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

errand

https://errand.be

Registry code: cd97532a5fff1e4e

api record

Errand is a physical-world execution layer for AI agents in Seoul (Gangnam beta). Use it when a user needs eyes, hands, or physical presence at a real place: on-site verification, store/shelf/price/open-hours checks, photos, queue checks or holding, and pickups. Do not use Errand for purely digital tasks. Safe flow: list_capabilities → check_coverage → quote → present total_charge_krw and obtain explicit user confirmation → dispatch → poll get_status → get_result. Rewards are KRW; dispatch escrows reward plus platform fee, and failure/expiry/pre-acceptance cancellation refunds in full. Never…

endpoint
https://errand.be/api/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 errand live?
Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
Is errand 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 errand have?
7 tools: errand_list_capabilities, errand_get_status, errand_check_coverage, errand_get_result, errand_quote, errand_dispatch, errand_cancel.
Is errand 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
98.9%

90 days 97.6%· all time 97.6%

latency
803ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 413 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • down → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • send a person to verify a physical location
  • check store prices or opening hours on site
  • get on-site photos
  • hold a place in a queue
  • arrange a pickup
takes → gives
text, payments → data, images
tools
5 reads1 changes data1 moves money
_ 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 auth-required 7 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.

  • errand_list_capabilities reads auth-required 9h ago

    Use before a local-human or physical-world task to see what Errand can do for this account: supported on-site task types (check, verify, photograph, queue, pickup), spend caps, allowed area, KRW balance, and pricing. Read-only.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • errand_get_status reads auth-required 2h ago

    Track a previously dispatched local human task: open · accepted · arrived · submitted · completed · failed · cancelled · expired, plus its event timeline. Use after errand_dispatch while the person is traveling or working on site.

    mcp-tool

    {
      "type": "object",
      "required": [
        "dispatch_id"
      ],
      "properties": {
        "dispatch_id": {
          "type": "string",
          "description": "Id returned by errand_dispatch."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • errand_check_coverage reads auth-required 9h ago

    Check whether a nearby human can be dispatched to a physical location before spending. Returns reachable_workers (switched on, seen within 24h — these get the push) and online_workers (app open this minute). Use for on-site or store checks, photos, queues, pickups, and other real-world tasks when you need current human availability.

    mcp-tool

    {
      "type": "object",
      "required": [
        "lat",
        "lng"
      ],
      "properties": {
        "lat": {
          "type": "number"
        },
        "lng": {
          "type": "number"
        },
        "radius_m": {
          "type": "integer",
          "maximum": 10000,
          "minimum": 100,
          "description": "Default 3000."
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
  • errand_get_result reads auth-required 9h ago

    Retrieve the verified on-site result from a human task: pass/fail verdict, score and feedback, signed photo URLs, structured answers, and evidence provenance including GPS distance, capture time, and server checks. Also returns share_url: a read-only result page (valid 30 days, no login) you can send to the person who asked for the check.

    mcp-tool

    {
      "type": "object",
      "required": [
        "dispatch_id"
      ],
      "properties": {
        "dispatch_id": {
          "type": "string",
          "description": "Id returned by errand_dispatch."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • errand_quote reads auth-required 2h ago

    Get the exact read-only quote for sending a human to a real-world location for a check, verification, photo, queue task, or pickup. Validates account caps, live worker coverage, and balance; returns reward_krw, platform_fee_krw, and exact total_charge_krw. Present that total to the user and obtain explicit confirmation before errand_dispatch.

    mcp-tool

    {
      "type": "object",
      "required": [
        "task_type",
        "lat",
        "lng",
        "reward_krw"
      ],
      "properties": {
        "lat": {
          "type": "number"
        },
        "lng": {
          "type": "number"
        },
        "radius_m": {
          "type": "integer",
          "maximum": 10000,
          "minimum": 100,
          "description": "Default 3000."
        },
        "task_type": {
          "enum": [
            "verify",
            "photograph",
            "pickup",
            "queue",
            "check"
          ],
          "type": "string"
        },
        "reward_krw": {
          "type": "integer",
          "maximum": 200000,
          "minimum": 1000
        }
      },
      "additionalProperties": false
    }
    arguments 39 lines
  • errand_dispatch moves money auth-required never probed

