_ registry / mcp streamable-http · checked 5h ago

disputes-online

https://disputes.online

Registry code: 1cfcf9797915ab1c

api record

disputes.online is a social prediction platform. People open "disputes" — questions about real-world events with two or more outcomes — and stake the platform's internal currency, QOT, on the outcome they expect.

Reading the numbers:

endpoint
https://disputes.online/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 disputes-online live?
Yes — it answered the hub's last check (checked 5h ago). It answered 100% of checks over the last 30 days.
Is disputes-online free to use?
Yes — the hub reached it with no key and no payment.
What tools does disputes-online have?
4 tools: get_dispute, search_disputes, search_disputes_by_tags, list_categories.
Is disputes-online 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
476ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 258 checks · signed record
  • unknown → live
_ what it is for
used for
  • search open prediction disputes
  • get dispute outcomes and odds
  • find disputes by tag
  • list dispute categories
takes → gives
text → data
tools
4 reads
_ 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
1 open 3 never probed 1 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.

  • list_categories reads open 23h ago

    List the categories disputes on disputes.online are filed under, as a flat tree. Use it to find the category_id for a topic before calling search_disputes.

    mcp-tool

    {
      "type": "object",
      "additionalProperties": false
    }
    arguments 4 lines
  • get_dispute reads unknown never probed

    Get one dispute from disputes.online by its id or page URL: the question, how it will be decided, the outcomes, how the stakes are split between them, and the deadlines. Also finds a dispute that has already been settled and returns which outcome won next to how the crowd had bet — use it to check a past prediction.

    mcp-tool

    {
      "type": "object",
      "required": [
        "dispute"
      ],
      "properties": {
        "dispute": {
          "type": "string",
          "description": "the dispute's id (UUID) or the URL of its page on disputes.online"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • search_disputes reads unknown never probed

    Find disputes on disputes.online that are open to bets, with each outcome's share of the stakes. Search by free text with query (a topic, a person, a team, an asset), filter by language, category, country and creation date, and sort by pool size, number of bets, newest or closing time. This is the tool for finding what people are predicting about something, what the crowd thinks the odds are, and what was opened recently — for yesterday's disputes pass yesterday's date as both created_from and created_to.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "lang": {
          "type": "string",
          "description": "two-letter language code of the disputes to return: en, ua (Ukrainian), pl, de and so on. Defaults to en. Disputes marked all are always included."
        },
        "sort": {
          "type": "string",
          "description": "amount (largest pool first; the default), bets (most bets first), newest (most recently created first), closing_soon (betting closes soonest first), result_soon (result due soonest first)"
        },
        "limit": {
          "type": "integer",
          "description": "page size, 1 to 20; defaults to 10"
        },
        "query": {
          "type": "string",
          "description": "free text to look for, for example bitcoin or trump impeachment. A dispute matches when every word occurs in its text or among its tags; fewer words find more. Leave empty to list everything."
        },
        "offset": {
          "type": "integer",
          "description": "number of disputes to skip, for paging"
        },
        "country": {
          "type": "string",
          "description": "ISO 3166-1 alpha-2 code of the country the dispute is about, for example US"
        },
        "created_to": {
          "type": "string",
          "description": "only disputes created at or before this moment, UTC. Either a day, 2026-10-07 (through the end of that day), or a full timestamp. For one day's disputes pass the same day as created_from and created_to."
        },
        "category_id": {
          "type": "integer",
          "description": "only disputes in this category or any category below it; ids come from list_categories"
        },
        "created_from": {
          "type": "string",
          "description": "only disputes created at or after this moment, UTC. Either a day, 2026-10-07 (from the start of that day), or a full timestamp, 2026-10-07T12:00:00Z."
        }
      },
      "additionalProperties": false
    }
    arguments 42 lines
  • search_disputes_by_tags reads unknown never probed

    List open disputes on disputes.online that carry every one of the given tags, spelled exactly. Tags are set by a dispute's author, many disputes have none, and their spelling is arbitrary — to find disputes about a subject, use search_disputes with query instead. Use this only when you already know the exact tag.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tags"
      ],
      "properties": {
        "lang": {
          "type": "string",
          "description": "two-letter language code of the disputes to return; defaults to en"
        },
        "tags": {
          "type": [
            "null",
            "array"
          ],
          "items": {
            "type": "string"
          },
          "description": "one or more tags; a dispute matches only if it carries every one of them, spelled exactly. Tags are single lowercase words, for example politics or usa."
        },
        "limit": {
          "type": "integer",
          "description": "page size, 1 to 20; defaults to 10"
        },
        "offset": {
          "type": "integer",
          "description": "number of disputes to skip, for paging"
        }
      },
      "additionalProperties": false
    }
    arguments 31 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 1cfcf9797915ab1c.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/1cfcf9797915ab1c/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/1cfcf9797915ab1c/badge.svg)](https://brick.blue/agent/1cfcf9797915ab1c?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.