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

chn-mcp-server

https://mcp.changenow.io

Registry code: 8b2bf238ecb76d1d

api record

ChangeNOW is a non-custodial crypto exchange: the user sends one asset to a deposit address and receives another asset at an address they control. No account, no API key and no KYC for standard swaps. Nothing here takes custody of user funds and no tool moves money on its own.

Assets are identified by a canonical id "ticker.network", for example btc.btc, usdt.trx, usdc.sol. The same ticker exists on several networks, and sending to the wrong network loses the funds, so always resolve what the user named with list_assets before quoting anything.

endpoint
https://mcp.changenow.io/mcp
protocol
http-sse ·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 chn-mcp-server live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is chn-mcp-server free to use?
Yes — the hub reached it with no key and no payment.
What tools does chn-mcp-server have?
7 tools: list_assets, get_asset, validate_address, create_swap, check_swap_status, quote_swap, swap_link.
Is chn-mcp-server 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
99.5%

90 days 99.4%· all time 99.4%

latency
191ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 341 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
used for
  • quote a crypto swap
  • create a swap order
  • check swap status
  • validate a crypto address
takes → gives
text → data
tools
6 reads1 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

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 7 tools
7 never probed 0 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.

  • list_assets reads unknown never probed

    Find the assets ChangeNOW can exchange and turn what the user said into a canonical asset id. Search by ticker, name or network, filter by network, by fiat or crypto, and by whether a fixed rate is possible. Always call this before quoting: the same ticker exists on several networks and only the canonical id "ticker.network" identifies one of them. When has_more is false the response is the complete answer and no paging is needed.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "q": {
          "type": "string",
          "description": "Substring search over canonical id, legacy ticker, name and network. Case insensitive. Example: \"usdt\", \"bitcoin\", \"tron\"."
        },
        "kind": {
          "enum": [
            "crypto",
            "fiat",
            "all"
          ],
          "type": "string",
          "default": "crypto",
          "description": "crypto for swappable coins and tokens, fiat for currencies that can only start a purchase, all for both."
        },
        "limit": {
          "type": "integer",
          "default": 50,
          "maximum": 500,
          "minimum": 1,
          "description": "How many assets to return. Default 50, maximum 500."
        },
        "cursor": {
          "type": "string",
          "description": "Cursor from next_cursor of the previous page. Only needed when has_more is true."
        },
        "network": {
          "type": "string",
          "description": "Keep only assets on this network, for example \"eth\", \"trx\", \"sol\"."
        },
        "popular": {
          "type": "boolean",
          "default": false,
          "description": "Return the short curated list. Use this to answer \"what can I swap\" without paging."
        },
        "fixed_rate": {
          "type": "boolean",
          "default": false,
          "description": "Keep only assets the catalogue flags as fixed rate capable. The flag is a hint: a pair flagged false can still get a fixed rate, so confirm with quote_swap rather than filtering a user out."
        }
      },
      "additionalProperties": false
    }
    arguments 45 lines
  • get_asset reads unknown never probed

    Everything needed to build a swap for one asset: the canonical id, the legacy ticker used in website links, decimals, whether a memo is required and what the receiving side calls it, the address format, the token contract and the warnings to relay to the user. Minimum and maximum amounts are not here because they belong to the pair, not to the asset: get them from quote_swap.

    mcp-tool

    {
      "type": "object",
      "required": [
        "asset"
      ],
      "properties": {
        "asset": {
          "type": "string",
          "description": "Canonical id \"usdt.trx\". A legacy ticker \"usdttrc20\" or a page slug \"tether-trc20\" is also accepted."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • validate_address reads unknown never probed

    Check a recipient address, and its memo when the asset needs one, against the format the network requires, before any order exists. Call this on every address the user gives. A valid-looking address on the wrong network is the one mistake in a swap that destroys the funds with no way back, so when the address belongs to another network the answer names that network instead of just refusing. A few assets carry no address format in the catalogue; for those the answer says the address could not be checked rather than calling it valid.

    mcp-tool

    {
      "type": "object",
      "required": [
        "asset",
        "address"
      ],
      "properties": {
        "memo": {
          "type": "string",
          "description": "Memo or destination tag, when the asset needs one."
        },
        "asset": {
          "type": "string",
          "description": "Asset that will be received at this address, canonical id."
        },
        "address": {
          "type": "string",
          "description": "Recipient address to check."
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
  • create_swap moves money unknown never probed

    Create a real swap order and return the deposit address the user has to send funds to. This call moves no money by itself, but the order is real: it exists in support, it can expire, and a fixed rate is locked against it. Quote the swap first, validate the recipient address, and confirm the amount and the address with the user before calling this. If the user has not explicitly approved both, use swap_link instead and let them confirm on the page. The answer names who executes the order, and that has to be relayed: some orders are routed to a partner aggregator rather than ChangeNOW.

