Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@medicover-mcp search for available slots for my child in Warsaw pediatrics tomorrow"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that lets an AI agent manage appointments on
Medicover's Polish patient portal (https://online24.medicover.pl/). It talks directly to the
portal's private JSON API (reverse-engineered from real traffic — see
NOTES.md); it does not drive a browser at runtime.
It is built for an unattended daily routine: hunt for scarce slots and optionally rebook an existing appointment to an earlier one — including for linked dependents (e.g. children).
Tool | Purpose |
| The account holder + linked dependents, each with a stable |
| A patient's planned/past appointments (read-only). |
| Available slots by region + specialty (optionally doctor/clinic/language, date range, and slot-search type e.g. |
| Book a slot for a patient — |
| Move an appointment to another slot; "earlier-only" by default. |
| Resolve specialty/doctor/clinic/region names → IDs from history. |
| Clinics/doctors/languages bookable for a region + specialty. |
Patient-scoped read tools default to the account holder; the write tools require an
explicit patient_id so a booking can never land on the wrong person. Nothing else (messaging,
records, prescriptions, payments, cancel-without-rebook) is exposed.
Related MCP server: dental-calendar-mcp
Login uses SMS 2FA, which can't be in an unattended hot path, so:
One-time bootstrap (interactive CLI, not a tool):
export MEDICOVER_USERNAME=<your-MRN-or-login>
export MEDICOVER_PASSWORD=<your-password> # or omit to be prompted
uv run medicover-auth login # prompts for the SMS codeThis completes OAuth + 2FA and saves the refresh token to a 0600 file (default
~/.config/medicover-mcp/credentials.json; override with MEDICOVER_STORE_PATH).
Username/password are never stored.
Unattended runtime: the MCP server loads the refresh token and silently refreshes the short-lived (~3 min) access token on every run. No password or SMS is ever needed during tool calls.
On expiry/revocation: tools fail with session expired — run medicover-auth login;
they never prompt for an SMS through a tool call.
Token-lifetime decision: the in-MCP
request_sms_code/submit_sms_codefallback is not shipped — see the reasoning inNOTES.md.
Helpers: uv run medicover-auth status (shows whether creds exist, no secrets) and
uv run medicover-auth logout (deletes them).
uv sync # create the venv and install
uv run medicover-auth login
uv run pytest # run the tests (no network — HTTP is mocked)Add to your MCP client (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"medicover": {
"command": "uv",
"args": ["--directory", "/abs/path/to/medicover", "run", "medicover-mcp"],
"env": {
"MEDICOVER_STORE_PATH": "/home/you/.config/medicover-mcp/credentials.json"
}
}
}
}(Run medicover-auth login once on the same machine first so the credential store exists.)
Var | Used by | Meaning |
| bootstrap only | Login credentials (else prompted). |
| bootstrap + server | Credential file path (default |
| server | HTTP timeout seconds (default 30). |
list_patients → find the child's patient_id.
list_appointments(patient_id=child, state="Planned") → note the appointment to improve and its appointment_id/date.
list_appointment_filters(patient_id=child) → get the region id and specialty id.
search_slots(patient_id=child, region_ids=[...], specialty_ids=[...], start_date="today").
If an earlier slot exists: reschedule_appointment(patient_id=child, appointment_id=..., booking_string=<slot>, new_slot_date=<slot date>) (refuses unless strictly earlier).
Read-before-write on booking/reschedule (the portal validates the slot at action time); reschedule never cancels without rebooking and defaults to earlier-only; polite request pacing with backoff; tokens/credentials are never logged or returned; request/response bodies (which carry medical data) are not logged.
Unofficial, built against an undocumented private API that may change without notice. Use with your own account and within Medicover's terms. Not affiliated with Medicover.
Book an available slot for a specific patient.
patient_id is mandatory so a booking can never land on the wrong person's record. The
portal validates the slot at booking time (read-before-write); if the slot is gone you get
a clear error and nothing is booked. Returns the new appointment id on success.
