MCP server for interacting with your LINE Official Account
Nothing to run from here
Dialyne is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
12
tools declared
remote
at its publisher
—
calls last 7d
What it does
Real phone calls in France for AI agents: dial +33 numbers, menus, hold, AI disclosure.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http dialyne-mcp https://mcp.dialyne.com/mcp
# 2 — ask your agent for something these tools do
# place_phone_call, get_call, answer_call_question and 9 more
Dialyne costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DIAll 1 server
dialyne1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http dialyne-mcp https://mcp.dialyne.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Place a real outbound phone call to a number in France (+33) and get back a written result: a voice agent carries out the task you describe (book a table, move an appointment, ask a business a question, follow up on an order or a claim). Compliance: the service's rules require the voice agent to disclose it is an AI assistant at the start of every call (EU AI Act art. 50), and calls are placed onl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| phone_number | string | yes | Number to call, French only. Copy it exactly as the user or the source wrote it: national format '01 42 00 00 00' is accepted and converted for you, so do not rewrite it yourself; E.164 '+33' followed |
| task | string | yes | What the call must achieve, in plain English or French (10-2000 characters): the goal, on whose behalf (the user's name), the facts the callee may ask for (dates, booking or customer references) and t |
| language | no | Language spoken on the call: 'fr' (French), 'en' (English) or 'auto' (starts in French, switches to English if the callee speaks English). Omit to use the account default (usually French). | |
| scheduled_at | no | When to PLACE the call (not the time of the booking or appointment: that goes in task). Omit to call now, the normal case. Only for a call the user wants placed later, e.g. 'call the vet tomorrow at 1 | |
| voice | no | Optional voice: '1' Solène (female, calm), '2' Gaspard (male, warm), '3' Coralie (female, lively), '4' Marius (male, deep), '5' Bella (female, premium, most expressive). Omit to use the account defaul | |
| voice_settings | no | Optional tuning, only if the user asks for it (omit otherwise: the account settings, already optimal, apply). Basic: address_form 'vous' (default) or 'tu'; expressiveness 'natural' (default) or 'plain | |
| idempotency_key | no | Optional unique key (letters, digits, '-', '_', '.', ':'; max 64) for this call request. Retrying with the same key within 24 h returns the original call instead of placing a second one. | |
| ai_disclosure | string | no | 'standard' (default, recommended): the voice agent says it is an AI assistant in its opening line. 'callee_already_informed': leave that mention out of the opening line. Before using it, explain to th |
| callee_informed_confirmation | no | Required with ai_disclosure='callee_already_informed' (10-300 characters): the user's confirmation, in their words, of who the callee is and how they know an AI will call (e.g. 'My sister Lea, I told | |
| outside_hours | no | Obsolete, accepted and ignored: no calling-hours window is imposed any more. Omit it. |
Get the status and written result of a call placed with place_phone_call (outcome, summary, pending question, transcript on request), optionally waiting for news. Compliance: read-only; transcripts are text only (no audio is recorded) and are kept 90 days at most. Use it to follow a call in progress (repeat until done=true), to see whether the voice agent is waiting for the user's answer (pen
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | string | yes | The call_id returned by place_phone_call or list_calls (e.g. 'mis_…'). |
| wait_seconds | integer | no | Seconds (0-50) to wait for news before returning: returns early when the callee answers, the call goes on hold, the voice agent asks a question, a transfer progresses or the call ends. Use 20-30 while |
| after_event_id | integer | no | Return only events after this id: pass last_event_id from the previous get_call response. 0 = from the start. |
| response_format | string | no | 'concise' (default): status, outcome, summary, pending question and key events. 'detailed': also every transcript line, talk and hold durations, attempts and scheduled time. |
Send the user's answer to a question the voice agent asked during a live call (shown by get_call as pending_question) and get confirmation that it was relayed. Compliance: the same rules as the task apply; an answer that threatens, impersonates someone, asks the callee for codes, card details or a transfer, or dictates a payment code or a full card with its security code is refused before anything
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | string | yes | The call_id of the live call (or of an ended call awaiting its callback with a pending_question). |
| answer | string | yes | The user's answer, as the voice agent should relay it to the callee (1-1000 characters), e.g. 'Indoors, please', 'The booking reference is AB-123-CD' or 'The code is [secret: 482913]'. |
| question_id | no | pending_question.question_id from get_call. Omit to answer the question currently pending. |
Transfer a live call to the user's own phone so they can talk to the callee themselves, and get the transfer request confirmed. Compliance: the voice agent tells the callee it is handing over to the person it calls for; recommended whenever a payment or sensitive data is needed. The voice agent tells the callee it is passing the call over, rings user_phone_number, connects both sides without
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | string | yes | The call_id of the live call to hand over. |
| user_phone_number | string | yes | The user's own phone number to ring, French only (+33…, mobile 06/07 accepted), e.g. +33612345678. |
Schedule a new attempt of a finished call (same number, same task) at the time the user chose and get the scheduled time back, for instance when the callee said 'call back tomorrow after 3 pm'. Compliance: only on the user's request; limited to 3 callbacks within 14 days, at the exact time the user chose (no calling-hours window); turned off on lines where every call needs a new request from the u
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | string | yes | The call_id of a finished call (status completed). |
| callback_at | string | yes | When to call again, ISO 8601, e.g. 2026-11-04T15:00:00+01:00 (without a time zone, Europe/Paris is assumed). |
Cancel a call that is scheduled or in progress (including a scheduled callback or automatic retry) and get the cancelled status back. Compliance: stops any further attempt to that number for this call; nothing is charged beyond the time already spoken. A live call is hung up immediately; only the time already spoken is paid and the reserved credit is released. A scheduled call will not be pla
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | string | yes | The call_id of the scheduled or live call to cancel. |
List this account's calls, newest first, and get for each one its call_id, phone number, status, outcome, task and one-line summary. Compliance: read-only, limited to this account's own calls; transcripts older than 90 days are deleted. Use it to find a call_id, to check whether a number was already called recently before placing a new call, or to answer questions such as 'what happened with
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Optional text searched in the task, the summary, the transcript and the phone number (e.g. 'garage', '0561'). Empty = all calls. |
| outcome | no | Optional filter on the call outcome. | |
| limit | integer | no | Maximum number of calls returned (1-50). |
Read the remaining call time on this account and get the minutes of conversation left on the prepaid credit (subscription minutes included, with their expiry date) and the account limits (simultaneous calls, calls per day). Compliance: read-only; no payment can be made from here (only the account owner adds credit, in the web app). Use it before a long call (e.g. one with a long hold) or afte
No parameter schema on file.
