# Chronary (remote · api.chronary.ai)

Calendar API for AI agents: events, availability, Google/Microsoft setup, scheduling, and iCal.

- Trust score: 81/100 (high trust)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.chronary.ai`: 81/100 (this document), [markdown](https://verifymcp.io/servers/ai-chronary-mcp/api.md), [page](https://verifymcp.io/servers/ai-chronary-mcp/api)
- npm · `@chronary/mcp`: 46/100, [markdown](https://verifymcp.io/servers/ai-chronary-mcp/chronary-mcp.md), [page](https://verifymcp.io/servers/ai-chronary-mcp/chronary-mcp)

## Channel facts

- Endpoint: `https://api.chronary.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.5.2`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 6199 tokens (~112/item across 55 items; 54 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-chronary-mcp https://api.chronary.ai/mcp
```

### Codex

```toml
[mcp_servers.ai-chronary-mcp]
url = "https://api.chronary.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-chronary-mcp": {
      "type": "remote",
      "url": "https://api.chronary.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-chronary-mcp --url https://api.chronary.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-chronary-mcp:
    url: "https://api.chronary.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-chronary-mcp": {
      "type": "http",
      "url": "https://api.chronary.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 80, +4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 76, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 74, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 73)

First indexed and scored.

## MCP tools (54)

### `create_agent` (~66 tokens)

Register your agent (AI assistant, human participant, or resource) with Chronary so it can own calendars, events, and webhooks.

Input parameters:

- `description` (string): Optional description
- `name` (string, required): Display name for the agent
- `type` (string, required): Agent type

### `list_agents` (~56 tokens)

List all agents in your organization

Input parameters:

- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset
- `status` (string): Filter by status
- `type` (string): Filter by agent type

### `create_calendar` (~160 tokens)

Create a calendar to hold events and track availability. Calendars are required before creating events — call this first when setting up a new agent. An agent can have multiple calendars (e.g. "Work", "Personal"). Org-level calendars (no agent_id) can be used as shared resources like meeting rooms.

Input parameters:

- `agent_id` (string): Agent ID to own this calendar (omit for org-level)
- `default_reminders`: Default reminder offsets in minutes before start, inherited by events on this calendar that don't set their own. Omit or null to use the system default (10 min); [] for no reminders.
- `name` (string, required): Calendar name
- `timezone` (string, required): IANA timezone (e.g. America/New_York)

### `create_event` (~466 tokens)

Create a booking, appointment, meeting, hold, or any scheduled event on a calendar. The calendar_id comes from create_calendar or list_events. Once created, this event blocks the agent's availability during that time and appears in availability queries. Use status="hold" with hold_expires_at to tentatively reserve a slot that auto-releases on TTL.

Input parameters:

- `all_day` (boolean): Whether this is an all-day event
- `calendar_id` (string, required): Calendar ID to add the event to
- `description` (string): Optional event description
- `end_time` (string, required): End time (ISO 8601)
- `hold_expires_at` (string): Required when status="hold". ISO 8601 timestamp 30s-15min in the future. Auto-releases the hold when reached.
- `hold_priority` (integer): Only valid with status="hold". Higher-priority overlapping holds pre-empt lower-priority ones. Defaults to 0.
- `recurrence_rule` (string): Make this a recurring series (RFC 5545 RRULE subset, no "RRULE:" prefix), e.g. "FREQ=WEEKLY;BYDAY=MO,WE;COUNT=12". Supports FREQ=DAILY/WEEKLY/MONTHLY/YEARLY, INTERVAL, COUNT (max 730) or UNTIL, BYDAY…
- `reminders`: Reminder offsets in minutes before start_time (e.g. [10, 1440]). Each fires an event.reminder webhook and shows as an alarm in the iCal feed. Omit or null to inherit the calendar default (then the sy…
- `start_time` (string, required): Start time (ISO 8601)
- `status` (string): Event status. "hold" creates a tentative reservation that auto-expires at hold_expires_at. Defaults to "confirmed".
- `title` (string, required): Event title

### `list_events` (~262 tokens)

List events on a calendar or across an agent's calendars, including internally created events and externally synced events from iCal subscriptions (e.g. Google Calendar, Outlook). Provide `calendar_id` OR `agent_id`. Narrow with `start_after`/`start_before` (time window), `status`, and `source`.

