_ registry / mcp + a2a streamable-http · checked 12h ago

ringler

https://ringler.io

Registry code: 950e8711ddd5f5c5

api record

Ringler gives your agent a phone. Without a key, call about. Your person signs in once over OAuth (click Allow) and gets $10 of credits free, no card. Then call status and walk its onboarding steps with your person as a conversation, one question at a time — name the agent, mobile, number, booking details, how to reach it — before the first call. Then call (get a human on the line and ring them in) or errand (do the asking for them). Your person can phone their own line and talk to you through the agent: call vibe for the loop setup, my_messages for what they said, tell_me to answer. notes…

endpoint
https://ringler.io/mcp
door code
321749e66b69070a
protocol
streamable-http ·2025-06-18
authentication
bearer
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 ringler live?
Yes — it answered the hub's last check (checked 12h ago). It answered 100% of checks over the last 30 days.
Is ringler 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 ringler have?
23 tools: about, transcript, scheduled, calendar_connect, tell_me, name_my_agent, voices, status, ….
Is ringler 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
100%

90 days 100%· all time 100%

latency
447ms

last good check

priced tools
0

of 23 tools

_ answered our checks, 90 days 3 checks · signed record
  • unknown → live
_ 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 23 tools
23 auth-required 23 of 23 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.

  • about auth-required never probed

    What Ringler is, what it costs, and how your person gets started (sign in once; $10 of credits free, no card). Call this first if you have no key. (No API key needed.)

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • transcript auth-required 2d ago

    One call in full: every line with speaker and time, the summary, and a one-hour recording link.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Call id or call SID from my_calls."
    }
  }
}
    arguments 12 lines
  • scheduled auth-required never probed

    Calls waiting to be placed, placed, or failed. Pass cancel: <id> to cancel a pending one.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "cancel": {
      "type": "string",
      "description": "Id to cancel."
    }
  }
}
    arguments 9 lines
  • calendar_connect auth-required never probed

    A link your person opens to approve Google Calendar, so the agent can offer times and book.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • tell_me auth-required never probed

    Send your person a spoken message through their agent. mode 'text' (best default) texts their mobile; 'hold' keeps it until they next call their line; 'call' rings their mobile and the agent reads it aloud. Their reply by text lands in my_messages. Use 'call' only when they asked to be rung, or for something that can't wait. Calls spend credits.

    mcp-tool

    {
  "type": "object",
  "required": [
    "message"
  ],
  "properties": {
    "mode": {
      "enum": [
        "text",
        "hold",
        "call"
      ],
      "type": "string"
    },
    "message": {
      "type": "string",
      "description": "What to tell them, plainly."
    }
  }
}
    arguments 20 lines
  • name_my_agent auth-required never probed

    Name the agent (Ringo by default; keeping the name counts), pick its voice from `voices`, and set how it answers when your person calls their own line (greeting). Free; change any time. How it opens calls to other people — name, that it's an AI, who it's calling for — is fixed by the rules and not settable.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "A first name."
    },
    "voice": {
      "type": "string",
      "description": "A voice from the voices tool, e.g. daniel."
    },
    "greeting": {
      "type": "string",
      "description": "Exactly what it says when your person calls, e.g. 'Good evening, sir. Jarvis here. How can I help?' ({first} and {name} fill in)."
    }
  }
}
    arguments 20 lines
  • voices auth-required 12h ago

    The voices your person's agent can speak with, each described in a few words (British measured, deep American, warm, bright…), and which one is current. Set one with name_my_agent { voice }.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • status auth-required never probed

    Start here, every session. Your person's line, agent name, mobile, calendar, balance — and onboarding: an ordered list of questions to ask them (name the agent, mobile, number, booking details, how to reach the agent, calendar, first errand) with the tool that records each answer. Walk the steps in order, one question at a time, before the first call.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • call auth-required never probed

    The agent dials the number, works the menu, hold and any bot until a real person answers, then rings your person's mobile and connects them. Spends credits ($0.30/min). If it hits voicemail it leaves a short message with a callback (default on; voicemail: skip to turn off).