Note: reporting_id defaults to empty. It's unverified whether the API requires it (the
captured bookings carried one from the out-of-scope triage flow); if booking fails citing
it, that's the likely cause.
| Name | Required | Description | Default |
|---|---|---|---|
| patient_id | Yes | MRN of the patient to book for. REQUIRED — never guessed. | |
| reporting_id | No | Reporting/correlation token. Whether the portal requires it is unverified (see NOTES.md); the in-scope search flow has no source for one, so leave empty unless you captured a value. | |
| booking_string | Yes | The `booking_string` of the slot to book (from search_slots). |
| Name | Required | Description |
|---|---|---|
| booked | Yes | |
| clinic | No | |
| doctor | No | |
| message | No | |
| slot_date | No | |
| appointment_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description fully covers behavior: read-before-write validation, error handling if slot is gone, return of appointment id, and the uncertainty of reporting_id. Comprehensive for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with clear sections for purpose, parameter details, and behavior. A bit verbose but every sentence adds value. Could be slightly trimmed without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists (so return values are documented elsewhere), the description provides necessary operational details: slot validation, error behavior, and a practical note on reporting_id. Covers all essential aspects for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds significant value: explains why patient_id is required, and gives practical caveat about reporting_id (unverified requirement, leave empty). Goes beyond schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool books an available slot for a specific patient, with a specific verb and resource. Distinguishes from siblings like reschedule_appointment and search_slots by the unique action of booking.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context: patient_id is mandatory, slot validation occurs at booking time, and a caveat about reporting_id. Does not explicitly state when not to use, but the context is sufficient for an agent to decide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve names → IDs from a patient's own visit history.
Returns the specialties, doctors, clinics and regions seen in this patient's appointments, each as {id, name}. Use this to discover the opaque IDs that search_slots needs (e.g. the region id and a specialty id), then narrow further with list_search_filters. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| patient_id | No | MRN; defaults to the account holder. |
| Name | Required | Description |
|---|---|---|
| clinics | No | |
| doctors | No | |
| regions | No | |
| languages | No | |
| specialties | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It states 'Read-only' and describes the output (each as {id, name}), adding value beyond the schema. However, it doesn't disclose potential errors or permission requirements, so a slight deduction is warranted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with three sentences that front-load the core purpose, then detail the output and usage. Every sentence adds value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional parameter, output schema exists), the description fully covers purpose, usage, and relation to siblings. It is complete without needing to describe return values since an output schema is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers the single parameter (patient_id) with a description ('MRN; defaults to the account holder'), resulting in 100% coverage. The description adds context about the patient's own visit history but does not enhance parameter semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool resolves names to IDs from a patient's visit history, explicitly listing the returned resource types (specialties, doctors, clinics, regions) and their format. It also distinguishes itself from the sibling tool list_search_filters by noting that the latter is used for further narrowing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: use this tool to discover opaque IDs needed by search_slots, then narrow further with list_search_filters. It also indicates the tool is read-only, helping the agent decide when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List a patient's appointments (upcoming by default).
Each appointment includes an opaque appointment_id (pass it to reschedule_appointment)
and a can_reschedule flag. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | Which appointments: 'Planned', 'Past', or 'All'. | Planned |
| patient_id | No | MRN of the patient. Defaults to the account holder when omitted. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Declares read-only nature and default date filter, which are key behavioral traits. No annotations exist, so description carries full burden; it does well for a simple list tool but lacks details on authentication or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three succinct sentences covering purpose, output details, and read-only status. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists and complexity is low, description provides necessary context: default upcoming, opaque id, read-only. Lacks pagination/ordering details but still adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. Description adds minimal extra meaning beyond schema (e.g., 'upcoming' maps to default state). No significant new information for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'List' and resource 'appointments' with patient scope and default upcoming behavior. Distinguishes from siblings by focusing on patient's existing appointments and mentioning how appointment_id is used with reschedule_appointment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage for viewing appointments but does not explicitly state when to use this vs book_appointment or search_slots. No exclusion criteria or alternative guidance provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every patient the logged-in account can act on.