Input parameters:

- `agent_id` (string): Agent ID to list events for across all of the agent's calendars. Provide this or calendar_id.
- `calendar_id` (string): Calendar ID to list events from. Provide this or agent_id.
- `expand` (boolean): Expand recurring series into individual occurrence instances within the window. Requires both start_after and start_before (max 366 days apart). Instances carry recurringEventId + originalStartTime.
- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset
- `source` (string): Filter by source: "internal" (created via the API) or "external_ical" (synced from an iCal subscription)
- `start_after` (string): Only events starting after this ISO 8601 time
- `start_before` (string): Only events starting before this ISO 8601 time
- `status` (string): Filter by event status

### `get_event` (~112 tokens)

Retrieve a single event by ID, including its title, times, status, location, reminders, and metadata. Works for both internally created events and externally synced iCal events. `calendar_id` is optional — if omitted the calendar is resolved from the event. Provide `calendar_id` to fail fast on cross-calendar typos.

Input parameters:

- `calendar_id` (string): Calendar ID that owns the event. Optional — if omitted the calendar is resolved from the event.
- `event_id` (string, required): Event ID to retrieve

### `update_event` (~299 tokens)

Reschedule or edit an event — change its title, description, start/end times, location, status, reminders, or metadata. Use this to move an appointment to a new time or update its details. Provide only the fields you want to change. Holds cannot be edited via this tool (use confirm_event / release_event). External iCal events are read-only. `calendar_id` is optional — if omitted it is resolved from the event.

Input parameters:

- `all_day` (boolean): Whether this is an all-day event
- `calendar_id` (string): Calendar ID that owns the event. Optional — if omitted the calendar is resolved from the event.
- `description`: New description, or null to clear it
- `end_time` (string): New end time (ISO 8601)
- `event_id` (string, required): Event ID to update
- `metadata` (object): Replacement metadata object
- `recurrence_rule`: Set/change the recurring series rule (RFC 5545 RRULE subset, full-series semantics), or null to make the event a one-off. Changing the rule or start_time resets cancelled occurrences.
- `reminders`: Reminder offsets in minutes before start_time. Omit to leave unchanged, null to inherit the calendar default, [] for no reminders.
- `start_time` (string): New start time (ISO 8601)
- `status` (string): New event status
- `title` (string): New event title

### `get_availability` (~234 tokens)

Check when a single agent is free across its Chronary calendars and any human calendars authorized for that agent. This tool is fail-closed: always inspect `availability_state` and `warnings` before using slots. Accepts `start`/`end` or the `start_time`/`end_time` aliases.

Input parameters:

- `agent_id` (string, required): Agent ID to check availability for
- `duration` (string): Requested slot length (15m/30m/45m/1h/2h). Preferred over the deprecated slot_duration. Defaults to 30m.
- `end` (string): Range end (ISO 8601). Alias: end_time.
- `end_time` (string): Alias for `end` (matches REST events naming).
- `include_busy` (boolean): Include busy blocks in response
- `slot_duration` (string): Deprecated alias for `duration` — minimum slot length. Prefer `duration`.
- `start` (string): Range start (ISO 8601). Alias: start_time.
- `start_time` (string): Alias for `start` (matches REST events naming).

### `find_meeting_time` (~287 tokens)

Find slots when multiple agents are free across Chronary calendars and any human calendars authorized for each agent. This tool is fail-closed: always inspect `availability_state` and `warnings` before using slots. Accepts `agents`/`start`/`end` or their aliases.

Input parameters:

- `agent_ids` (array): Alias for `agents` (matches REST/scheduling-proposal naming).
- `agents` (array): Array of agent IDs to find common free time for. All agents must be free during the returned slots. Alias: agent_ids.
- `calendars` (array): Additional shared calendar IDs to treat as busy
- `duration` (string): Requested slot length (15m/30m/45m/1h/2h). Preferred over the deprecated slot_duration. Defaults to 30m.
- `end` (string): Search range end (ISO 8601). Alias: end_time.
- `end_time` (string): Alias for `end` (matches REST events naming).
- `include_busy` (boolean): Include per-agent busy blocks in response
- `slot_duration` (string): Deprecated alias for `duration` — minimum slot length. Prefer `duration`.
- `start` (string): Search range start (ISO 8601). Alias: start_time.
- `start_time` (string): Alias for `start` (matches REST events naming).