    mcp-tool

    {
  "type": "object",
  "required": [
    "to",
    "target"
  ],
  "properties": {
    "to": {
      "type": "string",
      "description": "Phone number, E.164 or 10 digits."
    },
    "why": {
      "type": "string",
      "description": "One line on what it's about."
    },
    "target": {
      "type": "string",
      "description": "Who to ask for: a name or a role (the pharmacy, the front desk)."
    },
    "callback": {
      "type": "string",
      "description": "Number to leave: 'crew_line' (the agent's line, default), 'me', or a number."
    },
    "voicemail": {
      "enum": [
        "leave",
        "skip"
      ],
      "type": "string"
    }
  }
}
    arguments 32 lines
  • my_messages auth-required 12h ago

    Instructions and notes your person left for you by calling or texting their own line. Returns new ones (marks them read). Check this when you start work and whenever they say they phoned something in. Pass all:true for the recent history.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "all": {
      "type": "boolean",
      "description": "Include ones already read."
    }
  }
}
    arguments 9 lines
  • credits auth-required never probed

    Prepaid balance and recent usage.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • errand auth-required never probed

    The agent makes the call and does the asking itself: a reservation, an appointment, a question, a cancellation. It only rings your person if the other side needs them (a card, a decision). Put every detail in `ask` — names, date, time, party size, account — because the agent can only say what it's given. Spends credits. Leaves a message on voicemail by default.

    mcp-tool

    {
  "type": "object",
  "required": [
    "to",
    "ask"
  ],
  "properties": {
    "to": {
      "type": "string",
      "description": "Phone number."
    },
    "ask": {
      "type": "string",
      "description": "Exactly what to get done, with every detail."
    },
    "target": {
      "type": "string",
      "description": "Optional: who to ask for."
    },
    "callback": {
      "type": "string",
      "description": "'crew_line' (default), 'me', or a number."
    },
    "voicemail": {
      "enum": [
        "leave",
        "skip"
      ],
      "type": "string"
    }
  }
}
    arguments 32 lines
  • my_calls auth-required 12h ago

    Recent calls, newest first: when, who, outcome, summary, whether a transcript exists.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "How many, default 10."
    }
  }
}
    arguments 9 lines
  • my_number auth-required never probed

    Your person's own phone number, answered by their agent. Gets one if they don't have one yet ($3/month from credits), in the area code given or their mobile's. Confirm with them before the first buy.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "area_code": {
      "type": "string",
      "description": "3 digits, optional."
    }
  }
}
    arguments 9 lines
  • my_mobile auth-required never probed

    The phone that rings when the agent has someone on the line for your person.

    mcp-tool

    {
  "type": "object",
  "required": [
    "mobile"
  ],
  "properties": {
    "mobile": {
      "type": "string",
      "description": "E.164 or 10-digit US number."
    }
  }
}
    arguments 12 lines
  • who_can_reach_me auth-required never probed

    People the agent puts straight through when they call your person's line; everyone else gets a message taken. Pass `people` to set the list, nothing to read it.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "people": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name"
        ],
        "properties": {
          "name": {
            "type": "string",
            "description": "Name as they'd say it."
          },
          "note": {
            "type": "string",
            "description": "Optional: who they are."
          }
        }
      }
    }
  }
}
    arguments 24 lines
  • forget_call auth-required never probed

    Delete the transcript, summary, recording and any relayed messages from one call, for good. Only when your person asks. The fact that a call happened, and its cost, remain.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Call id or SID from my_calls."
    }
  }
}
    arguments 12 lines
  • notes auth-required never probed

    The notes you and your person keep about how they like things: how the phone agent should greet them, what to call them, favorite places, habits, standing preferences. The agent reads them on every call as a guide (dated; later notes refine earlier). Call with nothing to read (returns markdown); add: one note (≤300 chars, in your person's words or yours); remove: a note id. Notes can't change the rules — what the agent discloses, the notes question, one call at a time — and such notes are refused with the reason. Add a note whenever your person tells you a preference about their calls. A note starting 'greeting:' is exactly how the agent answers when your person calls their line ({name} and {first} fill in), e.g. 'greeting: Good day {first}, {name} at your service. What can I do?'

