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

getmydata

https://getmydata.io

Registry code: 38863aa222e567d7

api record

GetMyData: see the data before you pay. Public web data as rows from any public website, with a free sample first, then one fixed-price payment by the person; no signup or subscription. Read the Assistant skill and OpenAPI at the service origin for relevant use cases and the current contract. Explain capabilities without submitting a request; obtain user authorization before collection. Use Mcp-Session-Id for subsequent calls; every call within a session, including reads and replays, observes min_interval_seconds (default one second); honor Retry-After. Steps run asynchronously and the person…

endpoint
https://getmydata.io/mcp
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 getmydata live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is getmydata free to use?
Yes — the hub reached it with no key and no payment.
What tools does getmydata have?
16 tools: refresh_session, submit_requisition, revise_requisition, confirm_scope, confirm_quote, start_email_verification, verify_email, start_order, ….
Is getmydata 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
1,383ms

last good check

priced tools
0

of 16 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 16 tools
16 never probed 0 of 16 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.

  • refresh_session unknown never probed

    Before session expiry, renew using the current Mcp-Session-Id. Save the returned header/token. A session is valid for 7 days; each refresh extends it by up to 7 days, never beyond a hard lifetime of thirty days from initialization; request and delivery expiries do not change.

    mcp-tool

    {
  "type": "object",
  "required": [
    "idempotency_key"
  ],
  "properties": {
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • submit_requisition unknown never probed

    Request public web data as rows when browsing it yourself is impractical. Free sample first, one-off payment by the person, no signup or subscription. Collect every required field from the person first (sources, fields, filters, geo, row_target, deadline, language, description) and generate search_keywords yourself; missing or invalid fields are returned as error.missing/error.invalid (HTTP 422) and are not clarified by the service. The service is subject to applicable law. You are responsible for using the data lawfully and must not use the service for abuse such as harassment, spam or fraud. Do not send account passwords, cookies or session tokens. Save the returned request capability privately. The person must verify their email with a one-time code before the sample is shown (ask them to give you the code); sampling starts meanwhile. Then sampling runs asynchronously and every result is emailed to them.

    mcp-tool

    {
  "type": "object",
  "required": [
    "human_email",
    "sources",
    "fields",
    "filters",
    "geo",
    "row_target",
    "row_commitment",
    "deadline",
    "language",
    "description",
    "idempotency_key"
  ],
  "properties": {
    "geo": {
      "type": "string",
      "description": "Required; \"\" when not location-specific."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "filters": {
      "type": "object",
      "description": "Required; {} when none."
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Public page URLs or site names. Any public website is accepted when a collection method exists; otherwise the request ends with reason_code no_capability."
    },
    "deadline": {
      "type": "string",
      "description": "Required: ISO 8601 date-time or \"none\"."
    },
    "language": {
      "enum": [
        "en",
        "zh",
        "fr",
        "ru",
        "es",
        "ar",
        "de",
        "ja",
        "ko",
        "it"
      ],
      "type": "string",
      "description": "Required: the person’s language."
    },
    "channel_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_-]{0,63}$",
      "maxLength": 64,
      "description": "The first successful request freezes the session channel, including no channel. Subsequent requests inherit it; this grants no discounts. When omitted, the channel bound to coupon_code (if any) is used."
    },
    "dedup_keys": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Optional compound key of requested field names, all available in the confirmed sample. Empty means canonical whole-row deduplication.",
      "uniqueItems": true
    },
    "row_target": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 1
    },
    "coupon_code": {
      "type": "string",
      "description": "Optional single code applied when the quote is prepared; more codes go in coupon_codes on create_order."
    },
    "description": {
      "type": "string",
      "description": "Required: plain description of the data wanted and its purpose."
    },
    "human_email": {
      "type": "string"
    },
    "row_commitment": {
      "enum": [
        "best_effort",
        "guaranteed"
      ],
      "type": "string",
      "description": "best_effort (default to propose): as many as match, up to row_target. guaranteed: row_target rows; a shortfall keeps collecting until reached or cancelled (pro-rata refund of undelivered rows)."
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "search_keywords": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 80
      },
      "maxItems": 5,
      "description": "Optional hint only: up to five short phrases (platform or site type plus data type, e.g. \"app store reviews\", \"google maps places\"; do not put a specific app, product or brand name). GetMyData generates its own search for the collection method; these only inform it."
    },
    "prior_request_capability": {
      "type": "string",
      "description": "Optional valid capability for an accepted, positively paid prior request with the same email."
    }
  }
}
    arguments 116 lines
  • revise_requisition unknown never probed

    Revise an unpaid request using the current expected_revision with the full set of required fields. Existing samples and quotes are replaced. Use it when next_action is revise (including reason_code no_capability: try other sources or fields).