### `cancel_event` (~192 tokens)

Delete or cancel an event from a calendar. Use this to remove, cancel, or delete any scheduled event or appointment. The event is marked cancelled and excluded from future availability calculations. For a recurring series, pass `occurrence_start` to cancel just that one occurrence (the series continues); omit it to cancel the whole series. `calendar_id` is optional — if omitted the calendar is looked up from the event. Provide `calendar_id` to fail fast on cross-calendar typos.

Input parameters:

- `calendar_id` (string): Calendar ID that owns the event. Optional — if omitted the calendar is resolved from the event. Matches the asymmetry with confirm_event / release_event which never required this arg.
- `event_id` (string, required): Event ID to cancel
- `occurrence_start` (string): For recurring events only: ISO 8601 start of the single occurrence to cancel. The rest of the series is unaffected.

### `confirm_event` (~70 tokens)

Promote a held event to a confirmed booking. The event must currently have status="hold" and its hold_expires_at must not have passed. After confirmation, event.started and event.ended lifecycle webhooks fire at the scheduled times.

Input parameters:

- `event_id` (string, required): Event ID of the hold to confirm

### `release_event` (~55 tokens)

Manually release a held event before its hold_expires_at. The event must currently have status="hold". Frees the slot for other agents to book.

Input parameters:

- `event_id` (string, required): Event ID of the hold to release

### `subscribe_ical` (~144 tokens)

Link an external iCal feed (e.g. a human's Google Calendar) to an agent's calendar so external events appear in availability calculations. The target calendar must be owned by the specified agent — create the calendar with that agent_id first (org-level calendars without an agent_id cannot host external iCal subscriptions; create a dedicated per-agent calendar for sync targets).

Input parameters:

- `agent_id` (string, required): Agent ID that will own this subscription
- `calendar_id` (string, required): Calendar ID to sync external events into
- `label` (string): Optional label for this subscription
- `url` (string, required): HTTPS URL of the iCal feed (.ics) to subscribe to

### `list_ical_subscriptions` (~87 tokens)

List an agent's external iCal feed subscriptions (e.g. linked Google Calendar / Outlook feeds), including their sync status and last sync time.

Input parameters:

- `agent_id` (string, required): Agent ID whose iCal subscriptions to list
- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset
- `status` (string): Filter by subscription status

### `get_ical_subscription` (~48 tokens)

Get a single external iCal feed subscription by id, including its sync status, last sync time, and last error.

Input parameters:

- `subscription_id` (string, required): iCal subscription ID to fetch

### `update_ical_subscription` (~82 tokens)

Update an external iCal feed subscription — change its label or its feed URL. Changing the URL forces a full re-sync on the next poll.

Input parameters:

- `label` (string): New label for this subscription
- `subscription_id` (string, required): iCal subscription ID to update
- `url` (string): New HTTPS URL of the iCal feed (.ics)

### `delete_ical_subscription` (~43 tokens)

Delete an external iCal feed subscription. Events previously synced from the feed are no longer refreshed.

Input parameters:

- `subscription_id` (string, required): iCal subscription ID to delete

### `sync_ical_subscription` (~52 tokens)

Trigger an immediate sync of an external iCal feed subscription instead of waiting for the next scheduled poll. Returns once the sync has been queued.

Input parameters:

- `subscription_id` (string, required): iCal subscription ID to sync

### `get_calendar_context` (~89 tokens)

Get a calendar's temporal context in a single call: the current event (if one is happening now), the next upcoming event, recent past events, a short upcoming window, and the owning agent's status (idle/working/waiting/error). Use this to answer "what is this agent doing right now?" without issuing multiple list_events queries.

Input parameters:

- `calendar_id` (string, required): Calendar ID

### `create_proposal` (~180 tokens)

Create a scheduling proposal — send a set of candidate time slots to one or more participant agents so they can accept, decline, or counter-propose. The organizer agent owns the proposal; once every participant responds, the system auto-resolves to the highest-scoring slot (or cancels if all decline). Requires an org-level API key. Pro plan only.

Input parameters:

- `calendar_id` (string, required): Calendar the resolved event will be created on
- `description` (string): Longer context/agenda
- `expires_at` (string): Auto-cancel cutoff if unresolved
- `organizer_agent_id` (string, required): Agent ID proposing the meeting
- `participant_agent_ids` (array, required): Agent IDs invited to respond
- `slots` (array, required): Candidate time slots (up to 20)
- `title` (string, required): Short description of what the meeting is about

### `list_proposals` (~91 tokens)

List scheduling proposals for the org. Filter by status (pending|confirmed|expired|cancelled) or organizer_agent_id. Requires an org-level API key.