Returns the account holder plus any linked dependents (e.g. children). Each entry has a
stable patient_id (MRN) used by all other tools, and is_account_holder marks the
logged-in user. Use these IDs — never names — for the patient-scoped tools.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description discloses important behaviors: it returns account holder and linked dependents, provides stable `patient_id` (MRN), and marks the logged-in user with `is_account_holder`. This goes beyond the empty input schema, though it could mention potential pagination or limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no wasted words. The first sentence states the purpose and scope, the second adds behavioral details and usage guidance. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no annotations, no parameters, and an output schema (assumed adequate), the description is fully complete. It explains what the tool does, what the output contains, and how to use the results. No gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With no parameters, the schema coverage is 100% and the description adds meaning by explaining that no arguments are needed and that the tool lists all patients under the account. The description clarifies the implicit scope, justifying a score above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the action ('list'), resource ('patients'), and scope ('every patient the logged-in account can act on'). It distinguishes this tool from sibling tools focused on appointments and filters by explicitly stating it returns patients available for the account, which is a unique purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear guidance on using the output: 'Use these IDs — never names — for the patient-scoped tools.' This tells the agent how to apply the results. While no explicit 'when not to use' is stated, the lack of alternative patient-listing tools makes this sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the clinics, doctors and languages bookable for a region + specialty selection.
Use this after picking a region and specialty to enumerate valid clinic and doctor IDs before calling search_slots. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| doctor_ids | No | Optional doctor IDs to narrow the result. | |
| patient_id | No | MRN; defaults to the account holder. | |
| region_ids | Yes | Region IDs (e.g. ['204'] = Warszawa). | |
| specialty_ids | Yes | Specialty IDs to search within. | |
| slot_search_type | No | Match the search_slots value: 'Standard' (default) or 'DiagnosticProcedure'. | Standard |
| Name | Required | Description |
|---|---|---|
| clinics | No | |
| doctors | No | |
| regions | No | |
| languages | No | |
| specialties | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description correctly notes 'Read-only.', which is the key behavioral trait. It does not mention side effects, which are expected to be none for a list operation. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states purpose, second gives usage advice and read-only note. Every word earns its place; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the 5 parameters, full schema descriptions, and presence of an output schema, the description covers core purpose, sequencing, and safety. It does not detail return format, but that is handled by the output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema, only referencing 'region + specialty selection'. It does not provide deeper semantics for each parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool lists clinics, doctors, and languages bookable for a region and specialty selection, using specific verb 'List' and clear resource. It distinguishes from sibling tools like 'search_slots' by noting it should be used before that.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear usage context: 'Use this after picking a region and specialty to enumerate valid clinic and doctor IDs before calling search_slots.' It does not explicitly state when not to use, but the guidance is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Move an existing appointment to a different slot (atomic; never cancels without rebooking).
Only moves to the slot you explicitly pass. With require_earlier (default), it first
confirms the new slot is strictly earlier than the current appointment and otherwise
refuses — so an unattended 'earlier slot' routine can't accidentally move an appointment
later. The portal re-validates the slot at reschedule time.
| Name | Required | Description | Default |
|---|---|---|---|
| patient_id | Yes | MRN of the patient. REQUIRED — never guessed. | |
| new_slot_date | Yes | The new slot's datetime (ISO, as shown by search_slots). Used for the earlier-only safety check and to report the move. | |
| appointment_id | Yes | The `appointment_id` of the existing appointment to move. | |
| booking_string | Yes | `booking_string` of the new slot (from search_slots). | |
| require_earlier | No | If true (default), refuse the move unless the new slot is strictly earlier than the current appointment — for the 'find an earlier slot' use case. |
| Name | Required | Description |
|---|---|---|
| status | Yes | |
| message | No | |
| new_date | No | |
| old_date | No | |
| rescheduled | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses atomicity, the earlier-only safety check, and portal re-validation. Lacks details on failure modes, but covers key behaviors without annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences and one paragraph, front-loaded with purpose. Every sentence adds value, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists but not shown, so return values not needed. Description and schema together fully explain behavior and parameters for a 5-param tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline 3. The description adds context for `require_earlier` and `new_slot_date`, explaining their roles in the safety check and reporting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Move an existing appointment to a different slot' with the atomicity qualifier. Distinguishes from siblings like 'book_appointment' and 'search_slots' by specifying rescheduling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides guidance on using `require_earlier` for unattended routines, implying a use case. Does not explicitly compare with siblings, but the context makes it clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find available appointment slots for a specialty/region (optionally doctor/clinic).