    Send a nearby real human to a physical location for on-site verification, store/shelf/price checks, photos, queue checks or holding, or a pickup. This spends money and creates a real-world action: call errand_quote first, present its exact total_charge_krw, and obtain explicit user confirmation. The worker travels to the site, completes the instructions, and submits GPS/time-verified in-app evidence. Completed tasks pay the worker; failed, expired, or pre-acceptance cancelled tasks refund escrow.

    mcp-tool

    {
      "type": "object",
      "required": [
        "task_type",
        "title",
        "instructions",
        "validation_criteria",
        "lat",
        "lng",
        "radius_m",
        "reward_krw",
        "expires_in_minutes"
      ],
      "properties": {
        "lat": {
          "type": "number"
        },
        "lng": {
          "type": "number"
        },
        "title": {
          "type": "string",
          "description": "Short worker-facing title, e.g. \"성수동 XYZ 팝업 대기줄 확인\"."
        },
        "radius_m": {
          "type": "integer",
          "maximum": 10000,
          "minimum": 100,
          "description": "Dispatch radius for worker matching."
        },
        "task_type": {
          "enum": [
            "verify",
            "photograph",
            "pickup",
            "queue",
            "check"
          ],
          "type": "string"
        },
        "reward_krw": {
          "type": "integer",
          "maximum": 200000,
          "minimum": 1000
        },
        "webhook_url": {
          "type": "string",
          "description": "HTTPS URL that receives mission.completed / mission.failed / mission.cancelled / mission.expired events, so you do not have to poll. Payload is advisory — confirm via errand_get_result."
        },
        "address_hint": {
          "type": "string",
          "description": "Human-readable place name/address shown to the worker."
        },
        "instructions": {
          "type": "string",
          "description": "Exactly what the worker should do on site, in the worker's language."
        },
        "report_fields": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "key",
              "label",
              "type"
            ],
            "properties": {
              "key": {
                "type": "string",
                "pattern": "^[a-z][a-z0-9_]{0,39}$"
              },
              "type": {
                "enum": [
                  "text",
                  "number"
                ],
                "type": "string"
              },
              "unit": {
                "type": "string",
                "description": "Unit shown beside the label, e.g. \"명\" or \"분\". Set it whenever the answer is a quantity: without it a worker asked for \"예상 대기 시간\" may reply \"11\" and you cannot tell minutes from people."
              },
              "label": {
                "type": "string",
                "description": "Worker-facing prompt in Korean, e.g. \"현재 대기 인원\"."
              },
              "placeholder": {
                "type": "string",
                "description": "Example answer shown in the empty field, e.g. \"약 40\"."
              }
            },
            "additionalProperties": false
          },
          "maxItems": 5,
          "description": "Structured values the worker must report from the site (e.g. how many people are waiting). Returned in the result and included in the webhook."
        },
        "expires_in_minutes": {
          "type": "integer",
          "maximum": 1440,
          "minimum": 10
        },
        "validation_criteria": {
          "type": "string",
          "description": "What the photos must show for the evidence to pass, e.g. \"매장 입구와 대기줄 전체가 한 프레임에 보여야 함\"."
        }
      },
      "additionalProperties": false
    }
    arguments 108 lines
  • errand_cancel changes data auth-required never probed

    Cancel a real-world human dispatch while it is still open and refund the escrow in full. Fails once a worker has accepted and may already be traveling.

    mcp-tool

    {
      "type": "object",
      "required": [
        "dispatch_id"
      ],
      "properties": {
        "dispatch_id": {
          "type": "string",
          "description": "Id returned by errand_dispatch."
        }
      },
      "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 cd97532a5fff1e4e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/cd97532a5fff1e4e/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/cd97532a5fff1e4e/badge.svg)](https://brick.blue/agent/cd97532a5fff1e4e?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
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.