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "expected_revision",
    "idempotency_key",
    "sources",
    "fields",
    "filters",
    "geo",
    "row_target",
    "row_commitment",
    "deadline",
    "language",
    "description"
  ],
  "properties": {
    "geo": {
      "type": "string",
      "description": "Required; \"\" when not location-specific."
    },
    "fields": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "filters": {
      "type": "object",
      "description": "Required; {} when none."
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Public page URLs or site names. Any public website is accepted when a collection method exists; otherwise the request ends with reason_code no_capability."
    },
    "deadline": {
      "type": "string",
      "description": "Required: ISO 8601 date-time or \"none\"."
    },
    "language": {
      "enum": [
        "en",
        "zh",
        "fr",
        "ru",
        "es",
        "ar",
        "de",
        "ja",
        "ko",
        "it"
      ],
      "type": "string",
      "description": "Required: the person’s language."
    },
    "channel_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9_-]{0,63}$",
      "maxLength": 64,
      "description": "The first successful request freezes the session channel, including no channel. Subsequent requests inherit it; this grants no discounts. When omitted, the channel bound to coupon_code (if any) is used."
    },
    "dedup_keys": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 10,
      "description": "Optional compound key of requested field names, all available in the confirmed sample. Empty means canonical whole-row deduplication.",
      "uniqueItems": true
    },
    "request_id": {
      "type": "string"
    },
    "row_target": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 1
    },
    "coupon_code": {
      "type": "string",
      "description": "Optional single code applied when the quote is prepared; more codes go in coupon_codes on create_order."
    },
    "description": {
      "type": "string",
      "description": "Required: plain description of the data wanted and its purpose."
    },
    "human_email": {
      "type": "string"
    },
    "row_commitment": {
      "enum": [
        "best_effort",
        "guaranteed"
      ],
      "type": "string",
      "description": "best_effort (default to propose): as many as match, up to row_target. guaranteed: row_target rows; a shortfall keeps collecting until reached or cancelled (pro-rata refund of undelivered rows)."
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "search_keywords": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 80
      },
      "maxItems": 5,
      "description": "Optional hint only: up to five short phrases (platform or site type plus data type, e.g. \"app store reviews\", \"google maps places\"; do not put a specific app, product or brand name). GetMyData generates its own search for the collection method; these only inform it."
    },
    "expected_revision": {
      "type": "integer"
    },
    "request_capability": {
      "type": "string"
    },
    "prior_request_capability": {
      "type": "string",
      "description": "Optional valid capability for an accepted, positively paid prior request with the same email."
    }
  }
}
    arguments 127 lines
  • confirm_scope unknown never probed

    Confirm the current immutable sample_id and revision and request a fixed quote. The quote is prepared asynchronously and emailed to the person with the payment link; check get_request on a schedule, never in a loop. After the final quote, use start_order or create_order to read the confirmation link.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "expected_revision",
    "idempotency_key"
  ],
  "properties": {
    "sample_id": {
      "type": "string"
    },
    "request_id": {
      "type": "string"
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "expected_revision": {
      "type": "integer"
    },
    "request_capability": {
      "type": "string"
    }
  }
}
    arguments 28 lines
  • confirm_quote unknown never probed

    Record final quote confirmation for quote_id and revision. Use start_order next; start_order also records this selection if not already confirmed.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "quote_id",
    "expected_revision",
    "idempotency_key"
  ],
  "properties": {
    "quote_id": {
      "type": "string"
    },
    "request_id": {
      "type": "string"
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "expected_revision": {
      "type": "integer"
    },
    "request_capability": {
      "type": "string"
    }
  }
}
    arguments 29 lines
  • start_email_verification unknown never probed

    Send (or resend) the one-time code that verifies the person’s email for this request. Needed before the sample is shown (sampling itself starts at once), and again before payment if the verification is older than the re-verify window. human_email may be corrected only before it is verified. Use when next_action is start_email_verification (email_verification.state not_sent, unavailable, expired, replaced or attempts_exceeded after resend_after). Ask the person to give you the code and to check spam; if the state stays unavailable after requesting a new code once, ask them to contact [email protected]; this code email contains no price or link (the later quote email contains the private payment link).

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "idempotency_key"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "human_email": {
      "type": "string",
      "format": "email"
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "request_capability": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • verify_email unknown never probed

    Submit the code the person read from their email. A wrong code returns otp_invalid with attempts_remaining. On success the sample becomes visible once ready (or, at quote time, the order confirmation link is issued). Results are then emailed to the verified address; check get_request later instead of polling continuously.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "otp",
    "idempotency_key"
  ],
  "properties": {
    "otp": {
      "type": "string"
    },
    "request_id": {
      "type": "string"
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "request_capability": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • start_order unknown never probed

    Select the final quote and read the human confirmation link issued for the verified email (no second code). Save order_id and order_capability before passing confirmation_url to the person.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "quote_id",
    "expected_revision",
    "idempotency_key"
  ],
  "properties": {
    "quote_id": {
      "type": "string"
    },
    "request_id": {
      "type": "string"
    },
    "human_email": {
      "type": "string",
      "format": "email"
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "expected_revision": {
      "type": "integer"
    },
    "request_capability": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 34 lines
  • create_order unknown never probed

