_ registry / mcp streamable-http · checked 1h ago

nolizi-calendar

https://calendar.nolizi.com

Registry code: 19455eaa11a2507f

api record

Nolizi Calendar: scheduling for the account whose API key this server holds.

Work in this order: list_event_types to find a slug, list_available_slots to get real times, then create_booking once the person has confirmed the event, the time and the attendee details. Always verify a write with list_upcoming_bookings before reporting it as done.

endpoint
https://calendar.nolizi.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is nolizi-calendar live?
Yes — it answered the hub's last check (checked 1h ago). It answered 99% of checks over the last 30 days.
Is nolizi-calendar free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does nolizi-calendar have?
5 tools: create_booking, list_upcoming_bookings, cancel_booking, list_event_types, list_available_slots.
Is nolizi-calendar safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.1%

90 days 98.9%· all time 98.9%

latency
174ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 376 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • list bookable event types
  • find available meeting slots
  • book a meeting
  • cancel a booking
  • list upcoming bookings
takes → gives
data → data
tools
3 reads2 changes data
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
5 auth-required 5 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • create_booking changes data auth-required never probed

    Book a real meeting. This sends invitations and writes to connected calendars, and it cannot be undone except by cancelling. Ask the person to confirm the event, the exact time and the attendee details before calling it, and use their real name and email — never a placeholder. The start and end must be copied verbatim from a recent list_available_slots response; this server re-checks them against live availability and refuses times it cannot find. There is no idempotency key: if this call returns an uncertain outcome, do not call it again — call list_upcoming_bookings and read what actually happened.

    mcp-tool

    {
      "type": "object",
      "required": [
        "event_type",
        "start",
        "end",
        "name",
        "email"
      ],
      "properties": {
        "end": {
          "type": "string",
          "description": "The matching end from that same slot."
        },
        "name": {
          "type": "string",
          "description": "The attendee’s real name."
        },
        "note": {
          "type": "string",
          "description": "Optional note shared with the host (max 2000 characters)."
        },
        "email": {
          "type": "string",
          "description": "The attendee’s real email address. Invitations go here."
        },
        "start": {
          "type": "string",
          "description": "Start, copied exactly from a fresh list_available_slots response."
        },
        "booker_tz": {
          "type": "string",
          "description": "Attendee IANA timezone, e.g. Europe/Berlin. Defaults to UTC."
        },
        "event_type": {
          "type": "string",
          "description": "Event slug from list_event_types."
        }
      },
      "additionalProperties": false
    }
    arguments 41 lines
  • list_upcoming_bookings reads auth-required never probed

    List up to 100 upcoming confirmed bookings. This is the only way to verify that a booking exists. Use it after every create or cancel, and use it first whenever a write returned an uncertain outcome.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • cancel_booking changes data auth-required never probed

    Cancel a confirmed booking. This notifies the attendee and removes the meeting from connected calendars, and it cannot be undone. Use an exact booking_id taken from list_upcoming_bookings — never a guessed or reconstructed one. Cancelling one occurrence of a grouped or recurring booking can affect several meetings, so confirm with the person which meetings they mean.

    mcp-tool

    {
      "type": "object",
      "required": [
        "booking_id"
      ],
      "properties": {
        "booking_id": {
          "type": "string",
          "description": "Exact booking_id from list_upcoming_bookings."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • list_event_types reads auth-required 8h ago

    List the bookable event types owned by the configured Nolizi Calendar account. Start here: the returned slug is what every other tool needs. Never guess a slug. Events with required custom questions or email verification cannot be booked through this API — send the person to the event’s public booking page instead.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • list_available_slots reads auth-required 8h ago

    Return the live available start/end pairs for one event type. These are real times on a real calendar: show them to the person and let them choose. Do not invent, extrapolate or round a time that is not in this response. Convert times for display only — pass the original values back to create_booking unchanged.

    mcp-tool

    {
      "type": "object",
      "required": [
        "event_type"
      ],
      "properties": {
        "event_type": {
          "type": "string",
          "description": "Event slug from list_event_types (not a schedule_id)."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 19455eaa11a2507f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/19455eaa11a2507f/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/19455eaa11a2507f/badge.svg)](https://brick.blue/agent/19455eaa11a2507f?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.