Input parameters:

- `limit` (integer): Max results (default 50)
- `offset` (integer): Pagination offset (default 0)
- `organizer_agent_id` (string): Filter by organizer agent
- `status` (string): Filter by proposal status

### `get_proposal` (~43 tokens)

Get a scheduling proposal by id, including its slots and per-participant responses. Requires an org-level API key.

Input parameters:

- `proposal_id` (string, required): Proposal to fetch

### `respond_to_proposal` (~160 tokens)

Submit a response (accept / decline / counter) on behalf of one participant agent to an open proposal. An "accept" requires the slot id from the proposal; a "counter" can suggest alternative slots. When all participants have responded the proposal auto-resolves — no separate resolve call needed in the normal flow. Requires an org-level API key. Pro plan only.

Input parameters:

- `agent_id` (string, required): Participant agent responding
- `counter_slots` (array): Alternative slots when response is "counter"
- `message` (string): Optional note for the organizer
- `proposal_id` (string, required): Proposal to respond to
- `response` (string, required): Decision from this agent
- `selected_slot_id` (string): Required when response is "accept"

### `resolve_proposal` (~92 tokens)

Force-resolve an open proposal using responses collected so far. Picks the highest-scoring slot among those accepted by the most participants and creates a confirmed calendar event. If every response was "decline", the proposal is cancelled instead. Use when you want to close out a proposal without waiting for every participant. Requires an org-level API key. Pro plan only.

Input parameters:

- `proposal_id` (string, required): Proposal to resolve

### `cancel_proposal` (~50 tokens)

Cancel an open proposal. Fires a proposal.cancelled webhook with reason="organizer_cancelled". Requires an org-level API key. Pro plan only.

Input parameters:

- `proposal_id` (string, required): Proposal to cancel

### `set_availability_rules` (~172 tokens)

Set or replace the availability rules on a calendar — buffer times before/after events and optional per-day working hours. When these rules are set, every availability query on this calendar automatically applies them (busy-block expansion for buffers, masking outside working hours). Upsert: overwrites any existing rules.

Input parameters:

- `buffer_after_minutes` (integer): Minutes of buffer after each event (0–120)
- `buffer_before_minutes` (integer): Minutes of buffer before each event (0–120)
- `calendar_id` (string, required): Calendar to configure
- `timezone` (string): IANA timezone used to interpret working_hours (e.g. America/New_York)
- `working_hours`: Per-day working hours map in the calendar's timezone; omit keys for off-days. Pass null to remove any working-hours constraint.

### `get_availability_rules` (~47 tokens)

Read the buffer times and working-hours rules configured on a calendar. Returns the rules row, or an error if none are set.

Input parameters:

- `calendar_id` (string, required): Calendar to read

### `clear_availability_rules` (~58 tokens)

Remove the availability rules from a calendar, reverting to the default (no buffers, no working-hours mask). Returns the deleted row, or an error if none were set.

Input parameters:

- `calendar_id` (string, required): Calendar whose rules should be cleared

### `create_scoped_key` (~102 tokens)

Create an agent-scoped API key (chr_ak_*) that can only act on behalf of a single agent. Use this to self-provision or rotate per-agent credentials. The plaintext key is returned exactly once in the response — store it immediately, it cannot be retrieved later. Requires an org-level API key.

Input parameters:

- `agent_id` (string, required): Agent ID this key is scoped to
- `label` (string): Human-readable label for the key

### `list_scoped_keys` (~58 tokens)

List all live (non-revoked) agent-scoped API keys for this org. Returns key metadata only (id, prefix, agent_id, label, created_at) — never the plaintext secret. Requires an org-level API key.

### `revoke_scoped_key` (~65 tokens)

Revoke an agent-scoped API key by ID. Revocation is permanent (cannot be un-revoked); the key stops authenticating within about a minute. Requires an org-level API key.

Input parameters:

- `key_id` (string, required): ID of the scoped key to revoke

### `create_webhook` (~94 tokens)

Create a webhook subscription so the org receives HTTP POST notifications when events occur (e.g. event.created, proposal.confirmed). The signing secret is returned ONCE in this response — store it to verify the HMAC-SHA256 signature on delivered payloads. Requires an org-level API key.

Input parameters:

- `events` (array, required): Event types to subscribe to
- `url` (string, required): HTTPS endpoint that will receive event deliveries

### `list_webhooks` (~57 tokens)

List the org's webhook subscriptions with their subscribed event types and active state. Signing secrets are never returned. Requires an org-level API key.