    mcp-tool

    {
      "type": "object",
      "required": [
        "from",
        "to",
        "address"
      ],
      "properties": {
        "to": {
          "type": "string",
          "description": "Asset the user receives, canonical id, for example \"usdt.trx\"."
        },
        "from": {
          "type": "string",
          "description": "Asset the user sends, canonical id, for example \"eth.eth\"."
        },
        "memo": {
          "type": "string",
          "description": "Memo or destination tag for the recipient address, when the asset needs one."
        },
        "address": {
          "type": "string",
          "description": "Address that receives the swapped asset. Check it with validate_address first; a wrong network here loses the funds."
        },
        "rate_id": {
          "type": "string",
          "description": "The rate_id from quote_swap with rate_type \"fixed\". Required for a fixed rate order. It holds for about two minutes, so quote again right before this call if the user needed time to decide."
        },
        "amount_to": {
          "type": "string",
          "description": "Amount the user wants to receive. Requires rate_id from quote_swap."
        },
        "promo_code": {
          "type": "string",
          "description": "Promo code to apply, if the user has one."
        },
        "amount_from": {
          "type": "string",
          "description": "Amount the user sends. Pass this or amount_to, never both."
        },
        "refund_memo": {
          "type": "string",
          "description": "Memo for the refund address."
        },
        "contact_email": {
          "type": "string",
          "format": "email",
          "pattern": "^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
          "description": "Optional email for status notifications about this order."
        },
        "refund_address": {
          "type": "string",
          "description": "Where the deposit returns if the swap cannot complete. Strongly recommended: without it a failed swap needs support."
        }
      },
      "additionalProperties": false
    }
    arguments 57 lines
  • check_swap_status reads unknown 9h ago

    Follow an existing order by id: where it stands, what the deposit and payout amounts turned out to be, the transaction hashes, and a plain-language explanation of what the current stage means and what happens next. Use it after create_swap, and again whenever the user asks where their swap is.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "Order id returned by create_swap."
        },
        "sub_id": {
          "type": "string",
          "description": "Sub order id, for an order the provider split in two."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • quote_swap reads unknown 9h ago

    Ask what a swap would give, in either direction: pass amount_from to learn what the user receives, or amount_to to learn what the user must send. Returns the rate, the pair minimum and maximum, who would execute the order, and the warnings to relay. With rate_type "fixed" it also returns the rate_id that create_swap needs; that lock lasts about two minutes, so quote again right before creating the order. A fixed rate is not offered on every pair and the tool says so rather than quietly falling back to a float rate. Nothing is created and no funds move.

    mcp-tool

    {
      "type": "object",
      "required": [
        "from",
        "to"
      ],
      "properties": {
        "to": {
          "type": "string",
          "description": "Asset the user receives, canonical id, for example \"usdt.trx\"."
        },
        "from": {
          "type": "string",
          "description": "Asset the user sends, canonical id, for example \"btc.btc\"."
        },
        "amount_to": {
          "type": "string",
          "description": "Amount the user wants to receive, as a decimal string. The answer then says how much to send."
        },
        "rate_type": {
          "enum": [
            "float",
            "fixed"
          ],
          "type": "string",
          "default": "float",
          "description": "float: the rate is settled when the deposit arrives. fixed: the rate is held until valid_until, about two minutes, and returns the rate_id create_swap needs, usually at a slightly worse rate. Ask for fixed whenever the user wants a guaranteed number; if this pair cannot hold one the answer says so instead of quietly returning a float rate."
        },
        "promo_code": {
          "type": "string",
          "description": "Promo code to apply, if the user has one."
        },
        "amount_from": {
          "type": "string",
          "description": "Amount the user sends, as a decimal string. Pass this or amount_to, never both."
        }
      },
      "additionalProperties": false
    }
    arguments 39 lines
  • swap_link reads unknown 9h ago

    Build a changenow.io link with the pair, the amount, the recipient address and the memo already filled in, so the user checks the numbers on the real page and presses Confirm themselves. Opening the link creates nothing. This is the recommended way to finish a swap: the user sees the rate and the address with their own eyes, which no amount of care in a chat transcript can replace. Use create_swap instead only when the user has explicitly approved this exact amount and address.

    mcp-tool

    {
      "type": "object",
      "required": [
        "from",
        "to"
      ],
      "properties": {
        "to": {
          "type": "string",
          "description": "Asset the user receives, canonical id."
        },
        "from": {
          "type": "string",
          "description": "Asset the user sends, canonical id."
        },
        "memo": {
          "type": "string",
          "description": "Memo or destination tag to prefill."
        },
        "locale": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Two letter locale for the page, for example \"es\". English needs no locale."
        },
        "address": {
          "type": "string",
          "description": "Recipient address to prefill. The user can still change it on the page."
        },
        "amount_to": {
          "type": "string",
          "description": "Amount to prefill as the amount received. Implies a fixed rate on the page."
        },
        "rate_type": {
          "enum": [
            "float",
            "fixed"
          ],
          "type": "string",
          "default": "float",
          "description": "Which rate the page opens with."
        },
        "amount_from": {
          "type": "string",
          "description": "Amount to prefill as the amount sent."
        },
        "refund_address": {
          "type": "string",
          "description": "Refund address to prefill."
        }
      },
      "additionalProperties": false
    }
    arguments 53 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 8b2bf238ecb76d1d.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/8b2bf238ecb76d1d/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/8b2bf238ecb76d1d/badge.svg)](https://brick.blue/agent/8b2bf238ecb76d1d?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.