_ registry / mcp + a2a streamable-http · checked 1h ago

the-citadel

https://thecitadelapp.com

Registry code: 864d21fd817b9671

api record

Deterministic 6-dimension dating profile rubrics and readiness checks via Streamable HTTP MCP.

from a public catalogue that lists it, not from the operator

endpoint
https://thecitadelapp.com/api/mcp
door code
2bda280377f8a43a
protocol
streamable-http ·2025-03-26
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 the-citadel live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is the-citadel free to use?
Not measured yet.
What tools does the-citadel have?
7 tools: citadel_platform_status, citadel_get_lead_photo_rubric, citadel_evaluate_profile_readiness, citadel_start_profile_upgrade, citadel_run_or_poll_profile_audit, citadel_forge_profile_photo, citadel_get_session_status.
Is the-citadel 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
281ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
  • 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 7 tools
7 never probed 0 of 7 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.

  • citadel_platform_status unknown never probed

    Get The Citadel platform health, supported agentic protocols (MCP, A2A, UCP, ACP, x402), and public discovery endpoints.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • citadel_get_lead_photo_rubric unknown never probed

    Retrieve the deterministic 6-dimension dating profile and lead photo evaluation rubric (lighting, framing, eye contact, social context, prompt specificity, red-flag screening).

    mcp-tool

    {
      "type": "object",
      "properties": {
        "platform": {
          "type": "string",
          "description": "Target dating app (hinge, bumble, tinder, general)"
        }
      },
      "additionalProperties": false
    }
    arguments 10 lines
  • citadel_evaluate_profile_readiness unknown never probed

    Evaluate dating profile structural readiness and estimate first-impression conversion bottlenecks from photo count, group-photo ratio, and prompt length.

    mcp-tool

    {
      "type": "object",
      "required": [
        "photoCount",
        "soloClearLeadPhoto"
      ],
      "properties": {
        "photoCount": {
          "type": "number",
          "description": "Total number of photos in the profile (1-6)"
        },
        "promptCount": {
          "type": "number",
          "description": "Number of completed written prompts or bio sections (0-3)"
        },
        "soloClearLeadPhoto": {
          "type": "boolean",
          "description": "Whether Slot #1 is a clear, solo, unobstructed portrait without sunglasses"
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
  • citadel_start_profile_upgrade unknown never probed

    Start an A-to-Z Full Profile Upgrade session without requiring a prior user account. Stages 1-8 photos (via HTTPS URLs or base64 data URIs) or mints 6 signed upload slots + browser handoff URL, creates a $24.99 Full Profile Upgrade Stripe Checkout (30 credits: 15 Audit + 8 first Forge Photo + 7 left), and returns agent_session_token.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "email": {
          "type": "string",
          "description": "Optional buyer email for Stripe checkout & report delivery"
        },
        "context": {
          "type": "object",
          "description": "Optional dating context (app, city, goal, gender, age_bracket, residency)"
        },
        "image_urls": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "HTTPS URLs of 1-8 dating profile photos"
        },
        "image_base64": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Base64 or data:image/* URIs of 1-8 dating profile photos"
        },
        "agent_platform": {
          "type": "string",
          "description": "Caller platform name (e.g. chatgpt, gemini, grok, cursor, custom)"
        },
        "idempotency_key": {
          "type": "string",
          "description": "Optional idempotency key for checkout creation"
        }
      },
      "additionalProperties": true
    }
    arguments 36 lines
  • citadel_run_or_poll_profile_audit unknown never probed

    Verify Stripe payment and run or poll the 15-credit Profile Signal Audit. Returns awaiting_payment (with checkout_url, 0 credits charged) until paid, processing (with job_id), or complete structured audit findings + report_url.

    mcp-tool

    {
      "type": "object",
      "required": [
        "agent_session_token"
      ],
      "properties": {
        "roast_id": {
          "type": "string",
          "description": "Optional completed roast_id"
        },
        "image_urls": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional additional HTTPS photo URLs if not passed in start"
        },
        "image_base64": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional additional base64 photos if not passed in start"
        },
        "idempotency_key": {
          "type": "string",
          "description": "Optional idempotency key"
        },
        "agent_session_token": {
          "type": "string",
          "description": "Token returned by citadel_start_profile_upgrade"
        }
      },
      "additionalProperties": true
    }
    arguments 35 lines
  • citadel_forge_profile_photo unknown never probed

    Quote or generate an identity-locked Profile Forge photo (8 credits/photo). action='quote' previews exact credit cost without charging; action='generate' requires explicit human confirmation (confirm_quote=true) and auto-provisions a $14.99 (15 credits) Stripe top-up checkout if remaining credits < 8.

    mcp-tool

    {
      "type": "object",
      "required": [
        "agent_session_token"
      ],
      "properties": {
        "action": {
          "enum": [
            "quote",
            "generate",
            "poll"
          ],
          "type": "string",
          "description": "'quote' (default), 'generate' (requires confirm_quote=true), or 'poll'"
        },
        "job_id": {
          "type": "string",
          "description": "Optional Forge job_id when polling"
        },
        "roast_id": {
          "type": "string",
          "description": "Optional roast_id if not carried inside session token"
        },
        "confirm_quote": {
          "type": "boolean",
          "description": "Must be true after the human explicitly confirms the 8-credit Forge quote"
        },
        "idempotency_key": {
          "type": "string",
          "description": "Optional idempotency key"
        },
        "agent_session_token": {
          "type": "string",
          "description": "Session token from start/audit"
        }
      },
      "additionalProperties": true
    }
    arguments 38 lines
  • citadel_get_session_status unknown never probed

    Retrieve unified A-to-Z session state: Stripe payment status, wallet credit balance, staged photo count, Profile Audit report/findings, and generated Forge photos.

    mcp-tool

    {
      "type": "object",
      "required": [
        "agent_session_token"
      ],
      "properties": {
        "roast_id": {
          "type": "string",
          "description": "Optional roast_id filter"
        },
        "agent_session_token": {
          "type": "string",
          "description": "Session token returned by start, audit, or forge"
        }
      },
      "additionalProperties": true
    }
    arguments 17 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 864d21fd817b9671.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/864d21fd817b9671/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/864d21fd817b9671/badge.svg)](https://brick.blue/agent/864d21fd817b9671?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
1
ok
0
failed
1
success rate
0%
median latency
225ms
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
—

1 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.