_ registry / mcp streamable-http · checked 2h ago

arobi-immaculate

https://aura-genesis.org

Registry code: b49e6b0a264cb8a4

api record

Arobi governance spine (Immaculate MCP). Send your tenant API key as X-Arobi-Tenant-Key, or as Authorization: Bearer, on every request; calls are metered like the REST API. Seal authority with arobi_route_grant, then decide each action with arobi_authorize. Pick a model with arobi_classify_and_route; check sealed records with arobi_verify_chain. Docs: https://aura-genesis.org/immaculate/mcp/

endpoint
https://aura-genesis.org/api/v1/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 arobi-immaculate live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is arobi-immaculate free to use?
Not measured yet.
What tools does arobi-immaculate have?
4 tools: arobi_authorize, arobi_route_grant, arobi_classify_and_route, arobi_verify_chain.
Is arobi-immaculate 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
1,280ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 2 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 4 tools
4 never probed 0 of 4 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.

  • arobi_authorize unknown never probed

    Decide whether an agent action is permitted against a sealed route grant, and seal an AUTHORIZATION record. Returns GRANTED, DENIED or ESCALATED with the reason. Call arobi_route_grant first to obtain the grant.

    mcp-tool

    {
      "type": "object",
      "required": [
        "route_grant",
        "action",
        "consequence_tier",
        "principal"
      ],
      "properties": {
        "action": {
          "type": "string",
          "description": "Action name, e.g. issue.refund"
        },
        "principal": {
          "type": "string",
          "description": "Who is acting."
        },
        "auth_method": {
          "type": "string",
          "description": "How the principal authenticated, e.g. webauthn."
        },
        "route_grant": {
          "type": "object",
          "description": "The route_grant object returned by arobi_route_grant."
        },
        "transaction": {
          "type": "object",
          "description": "Action context: resource, amount, category, payee."
        },
        "consequence_tier": {
          "enum": [
            "low",
            "medium",
            "high",
            "critical"
          ],
          "type": "string"
        },
        "auth_freshness_sec": {
          "type": "number",
          "description": "Age in seconds of that authentication."
        }
      }
    }
    arguments 44 lines
  • arobi_route_grant unknown never probed

    Seal WHO granted WHAT authority to WHICH workflow, with scope, caps, attenuation and expiry. One grant authorises many later arobi_authorize decisions.

    mcp-tool

    {
      "type": "object",
      "required": [
        "route_id",
        "scope",
        "granted_by",
        "delegated_to"
      ],
      "properties": {
        "scope": {
          "type": "object",
          "description": "{ actions: string[], category_caps?: Record<string, number> }"
        },
        "route_id": {
          "type": "string"
        },
        "revocable": {
          "type": "boolean"
        },
        "expires_at": {
          "type": "string",
          "description": "ISO 8601."
        },
        "granted_by": {
          "type": "string"
        },
        "attenuation": {
          "type": "string",
          "description": "Plain-language limits carried with the grant."
        },
        "delegated_to": {
          "type": "string"
        }
      }
    }
    arguments 35 lines
  • arobi_classify_and_route unknown never probed

    Classify a prompt and choose the cheapest route CAPABLE of the work from your candidate set, reporting whether any cost above the cheapest capable route is justified by a named required capability, by measured quality under your explicit quality_exception policy, or by nothing. Also reports whether this work was already done. Set record=false to preview without writing to your ledger.

    mcp-tool

    {
      "type": "object",
      "required": [
        "prompt",
        "candidates"
      ],
      "properties": {
        "prompt": {
          "type": "string"
        },
        "record": {
          "type": "boolean",
          "description": "Default true. false = answer without sealing."
        },
        "candidates": {
          "type": "array",
          "description": "Routes with cost_per_1k_prompt_usd, cost_per_1k_completion_usd, capabilities, observed_success_rate, observed_sample_size."
        },
        "quality_exception": {
          "type": "object",
          "required": [
            "min_success_uplift",
            "min_sample_size"
          ],
          "properties": {
            "max_premium_usd": {
              "type": "number"
            },
            "min_sample_size": {
              "type": "integer"
            },
            "min_success_uplift": {
              "type": "number"
            }
          },
          "description": "Optional. The only way a dearer route is chosen: its measured success must beat the cheapest capable route by min_success_uplift (0-1] with at least min_sample_size recorded runs on each side, optionally capped by max_premium_usd."
        },
        "required_capabilities": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      }
    }
    arguments 45 lines
  • arobi_verify_chain unknown never probed

    Recompute a set of sealed spine records and report whether the hash chain is continuous, which record breaks it, and why. Verification only — it re-derives, it does not re-execute.

    mcp-tool

    {
      "type": "object",
      "required": [
        "records"
      ],
      "properties": {
        "records": {
          "type": "array",
          "description": "Sealed records in order."
        }
      }
    }
    arguments 12 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 b49e6b0a264cb8a4.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/b49e6b0a264cb8a4/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/b49e6b0a264cb8a4/badge.svg)](https://brick.blue/agent/b49e6b0a264cb8a4?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
80%

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.