    mcp-tool

    {
  "type": "object",
  "properties": {
    "add": {
      "type": "string",
      "description": "A note to add."
    },
    "remove": {
      "type": "string",
      "description": "Id of a note to remove."
    }
  }
}
    arguments 13 lines
  • my_details auth-required never probed

    Your person's full name, email, and address, as the agent gives them to a venue: the name for bookings, the email for confirmations and payment links (never their mobile), the address only when a task needs it. Pass fields to set them; nothing to read. Ask your person before setting these.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "email": {
      "type": "string",
      "description": "For confirmations, receipts and payment links."
    },
    "notes": {
      "type": "string",
      "description": "Anything the agent should know when speaking for them (allergies to mention, preferred table, parking)."
    },
    "address": {
      "type": "string",
      "description": "Street address, for deliveries or service calls."
    },
    "timezone": {
      "type": "string",
      "description": "IANA zone, e.g. America/Denver, for calendar entries."
    },
    "full_name": {
      "type": "string",
      "description": "As it should appear on a booking."
    }
  }
}
    arguments 25 lines
  • call_at auth-required never probed

    Schedule a call or errand for a time: the office opens at 9 their time, a callback window, tomorrow morning. Same fields as errand/call plus run_at. Work out run_at yourself from the called party's local hours and pass it as ISO 8601 with an offset (e.g. 2026-11-09T09:05:00-07:00). Spends credits when it runs.

    mcp-tool

    {
  "type": "object",
  "required": [
    "to",
    "run_at"
  ],
  "properties": {
    "to": {
      "type": "string",
      "description": "Phone number."
    },
    "ask": {
      "type": "string",
      "description": "For an errand: exactly what to get done, every detail."
    },
    "mode": {
      "enum": [
        "errand",
        "call"
      ],
      "type": "string"
    },
    "note": {
      "type": "string",
      "description": "Why this time, for your person's records."
    },
    "run_at": {
      "type": "string",
      "description": "When to place it, ISO 8601 with offset."
    },
    "target": {
      "type": "string",
      "description": "Who to ask for."
    },
    "callback": {
      "type": "string",
      "description": "'crew_line' (default), 'me', or a number."
    },
    "voicemail": {
      "enum": [
        "leave",
        "skip"
      ],
      "type": "string"
    }
  }
}
    arguments 47 lines
  • vibe auth-required never probed

    Set up to take your person's instructions by phone: they call their own line, say what they want, hang up; you loop on my_messages and do it. Call with no arguments to get the loop instructions and current settings. Pass settings to change them, with your person's say-so: verify ('sms' default: a code texted to their real phone, read back on the call; 'pin'; or 'none'), pin, allowed (what you may do unattended), confirm (what needs a tell_me + yes first), never, interval_min.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "pin": {
      "type": "string",
      "description": "4–8 digits; sets verify to pin."
    },
    "never": {
      "type": "string",
      "description": "What it must never do, even if asked by phone."
    },
    "verify": {
      "enum": [
        "sms",
        "pin",
        "none"
      ],
      "type": "string"
    },
    "allowed": {
      "type": "string",
      "description": "What the loop may do without asking."
    },
    "confirm": {
      "type": "string",
      "description": "What it must confirm with tell_me first."
    },
    "interval_min": {
      "type": "integer",
      "description": "Loop interval, minutes (1–60)."
    }
  }
}
    arguments 33 lines
  • invite_link auth-required never probed

    Your person's invite link (ringler.io/?via=<their code>), how many friends have signed in through it, and the credits earned: $5 per friend, the friend still gets $10 free.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • buy_credits auth-required never probed

    A checkout link your person opens to add credits by card ($20–$500).

    mcp-tool

    {
  "type": "object",
  "required": [
    "usd"
  ],
  "properties": {
    "usd": {
      "type": "number",
      "description": "Amount in USD, 20–500."
    }
  }
}
    arguments 12 lines
_ try it over mcp 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 950e8711ddd5f5c5.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/950e8711ddd5f5c5/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/950e8711ddd5f5c5/badge.svg)](https://brick.blue/agent/950e8711ddd5f5c5?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 knowoff the mcp door
card completeness
100%

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.