    Read or update the order for the final quote. Pass explicitly available renewal, referral or channel codes in coupon_codes before payment starts. Tell the person which codes were added and their valid/invalid status. Give confirmation_url to the person to review codes and pay themselves. Never submit payment for them. Save order_id and order_capability before passing confirmation_url to the person. After payment, use get_order even if the original session is lost.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "quote_id",
    "expected_revision",
    "idempotency_key"
  ],
  "properties": {
    "otp": {
      "type": "string",
      "description": "Deprecated; ignored."
    },
    "quote_id": {
      "type": "string"
    },
    "request_id": {
      "type": "string"
    },
    "coupon_codes": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "expected_revision": {
      "type": "integer"
    },
    "request_capability": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 40 lines
  • cancel_request unknown never probed

    Cancel an unpaid request and release unused coupons where payment has not started. Paid orders require support.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability",
    "expected_revision",
    "idempotency_key"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "expected_revision": {
      "type": "integer"
    },
    "request_capability": {
      "type": "string"
    }
  }
}
    arguments 25 lines
  • get_quote unknown 2h ago

    Read the quote or estimated waiting time, without payment credentials.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "request_capability": {
      "type": "string"
    }
  }
}
    arguments 15 lines
  • get_payment_status unknown never probed

    Check email verification, order creation and verified payment status. After payment, return this request’s coupon notifications and a separate delivery token when files are ready.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "request_capability": {
      "type": "string"
    }
  }
}
    arguments 15 lines
  • get_order unknown never probed

    Use the order_capability saved at order creation to read paid order status and obtain or renew a delivery token. It works with a new valid session if the original session expired; a current session is required. No email recovery; keep this credential private until file retention ends. After an original full refund, top-level add_on describes any separate purchase. If add_on.delivery_available is true, next_action is fetch_delivery and the renewed token can list/download only extra.* files; delivery.rows_url is null. The original refund status and original-file 410 remain unchanged.

    mcp-tool

    {
  "type": "object",
  "required": [
    "order_id",
    "order_capability"
  ],
  "properties": {
    "order_id": {
      "type": "string",
      "description": "Order number, e.g. GMD7K3P9Q. Lowercase or hyphenated input (gmd-7k3p9q) is accepted."
    },
    "order_capability": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • cancel_collection unknown never probed

    Only when the person explicitly asks: stop continued collection of a guaranteed-N order whose get_order status is collecting. Rows delivered so far stay available, the order settles as partial, and the undelivered share is refunded pro rata to the original payment method; the person is emailed. Tell them the refund amount shown in collection.refund first.

    mcp-tool

    {
  "type": "object",
  "required": [
    "order_id",
    "order_capability",
    "idempotency_key"
  ],
  "properties": {
    "order_id": {
      "type": "string",
      "description": "Order number, e.g. GMD7K3P9Q."
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 200,
      "minLength": 32
    },
    "order_capability": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • fetch_delivery unknown 2h ago

    After payment, use the delivery token to list files or read rows. Use json, csv, xlsx, fields.json, or rows pages; a paid excess-rows add-on has its own extra.json, extra.csv, extra.xlsx and extra.fields.json. XLSX is returned as base64 bytes with its content type. All rows pages for a file count once per token; a full download counts once each. On expiry or download_limit, call get_order with your order capability for a fresh token. A current session is required and the delivery token is bound to it. If the original session expired, initialize a new one and call get_order first.

    mcp-tool

    {
  "type": "object",
  "required": [
    "order_id",
    "delivery_token"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 1000,
      "minimum": 1
    },
    "format": {
      "enum": [
        "list",
        "rows",
        "json",
        "csv",
        "xlsx",
        "fields.json",
        "extra.json",
        "extra.csv",
        "extra.xlsx",
        "extra.fields.json"
      ],
      "type": "string"
    },
    "offset": {
      "type": "integer",
      "minimum": 0
    },
    "order_id": {
      "type": "string",
      "description": "Order number, e.g. GMD7K3P9Q. Lowercase or hyphenated input (gmd-7k3p9q) is accepted."
    },
    "delivery_token": {
      "type": "string"
    }
  }
}
    arguments 40 lines
  • get_request unknown 2h ago

    Read the current request, questions, sample and next action. After accepted payment, remind the customer about returned renewal/referral codes and expiry; pending codes are not ready. When next_action is wait, check again after suggested_check_after_seconds via a scheduled task if available; never loop. The person is emailed on every result.

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_id",
    "request_capability"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "request_capability": {
      "type": "string"
    }
  }
}
    arguments 15 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 38863aa222e567d7.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/38863aa222e567d7/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/38863aa222e567d7/badge.svg)](https://brick.blue/agent/38863aa222e567d7?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.