Input parameters:

- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset

### `get_webhook` (~53 tokens)

Get a single webhook subscription by id, including its subscribed event types and active state. The signing secret is never returned. Requires an org-level API key.

Input parameters:

- `webhook_id` (string, required): Webhook subscription to fetch

### `update_webhook` (~104 tokens)

Update a webhook subscription — change its delivery URL, the set of subscribed event types, or pause/resume it via active. At least one field must be supplied. Requires an org-level API key.

Input parameters:

- `active` (boolean): Set false to pause deliveries, true to resume
- `events` (array): Replacement set of event types to subscribe to
- `url` (string): New HTTPS delivery endpoint
- `webhook_id` (string, required): Webhook subscription to update

### `delete_webhook` (~47 tokens)

Permanently delete a webhook subscription. This frees its endpoint slot against the per-plan cap. Requires an org-level API key.

Input parameters:

- `webhook_id` (string, required): Webhook subscription to delete

### `list_webhook_deliveries` (~111 tokens)

List delivery attempts for a webhook subscription, with per-status counts (pending/delivered/failed). Use this to debug failing deliveries. Requires an org-level API key.

Input parameters:

- `include_payload` (boolean): Include the full event payload sent on each delivery
- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset
- `status` (string): Filter to a single delivery status
- `webhook_id` (string, required): Webhook subscription whose deliveries to list

### `get_agent` (~59 tokens)

Fetch a single agent by ID. An agent represents an AI assistant, human, or shared resource (e.g. a meeting room). Agent-scoped API keys may only read their own agent.

Input parameters:

- `agent_id` (string, required): Agent ID to fetch

### `update_agent` (~97 tokens)

Update an agent's name, description, metadata, or status (active/paused). Requires an org-level API key — agent-scoped keys cannot mutate agents.

Input parameters:

- `agent_id` (string, required): Agent ID to update
- `description`: New description (null to clear)
- `metadata` (object): Arbitrary metadata (max 16KB)
- `name` (string): New display name
- `status` (string): Operational status

### `delete_agent` (~59 tokens)

Decommission an agent. This marks the agent as decommissioned and revokes all of its scoped API keys. Requires an org-level API key — agent-scoped keys cannot delete agents.

Input parameters:

- `agent_id` (string, required): Agent ID to decommission

### `list_calendars` (~128 tokens)

List calendars in the org. Org-level API keys see every calendar (agent-owned and shared); agent-scoped keys see only their own agent's calendars. Use this to discover calendar IDs before creating or listing events.

Input parameters:

- `agent_id` (string): Filter to calendars owned by this agent. Org keys only — agent-scoped keys are always limited to their own agent and ignore this.
- `include` (string): Pass "all" to include calendars across all agents (org keys only)
- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset

### `get_calendar` (~53 tokens)

Fetch a single calendar by ID, including its name, timezone, agent status, and default reminders. Agent-scoped keys may only read calendars owned by their agent.

Input parameters:

- `calendar_id` (string, required): Calendar ID to fetch

### `update_calendar` (~128 tokens)

Update a calendar's name, timezone, agent status, default reminders, or metadata. Agent-scoped keys may only update calendars owned by their agent.

Input parameters:

- `agent_status` (string): Owning agent's status
- `calendar_id` (string, required): Calendar ID to update
- `default_reminders`: Default reminder offsets in minutes; null for system default, [] for none
- `metadata` (object): Arbitrary metadata (max 16KB)
- `name` (string): New calendar name
- `timezone` (string): New IANA timezone (e.g. America/New_York)

### `delete_calendar` (~53 tokens)

Delete a calendar (soft delete). Its events are no longer returned and it stops contributing to availability. Agent-scoped keys may only delete calendars owned by their agent.

Input parameters:

- `calendar_id` (string, required): Calendar ID to delete

### `create_booking_page` (~270 tokens)

Create a public booking page (a hosted scheduling link) for a calendar. Returns a booking_url to send to a human; when they pick a slot, a confirmed event is created on the calendar and an event.created webhook fires with a booking_page_id field. Set availability_constraints to restrict to weekly working hours; existing calendar events always block slots.

