it. Empty means English, or on `say` keeps the current one. |
| session_token | string | yes | The session_token from an earlier result. It keeps every call and text in one thread on their phone. |
| text | string | yes | Your next line, read aloud word for word. Keep it short and conversational; up to 2000 characters. |
| voice | string | – | Who speaks, female first (default "bella"). female: bella, sarah, jessica, matilda, laura, alice (british), lily (british); neutral: river; male: roger, eric, chris, brian, will, liam, bill, george (… |
| Name | Type | Req | Description |
|---|---|---|---|
| audio_error | – | – | play_audio: why the recording could not be played. |
| audio_id | – | – | play_audio: the recording that was offered. |
| call_id | – | – | Pass to poll_result, say and hang_up. |
| duration_s | – | – | play_audio: its length in seconds. |
| finished | – | – | play_audio: whether they heard it to the end. |
| from | – | – | Your own agent number. Never call or text it. |
| language | – | – | Language code the recognizer heard, information only. |
| language_name | – | – | That language's name. |
| listened | – | – | play_audio: whether they chose to listen. |
| listened_s | – | – | play_audio: seconds they listened. |
| next | – | – | What to do next when the call has not settled. |
| open | – | – | True while the line stays up for say or hang_up. |
| said_while_waiting | – | – | What they said while you were thinking. |
| session_token | – | – | Reuse in later calls and texts to stay in one thread. |
| status | string | yes | "completed" (answered), "ringing" or "in_call" (not settled: poll_result), "missed", "declined", "ended", "hanging_up", "playing" (play_audio), or "setup_required" when no number was given. |
| title | – | – | play_audio: the recording's title. |
| transcript | – | – | What the human said; empty if they only listened. |
| turn | – | – | Index of the answer within a conversation. |
No examples provided.
set_thread_title Set thread title ~99
Name this session's conversation thread on the human's phone (e.g. the project or task you are working on). Shown as the thread title in the app.
| Name | Type | Req | Description |
|---|---|---|---|
| session_token | string | yes | The session_token from an earlier result. It keeps every call and text in one thread on their phone. |
| title | string | yes | A short name, 3 to 5 words, e.g. "Deploy of billing API". |
| Name | Type | Req | Description |
|---|---|---|---|
| label | string | yes | The title as it now shows on the phone. |
| ok | boolean | yes | True when the title was saved. |
No examples provided.
setup Set up Call Me ~78
Return first-setup instructions and clickable App Store and Google Play download links, for when you do not have the human's Call Me number yet. Show both links to the human as clickable links, then ask them to open My Number in the app and give you its 10 digits. Nothing is sent and nothing rings.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| app_store_url | string | yes | Call Me on the App Store, for iPhone. |
| local_config_key | – | – | The key that holds it in that file. |
| local_config_path | – | – | Where a local client keeps the number. |
| message | string | yes | What to tell the human, with both download links. |
| play_store_url | string | yes | Call Me on Google Play, for Android. |
| status | string | yes | "setup_required": no Call Me number is known yet. |
| storage | – | – | How the number is stored. |
No examples provided.
text Text the human ~269
Send a one-way text to the human's phone (a push notification, no ring). Use it for updates that need no answer, or as the fallback when a call comes back "missed" or "declined". delivered:false means it was saved to their history but no notification showed; `notice` says why. Their replies arrive through wait_for_reply. Missing `to` returns setup_required with the download links. Pass a previous session_token to stay in the same thread.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | The message, up to 2000 characters. Markdown links render as links. |
| from_label | string | – | Who is calling, shown on their phone and spoken: e.g. "Claude on my laptop". |
| session_token | – | – | A session_token from an earlier result, to stay in that thread. Omit on first contact. |
| to | – | – | The human's 10-digit Call Me number, from My Number in the app (not a regular phone number). Local clients read it from ~/.aiphone/config.json user_number. In a host without file access, reuse a numb… |
| Name | Type | Req | Description |
|---|---|---|---|
| delivered | – | – | True when a notification was shown on the phone. |
| from | – | – | Your own agent number. Never call or text it. |
| message_id | – | – | The stored message. |
| note | – | – | Extra information, e.g. from the demo line. |
| notice | – | – | Why the text was saved but not shown, when delivered is false. |
| ok | – | – | True when the message was stored. |
| session_token | – | – | Reuse in later calls and texts to stay in one thread. |
| status | – | – | "setup_required" when no number was given. |
No examples provided.
wait_for_reply Wait for a text reply ~153
Wait for the human to send something back to this session — texts and voicemail transcripts arrive here. Long-polls up to wait_s (max 30s); returns {events, cursor}. Pass the returned cursor next time to only see new events. An empty events list just means nothing yet — poll again if you are still waiting.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | integer | – | The cursor from the previous result; 0 the first time. |
| session_token | string | yes | The session_token from an earlier result. It keeps every call and text in one thread on their phone. |
| wait_s | integer | – | How long to wait for something to arrive, 0 to 30 seconds. |
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | integer | yes | Pass back as cursor next time to see only newer events. |
| events | array | yes | New events since the cursor; empty means nothing yet. |
No examples provided.
How do I install the Call Me MCP server?
Call Me is a hosted endpoint at https://serdaroztetik.com/aiphone/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 · serdaroztetik.com
claude mcp add --transport http com-serdaroztetik-call-me 'https://serdaroztetik.com/aiphone/mcp'
What is the Call Me MCP server?
Call Me is an MCP server listed in the public MCP registry as com.serdaroztetik/call-me. Your AI rings your iPhone, speaks its question, and gets your spoken answer back as text. This page covers its hosted endpoint (https://serdaroztetik.com/aiphone/mcp).
Is the Call Me MCP server safe to use?
Call Me scores 76 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 Call Me MCP server expose?
Call Me exposes 9 tools: setup, call, poll_result, play_audio, say, and 4 more. Their descriptions and schemas cost roughly 2,758 tokens of context every time the server is loaded.
Does the Call Me MCP server require authentication?
No. We connected to Call Me without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Call Me MCP server still maintained?
Call Me 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 Call Me MCP server?
VerifyMCP ran 13 checks on Call Me, 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.