Get one more minute to answer the voice agent's pending question: the request is passed to the voice agent, which asks the callee. Compliance: the extension happens ONLY if the callee agrees; the voice agent asks them politely and never makes anyone wait more than 2 minutes in total for one question. Use it as soon as get_call shows a pending_question you cannot answer yourself (you need to a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| call_id | string | yes | The call_id of the live call whose voice agent is waiting for an answer. |
| question_id | no | pending_question.question_id from get_call. Omit for the question currently pending. |
Place the same call to a list of numbers in France (Pro and Enterprise plans) and get back a batch_id with one call_id per number. Compliance: the AI disclosure is always made; marketing, prospecting, surveys and mass calling of people who did not expect it are unlawful and refused; anti-harassment limits per number apply. Use it when the user explicitly asks to make the same kind of call to
| Parameter | Type | Required | Notes |
|---|---|---|---|
| phone_numbers | array | yes | Numbers to call, French only, copied as given ('01 42 00 00 00' or +33…); 100 at most. Duplicates and invalid numbers are skipped and listed in refused. Every number must come from the user. |
| task | string | yes | The same task for every call, as in place_phone_call (goal, on whose behalf, facts, limits). Never marketing or prospecting. |
| name | no | Optional batch name, e.g. 'Tuesday appointment confirmations'. | |
| language | no | Language of the calls; omit for the account default. | |
| voice | no | Optional voice; omit for the account default. | |
| scheduled_at | no | When to start (ISO 8601 with time zone). Omit to start now. |
Get the progress and results of a batch of calls: counts by status, successes, refused numbers and, for each call, its call_id, status, outcome and summary. Compliance: read-only, limited to this account's own batches. Use it after place_batch_calls to report results to the user. Read-only. For one call's transcript, use get_call with response_format='detailed'. To stop a single call, use can
| Parameter | Type | Required | Notes |
|---|---|---|---|
| batch_id | string | yes | The batch_id returned by place_batch_calls (e.g. 'lot_…'). |
Read or change how the voice agent introduces itself on the user's calls: name, tone, opening line, answer to "who is calling?", introduction and the AI mention in the opening. Compliance: the recommended settings (default) say "Hello, this is Léa, <user>'s virtual assistant. I'm calling about…" and answer yes when asked if it is an AI (EU AI Act art. 50); the agent never denies being an AI, whate
| Parameter | Type | Required | Notes |
|---|---|---|---|
| first_name | no | Name the voice agent gives (e.g. 'Lea'). Omit to keep the current one. Stays within the recommended settings. | |
| tone | no | Tone of voice: 'warm' (recommended), 'neutral', 'formal' or 'upbeat'. Stays within the recommended settings. | |
| opening_line | no | Custom opening line, spoken word for word when the callee answers, before the purpose of the call; may use {prenom} (agent name) and {operateur} (user's announced name). Write it in the language of th | |
| who_is_calling_answer | no | Custom answer when the callee asks who the agent is calling for. Empty string = recommended. DEVIATION. | |
| introduction | no | Custom answer when the callee asks who the agent is. Empty string = recommended. DEVIATION. | |
| ai_mention_in_opening | no | true (recommended): the opening line says the agent is a virtual assistant. false = DEVIATION. Either way the agent says yes if asked whether it is an AI. | |
| reset_to_recommended | boolean | no | true: drop every deviation (keeps first_name and tone). |
| accept_responsibility | boolean | no | Set true ONLY after you showed the user the warning text returned by this tool and the user explicitly accepted it in their own words. Never set it on your own initiative. |
| warning_version | no | The warning.version the user accepted (from a previous call of this tool). |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Dialyne or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 8 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest58fb0b2ab67402ef56186a6d5c500910c9ec41852a11bf73dfa4dca47a2400b4
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| place_phone_call | untrusted-inputexternal-sink | untrusted-input: keyword "web_search"; external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_call | no tags | |
| answer_call_question | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| transfer_call_to_user | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| schedule_callback | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| cancel_call | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_calls | no tags | |
| get_account_balance | no tags | |
| hold_call_question | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| place_batch_calls | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_batch_calls | no tags | |
| configure_agent_identity | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest58fb0b2ab67402ef
Scanned2026-11-08
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Dialyne can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.