Input parameters:

- `active` (boolean): Whether the page accepts bookings (default true).
- `availability_constraints`: Weekly working hours, e.g. {"mon":{"start":"09:00","end":"17:00"}}. Omit/null for any time in the window.
- `buffer_minutes` (integer): Padding before/after existing events (default 0).
- `calendar_id` (string, required): Calendar a booking resolves to (from create_calendar/list_calendars).
- `description` (string): Optional description shown to the booker.
- `duration_minutes` (integer): Slot length in minutes (default 30).
- `min_notice_minutes` (integer): Minimum lead time before a bookable slot (default 0).
- `timezone` (string): IANA timezone for display + working hours (default UTC).
- `title` (string, required): Meeting title shown on the page.
- `window_days` (integer): How far ahead bookings are allowed (default 14).

### `list_booking_pages` (~50 tokens)

List booking pages in the org. Agent-scoped keys see only pages on their own agent's calendars.

Input parameters:

- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset

### `get_booking_page` (~43 tokens)

Fetch a single booking page by ID, including its public booking_url and settings.

Input parameters:

- `booking_page_id` (string, required): Booking page ID to fetch (bkp_...)

### `delete_booking_page` (~49 tokens)

Delete (deactivate) a booking page. Its hosted URL stops resolving; already-booked events are unaffected.

Input parameters:

- `booking_page_id` (string, required): Booking page ID to delete (bkp_...)

### `get_usage` (~71 tokens)

Get the calling org's current-period usage and plan limits (agents, calendars, events, API calls, webhooks, availability queries, iCal subscriptions, proposals, scoped keys, holds, cross-calendar queries). Requires an org-level API key (chr_sk_*); agent-scoped keys cannot read org-wide usage.

### `get_audit_log` (~175 tokens)

List audit-log entries for the calling org — mutating operations and auth-lifecycle events, newest first. Results are clamped to the plan's retention window. Requires an org-level API key (chr_sk_*); agent-scoped keys cannot read the org-wide audit log.

Input parameters:

- `action` (string): Filter by action name (e.g. event.created)
- `actor_key_prefix` (string): Filter by the API key prefix that performed the action
- `cursor` (string): Opaque pagination cursor from a previous response
- `from` (string): Start of the window (ISO 8601). Silently clamped to the plan retention window if older.
- `limit` (integer): Max results to return (default 50)
- `to` (string): End of the window (ISO 8601)

### `accept_terms` (~117 tokens)

Re-accept the current Chronary terms of service on behalf of the calling org. Use this when responses carry the Chronary-Terms-Upgrade-Required header — a material ToS bump otherwise leaves MCP-only agents stuck without a console session. Pass the current tos_version (read it from GET /v1/auth/terms/current). Requires an org-level API key (chr_sk_*); agent-scoped keys cannot accept org-wide terms.

Input parameters:

- `tos_version` (string, required): The terms-of-service version to accept; must match the current version

### `create_connection_link` (~132 tokens)

Request human setup of Google Calendar or Microsoft Outlook for a Chronary calendar. Give setup_url to a human; the agent never receives OAuth credentials, provider calendar names, or event data. The secret URL is returned only on first creation. If reused=true and setup_url is null, retain the original URL or cancel this link and create a replacement.

Input parameters:

- `calendar_id` (string, required): Chronary calendar whose owning agent will receive authorized availability
- `capabilities` (array): Request opaque availability, plus optional opt-in event publishing permission
- `publication_policy` (string): Desired publishing policy; a human still chooses the destination

### `get_connection_link` (~54 tokens)

Poll a human-calendar setup request. Returns provider-neutral status and resulting connection ID when complete, but never replays the bearer setup URL or exposes human calendar data.

Input parameters:

- `connection_link_id` (string, required): Connection setup link ID

### `cancel_connection_link` (~48 tokens)

Cancel a pending human-calendar setup request. This invalidates the setup URL and does not disconnect an already completed Google or Microsoft connection.

Input parameters:

- `connection_link_id` (string, required): Connection setup link ID

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-chronary-mcp/api#diagnostics

## Score history

- 2026-08-03: 81
- 2026-08-02: 81
- 2026-08-01: 80
- 2026-07-31: 80
- 2026-07-30: 76
- 2026-07-29: 75
- 2026-07-28: 74
- 2026-07-27: 74
- 2026-07-26: 73

## Links

- Remote endpoint: https://api.chronary.ai/mcp
- Authorisation metadata: https://api.chronary.ai/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/Chronary/chronary-mcp
- Website: https://docs.chronary.ai/mcp/overview
- Changelog RSS feed: https://verifymcp.io/servers/ai-chronary-mcp/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-chronary-mcp/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-chronary-mcp/api