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

Human Tasks by The2410

https://tasks.the2410.com

Registry code: 992da02226779e48

api record

Human Tasks by The2410 lets AI assistants order predefined fixed-price digital services that are delivered by people. Always start with search-services-tool for every new customer request: pass the task as written and 1-3 short English search phrases. Search results are candidates, not a guarantee that the task fits a package. Inspect a service with get-service-tool, compare the customer's task with the selected package and ask about unclear requirements. When the customer chooses a package, ask the service questions and call prepare-order-tool with the task, answers and contact details, then…

endpoint
https://tasks.the2410.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 Human Tasks by The2410 live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is Human Tasks by The2410 free to use?
Yes — the hub reached it with no key and no payment.
What tools does Human Tasks by The2410 have?
5 tools: search-services-tool, get-service-tool, prepare-order-tool, create-checkout-tool, send-feedback-tool.
Is Human Tasks by The2410 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
1,236ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 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

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 5 tools
5 never probed 0 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.

  • search-services-tool unknown 1h ago

    Finds predefined fixed-price services, delivered by people, for a customer's task. Use it when a customer describes a new task; it can be called again with other phrases. Pass the customer's full task in task, in any language. Also pass 1-3 short English phrases in queries, one per service the task needs, e.g. 'convert PDF bank statements to Excel'. Returns the 10 closest services with service_id, title, summary, score and starting prices with business-day delivery. Score only ranks candidates; it is not a delivery guarantee. Use get-service-tool to inspect scope and requirements before recommending a package. This tool does not create an order or change the catalog.

    mcp-tool

    {
      "type": "object",
      "required": [
        "task"
      ],
      "properties": {
        "task": {
          "type": "string",
          "description": "The customer's task as written, in any language: desired result, platform, constraints. At most 8000 UTF-8 bytes."
        },
        "queries": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "1-3 short English search phrases, one per needed service. Strongly recommended, especially when the task is not in English."
        }
      }
    }
    arguments 19 lines
  • get-service-tool unknown 1h ago

    Read one active The2410 microservice using a service_id returned by search-services-tool, e.g. svc_8f3k2m9qxa. Returns content, scope with exclusions, buyer requirements, questions_before_order with ids, attributes, and all packages with their IDs, prices, currencies and delivery estimates in business days. Compare package requirements and scope with the customer's task before selecting a package. To order, pass the chosen package and answers to prepare-order-tool. This tool does not create an order, collect payment, or call an AI provider.

    mcp-tool

    {
      "type": "object",
      "required": [
        "service_id"
      ],
      "properties": {
        "service_id": {
          "type": "string",
          "description": "The service_id returned by search-services-tool, e.g. svc_8f3k2m9qxa. Not a package ID."
        }
      }
    }
    arguments 12 lines
  • prepare-order-tool unknown never probed

    Create or update a draft order for one package of a The2410 microservice. Use after get-service-tool, once the customer has chosen a package. Pass the customer's task, answers to questions_before_order by question id, and contact details. To change or complete a draft, call again with the returned order_id. Returns the order summary: price (net), delivery, deliverables, exclusions, unanswered questions, and what the customer will be asked to provide by email after payment. Do not pass passwords or access credentials. This tool does not charge the customer or notify The2410.

    mcp-tool

    {
      "type": "object",
      "required": [
        "service_id",
        "package_id",
        "task",
        "contact"
      ],
      "properties": {
        "task": {
          "type": "string",
          "description": "What exactly should be done, in the customer's words: website or account URL, platform, priorities, constraints. Covers buyer_inputs. At most 8000 characters."
        },
        "answers": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "id",
              "answer"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Question id from questions_before_order, e.g. q1."
              },
              "answer": {
                "type": "string",
                "description": "The customer's answer. Use \"unknown\" if the customer does not know."
              }
            }
          },
          "description": "Answers to questions_before_order. Every question must be answered before checkout."
        },
        "contact": {
          "type": "object",
          "required": [
            "name",
            "email"
          ],
          "properties": {
            "name": {
              "type": "string",
              "description": "The customer's full name."
            },
            "email": {
              "type": "string",
              "description": "The customer's email address. Order updates and access requests are sent here."
            },
            "phone": {
              "type": "string",
              "description": "The customer's phone number."
            },
            "company": {
              "type": "string",
              "description": "The customer's company name, if buying for a company."
            }
          },
          "description": "Customer contact details. Name and email are required."
        },
        "order_id": {
          "type": "string",
          "description": "The order_id of an existing draft to update, e.g. ord_8f3k2m9qxa. Omit to create a new order."
        },
        "package_id": {
          "type": "integer",
          "description": "The id of the chosen package from get-service-tool."
        },
        "service_id": {
          "type": "string",
          "description": "The service_id from search-services-tool or get-service-tool, e.g. svc_8f3k2m9qxa."
        }
      }
    }
    arguments 74 lines
  • create-checkout-tool unknown never probed

    Send a prepared order to checkout and return the payment link. Call only after the customer has seen the prepare-order-tool summary and explicitly confirmed it. All questions must be answered first. The customer opens checkout_url and pays themselves; billing address, VAT ID and taxes are handled by Stripe. The link is valid for 24 hours. Repeated calls return the same link while it is valid, or a new one after it expires. After this call the order can no longer be changed.

    mcp-tool

    {
      "type": "object",
      "required": [
        "order_id"
      ],
      "properties": {
        "order_id": {
          "type": "string",
          "description": "The order_id returned by prepare-order-tool, e.g. ord_8f3k2m9qxa."
        }
      }
    }
    arguments 12 lines
  • send-feedback-tool unknown never probed

    Send feedback to The2410 team: a problem, a suggestion, praise or any other message about this MCP server, an order or a project. Use only when the customer wants to share feedback. Show the message to the customer and send it after they confirm. Name and email are optional; include them if the customer wants a reply. If the feedback is about a specific project or order, add the project_context_id or order_id returned by an earlier call. Never include passwords, access details or payment card data.

    mcp-tool

    {
      "type": "object",
      "required": [
        "message"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "Optional customer name."
        },
        "type": {
          "enum": [
            "bug",
            "suggestion",
            "praise",
            "other"
          ],
          "type": "string",
          "description": "Feedback type. Default: other."
        },
        "email": {
          "type": "string",
          "description": "Optional customer email, if the customer wants a reply."
        },
        "message": {
          "type": "string",
          "description": "The feedback text, in the customer's words."
        },
        "order_id": {
          "type": "string",
          "description": "Optional order id of a fixed-price service order, e.g. ord_8f3k2m9qxa."
        },
        "project_context_id": {
          "type": "string",
          "description": "Optional project context UUID returned by a previous tool call."
        }
      }
    }
    arguments 38 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 992da02226779e48.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/992da02226779e48/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/992da02226779e48/badge.svg)](https://brick.blue/agent/992da02226779e48?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.

_ also on the2410.com 1 entry

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.