Each returned slot carries a booking_string — the single-use handle you pass to
book_appointment or reschedule_appointment, and a visit_type (Center | Phone |
PhoneAdvice). The portal has no visit-type search filter, so to get in-person ("Center")
visits, choose an in-person specialty and/or filter the returned slots by visit_type.
next_search_date hints the StartTime to use to page further into the future. Re-run this
immediately before booking, because a booking_string can expire. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| end_date | No | Optional latest date (YYYY-MM-DD). Slots after this date are dropped client-side (the portal only honours a start date). | |
| clinic_ids | No | Optional clinic IDs. | |
| doctor_ids | No | Optional doctor IDs. | |
| patient_id | No | MRN; defaults to the account holder. | |
| region_ids | Yes | Region IDs (e.g. ['204']). Required. | |
| start_date | Yes | Earliest date to search from, YYYY-MM-DD. | |
| language_ids | No | Optional doctor-language IDs (e.g. 4=Polski, 6=Angielski, 60=Ukraiński; resolve others via list_search_filters). | |
| specialty_ids | Yes | Specialty IDs. Required. | |
| slot_search_type | No | Slot category. 'Standard' (default) for normal consultations; 'DiagnosticProcedure' for diagnostic procedures. | Standard |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| slots | Yes | |
| next_search_date | No | Hint for the next StartTime when paging forward in time. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses that the tool is 'Read-only', that booking_string is single-use and can expire, that end_date is ignored server-side (dropped client-side), and that next_search_date hints pagination. This provides sufficient behavioral insight beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured paragraph with no redundant sentences. It front-loads the core purpose and follows with necessary details. Every sentence adds value and earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (9 parameters, output schema exists), the description covers key aspects: main function, optional filters, pagination hint, expiration, and client-side filtering limitations. It does not explain output schema details (which is acceptable) or error handling, but is complete enough for typical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value beyond schema descriptions: it explains the purpose of booking_string (carried in each slot), the need for client-side filtering of visit_type, and the expiration hint. This additional context helps the agent understand how to use parameters effectively.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Find' and the resource 'available appointment slots', with optional filters. It distinguishes from siblings like book_appointment (which uses the booking_string) and list_appointments (which lists existing appointments). The explanation of booking_string and visit_type further clarifies the tool's role.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit usage guidance: 'Re-run this immediately before booking, because a booking_string can expire.' It also advises on filtering visit_type client-side for in-person visits. Although it does not explicitly state when not to use it, the context implies it for finding slots before booking. Alternatives like list_search_filters are mentioned for resolving language IDs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0book_appointmentlist_appointment_filterslist_appointmentslist_patientslist_search_filtersreschedule_appointmentsearch_slotsScored across 7 tools
Each tool targets a distinct action (booking, listing, searching, rescheduling) on different entities (appointments, patients, filters). There is no ambiguity between them.
All tool names follow the consistent verb_noun pattern in snake_case (e.g., book_appointment, list_patients, search_slots). No mixing of styles or unconventional names.
With 7 tools, the set is well-scoped for an appointment booking domain. Each tool has a clear role, and the count is neither too thin nor too heavy.
The set covers the main lifecycle: search, filter, book, list, and reschedule. However, a cancellation tool is missing, which is a minor gap for a complete appointment management workflow.
Book medical appointments with French doctors by specialty and city via AI agents.
Read appointments, types, calendars and availability; create, cancel or reschedule bookings.
Calendar API for AI agents: events, availability, Google/Microsoft setup, scheduling, and iCal.
AI-native scheduling: check availability, book meetings, cancel and reschedule via MCP
