_ registry / mcp streamable-http · checked 13h ago

truce

https://trucehq.com

Registry code: 8ff65d4ccdebec9e

api record

Truce settles disagreements the friendly way: each side tells a neutral AI mediator their side in private, Truce proposes something fair, and both sign. Free when no money is involved; for money disputes each side pays a small flat fee only if both sign. Use start_whos_right for light, everyday arguments (chores, whose turn, small things) and start_truce for real disagreements (deposits, unpaid invoices, money between friends, flatmates, neighbours, business partners). Do not use Truce for abuse, violence, threats, a child's safety or crimes: point the user to qualified help instead. If your…

endpoint
https://trucehq.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 truce live?
Yes — it answered the hub's last check (checked 13h ago). It answered 100% of checks over the last 30 days.
Is truce free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does truce have?
7 tools: start_truce, start_whos_right, get_invite, answer_truce, answer_whos_right, get_whos_right_status, get_truce_status.
Is truce 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
496ms

last good check

priced tools
0

of 7 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

_ what it can do 7 tools
1 open1 auth-required 5 never probed 2 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.

  • get_whos_right_status open 13h ago

    Check whether the other person has answered a Who's right?, and the verdict if so.

    mcp-tool

    {
      "type": "object",
      "required": [
        "code"
      ],
      "properties": {
        "code": {
          "type": "string",
          "description": "The code at the end of invite_url."
        }
      }
    }
    arguments 12 lines
  • get_truce_status auth-required 13h ago

    Check a Truce your user started: whether the other side joined, the proposal, and whether both signed. Needs the private token from the private_url (the part after /t/).

    mcp-tool

    {
      "type": "object",
      "required": [
        "token"
      ],
      "properties": {
        "token": {
          "type": "string",
          "description": "The private token from private_url."
        }
      }
    }
    arguments 12 lines
  • start_truce unknown never probed

    Start a Truce (neutral, private mediation) for your user about a real disagreement. Returns an invite link for your user to send to the other person, and a private link for your user. Free unless money is involved.

    mcp-tool

    {
      "type": "object",
      "required": [
        "topic",
        "name",
        "statement",
        "wants"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "Your user's first name."
        },
        "email": {
          "type": "string",
          "description": "Optional: your user's email for updates."
        },
        "floor": {
          "type": "string",
          "description": "Optional, private: the least your user could accept. Never shown to the other side."
        },
        "olive": {
          "type": "string",
          "description": "Optional short, kind note to the other person."
        },
        "topic": {
          "type": "string",
          "description": "What the disagreement is about, in a few neutral words."
        },
        "wants": {
          "type": "string",
          "description": "What your user would like to happen."
        },
        "category": {
          "type": "string",
          "description": "Optional: deposit, invoice, flatmates, neighbours, friends, business, family or other."
        },
        "otherName": {
          "type": "string",
          "description": "The other person's first name."
        },
        "statement": {
          "type": "string",
          "description": "Your user's side, in their words."
        }
      }
    }
    arguments 47 lines
  • start_whos_right unknown never probed

    Start a free, friendly 'Who's right?' for a light everyday argument. Your user gives their side; the other person gives theirs in private; both get a neutral, good-humoured verdict and a fair middle ground.

    mcp-tool

    {
      "type": "object",
      "required": [
        "topic",
        "nameA",
        "nameB",
        "sideA"
      ],
      "properties": {
        "email": {
          "type": "string",
          "description": "Optional: your user's email."
        },
        "nameA": {
          "type": "string",
          "description": "Your user's first name."
        },
        "nameB": {
          "type": "string",
          "description": "The other person's first name."
        },
        "sideA": {
          "type": "string",
          "description": "Your user's side, in a few sentences."
        },
        "topic": {
          "type": "string",
          "description": "What the argument is about."
        }
      }
    }
    arguments 31 lines
  • get_invite unknown never probed

    For the agent of someone who received a Truce invite link (trucehq.com/claim/CODE): see who invited them, what about, and whether it is still open. Read-only.

    mcp-tool

    {
      "type": "object",
      "required": [
        "code"
      ],
      "properties": {
        "code": {
          "type": "string",
          "description": "The code at the end of the invite link."
        }
      }
    }
    arguments 12 lines
  • answer_truce unknown never probed

    For the agent of the invited person: give their side of the Truce, in private, so the neutral mediator can propose something fair. Only with their explicit consent to the exact words. They still read the proposal and sign themselves.

    mcp-tool

    {
      "type": "object",
      "required": [
        "code",
        "name",
        "statement",
        "wants",
        "consent"
      ],
      "properties": {
        "code": {
          "type": "string",
          "description": "The code at the end of the invite link."
        },
        "name": {
          "type": "string",
          "description": "Your user's first name."
        },
        "email": {
          "type": "string",
          "description": "Optional: your user's email for updates."
        },
        "floor": {
          "type": "string",
          "description": "Optional, private: the least your user could accept. Never shown to the other side."
        },
        "wants": {
          "type": "string",
          "description": "What your user would like to happen."
        },
        "consent": {
          "type": "boolean",
          "description": "Must be true: your user asked you to answer and agreed to these words."
        },
        "statement": {
          "type": "string",
          "description": "Your user's side, in their words."
        }
      }
    }
    arguments 40 lines
  • answer_whos_right unknown never probed

    For the agent of the other person in a Who's right? (trucehq.com/whos-right/CODE): give their side, with their consent. Returns the neutral, good-humoured verdict.

    mcp-tool

    {
      "type": "object",
      "required": [
        "code",
        "sideB",
        "consent"
      ],
      "properties": {
        "code": {
          "type": "string",
          "description": "The code at the end of the link."
        },
        "sideB": {
          "type": "string",
          "description": "Your user's side, in a few sentences."
        },
        "consent": {
          "type": "boolean",
          "description": "Must be true: your user asked you to answer and agreed to these words."
        }
      }
    }
    arguments 22 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 8ff65d4ccdebec9e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/8ff65d4ccdebec9e/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/8ff65d4ccdebec9e/badge.svg)](https://brick.blue/agent/8ff65d4ccdebec9e?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.