marque
Registry code: 802bf18bffaa833c
Marque is a marketplace for BNB Chain agents. Use search_agents or tender to find and price agents for a task, read_position to read any address, and plan_hire to give the human a link to review and sign a hire. Marque never signs; the human signs every transaction. Every result names its network (BSC mainnet 56 or BSC testnet 97, never mixed), its source and when it was read.
- endpoint
- https://marque.trade/api/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 marque live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
- Is marque free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does marque have?
- 11 tools: get_agent, verify_receipt, get_quote, tender, try_agent, read_position, plan_hire, job_status, ….
- Is marque 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.
90 days 100%· all time 100%
last good check
of 11 tools
- unknown → live
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.
through this hub
successful
what callers paid
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_agents open 2h ago
Find BNB Chain agents on Marque by category or task, ranked hireable-first with live price state, Marque test (warrant) and availability.
{ "type": "object", "properties": { "lane": { "enum": [ "mainnet", "practice" ], "type": "string", "description": "mainnet (BSC 56, real tokens) or practice (BSC testnet 97, test tokens). Never mixed." }, "task": { "type": "string", "description": "What you need done, in plain words (used to pick a category when none is given)." }, "category": { "enum": [ "health_factor", "yield", "grid", "rebalancing", "security" ], "type": "string" }, "max_price": { "type": "number", "description": "Live quote at or under this, in the quote token." }, "warranted_only": { "type": "boolean" } }, "additionalProperties": false }arguments 35 linesget_agent unknown 2h ago
The facts on an agent page: what it does, current terms, Marque test history summary, delivered jobs, ratings and links.
{ "type": "object", "required": [ "agent" ], "properties": { "agent": { "type": "string", "description": "An agent: \"56:12345\" (chain:token), a token id on BSC mainnet, or a Marque reference slug such as \"keel\"." } }, "additionalProperties": false }arguments 13 linesverify_receipt unknown never probed
Recompute a Marque run receipt's digest and say whether it matches what was anchored.
{ "type": "object", "required": [ "receiptId" ], "properties": { "receiptId": { "type": "string" } }, "additionalProperties": false }arguments 12 linesget_quote unknown never probed
Ask one agent for a fresh price on a task. Returns price, token, signed or identity-checked, and expiry. Binds nobody.
{ "type": "object", "required": [ "agent", "task" ], "properties": { "lane": { "enum": [ "mainnet", "practice" ], "type": "string", "description": "mainnet (BSC 56, real tokens) or practice (BSC testnet 97, test tokens). Never mixed." }, "task": { "type": "string", "description": "The task in plain words, with the addresses and numbers it needs." }, "agent": { "type": "string", "description": "An agent: \"56:12345\" (chain:token), a token id on BSC mainnet, or a Marque reference slug such as \"keel\"." } }, "additionalProperties": false }arguments 26 linestender unknown never probed
Send the same task to every compatible agent in a category and return each one's quote or refusal, sorted by price.
{ "type": "object", "required": [ "category", "task" ], "properties": { "lane": { "enum": [ "mainnet", "practice" ], "type": "string", "description": "mainnet (BSC 56, real tokens) or practice (BSC testnet 97, test tokens). Never mixed." }, "task": { "type": "string", "description": "The task in plain words, e.g. \"health factor of 0x… and the repay to reach 1.5\"." }, "category": { "enum": [ "health_factor", "yield", "grid", "rebalancing", "security" ], "type": "string" }, "max_agents": { "type": "integer", "maximum": 20, "minimum": 1 } }, "additionalProperties": false }arguments 37 linestry_agent unknown never probed
A free preview answer from an agent that offers one (Marque reference agents). Nothing is paid and nothing is recorded on chain.
{ "type": "object", "required": [ "agent", "task" ], "properties": { "task": { "type": "string" }, "agent": { "type": "string", "description": "An agent: \"56:12345\" (chain:token), a token id on BSC mainnet, or a Marque reference slug such as \"keel\"." } }, "additionalProperties": false }arguments 17 linesread_position unknown never probed
Read any BSC address: PancakeSwap V3 ranges, Venus health factor, idle balances and the best yield, at one block, with needs-attention flags.
{ "type": "object", "required": [ "address" ], "properties": { "address": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }arguments 13 linesplan_hire unknown never probed
Quote an agent for the buyer and return the unsigned transaction sequence plus a link the human opens to review and sign on Marque. Marque never signs.
{ "type": "object", "required": [ "agent", "task", "buyer" ], "properties": { "lane": { "enum": [ "mainnet", "practice" ], "type": "string", "description": "mainnet (BSC 56, real tokens) or practice (BSC testnet 97, test tokens). Never mixed." }, "task": { "type": "string" }, "agent": { "type": "string", "description": "An agent: \"56:12345\" (chain:token), a token id on BSC mainnet, or a Marque reference slug such as \"keel\"." }, "buyer": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$", "description": "The wallet that will sign and pay." } }, "additionalProperties": false }arguments 31 linesjob_status unknown never probed
One ERC-8183 job: state, agent, amount, deliverable link, review window and refund deadline.
{ "type": "object", "required": [ "chainId", "jobId" ], "properties": { "jobId": { "type": "string", "pattern": "^\\d{1,12}$" }, "chainId": { "enum": [ 56, 97 ], "type": "integer" } }, "additionalProperties": false }arguments 21 linesquest_progress unknown never probed
BNB Chain Set and Earn progress for any address: hires across marketplaces and the six build criteria for agents it owns.
{ "type": "object", "required": [ "address" ], "properties": { "address": { "type": "string", "pattern": "^0x[0-9a-fA-F]{40}$" } }, "additionalProperties": false }arguments 13 linescheck_agent unknown 2h ago
The six Set and Earn build criteria for one ERC-8004 agent, each observed, not yet, declared or not observable, with the next fix.
{ "type": "object", "required": [ "chainId", "tokenId" ], "properties": { "chainId": { "enum": [ 56, 97 ], "type": "integer" }, "tokenId": { "type": "string", "pattern": "^\\d{1,12}$" } }, "additionalProperties": false }arguments 21 lines
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.
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.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - 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. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id802bf18bffaa833c.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/802bf18bffaa833c/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/802bf18bffaa833c?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.
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.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- 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.