mcp-registry/io.github.tmcodingarc/bull-otc · registry v1.0.0 · server reports v1.1.0
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clientsAs of 2026-11-22 15:07 UTC, the Bull OTC MCP server is up with a Glimind reliability score of 93/100 (grade A). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 7 minutes.
Non-custodial RFQ and atomic swap settlement for AI agents. Escrow onchain, signed receipts.
Point your MCP client at this streamable-http endpoint: https://www.bull.family/api/mcp
34 of 34 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
7 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
In the last 30 days: 0 tool(s) removed and 24 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.tmcodingarc%2Fbull-otc/fixes
{
"name": "bull_agreement_create",
"description": "Use when your agent must pay an agent it does not trust, and the payment should depend on conditions: a programmable escrow (\"do A when B does C\"), built from Bull blocks. The payer locks USDC (Base), USDG/ETH/any ERC-20 (Robinhood Chain); the payee is paid when ALL conditions are true: a time passed, a named agent or arbiter attested (confirmed delivery), an objection or veto window ended without an objection, k of n agents voted yes (quorum), another Bull deal settled, or an onchain value (tok",
"inputSchema": {
"type": "object",
"required": [
"payer",
"payee",
"amount",
"conditions"
],
"properties": {
"asset": {
"type": "string",
"description": "\"eth\" (default, native ETH on both chains), the chain's stablecoin (\"usdg\" on Robinhood Chain, \"usdc\" on Base) or an ERC-20 address. Whole units."
},
"chain": {
"type": "string",
"description": "robinhood (default) or base."
},
"payee": {
"type": "string",
"description": "Wallet that is paid when every condition is true."
},
"payer": {
"type": "string",
"description": "Wallet that locks the funds. It sends the approve and createAgreement transactions."
},
"terms": {
"type": "string",
"description": "The agreement in plain words (optional). Its hash is stored onchain."
},
"amount": {
"type": "string",
"description": "Amount to lock in WHOLE units, e.g. \"500\"."
},
"conditions": {
"type": "array",
"items": {
"type": "object"
},
"description": "1 to 8 conditions, all must be true. Each: {type:\"time_after\", afterHours|at} | {type:\"attest\", by:\"0xWallet\"} | {type:\"token_balance_gte\", token, holder, min} | {type:\"call_gte\"|\"call_lte\", target, data, value} | {type:\"deal_settled\", dealId} | {type:\"unless\", by, afterHours} (pays unless this wallet objects) | {type:\"veto\", by, afterHours, attestIndex} (objection window that starts when the attest at attestIndex happens) | {type:\"quorum\", by:[wallets], k}. A time_after or unless must end before expiryHours."
},
"expiryHours": {
"type": "number",
"description": "Hours until anyone can refund the payer if the conditions are not met. Default 72."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "bull_agreement_status",
"description": "Use to check where an agreement stands before you serve, pay or wait: status, every condition with met true/false and who it is waiting on, and the next transactions (attest by the named wallet, release when all conditions are true, refund after expiry). Read from the chain. Public, no signature.",
"inputSchema": {
"type": "object",
"required": [
"agreementId"
],
"properties": {
"chain": {
"type": "string",
"description": "robinhood (default) or base."
},
"agreementId": {
"type": "string",
"description": "Agreement id from the AgreementCreated event."
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "bull_bridge_status",
"description": "Use after sending the bridge transactions from bull_bridge_quote: returns pending, confirmed, failed or refunded and the transaction hashes. Open the Bull agreement on the settlement chain only when it says confirmed. Public, no signature.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "The id returned by bull_bridge_quote (0x…, 66 characters)."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.tmcodingarc/bull-otc"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.tmcodingarc/bull-otc"}) over MCP.
bull_agreement_from_template ~1,191 tokensbull_settle_plan ~738 tokensbull_settle ~661 tokensbull_create_rfq ~591 tokensbull_agreement_create ~575 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live.
Shows whether the server is live and its agent-readiness score; it updates within the hour.
[](https://glimind.com/server/mcp-registry%2Fio.github.tmcodingarc%2Fbull-otc?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.tmcodingarc%2Fbull-otc?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fio.github.tmcodingarc%2Fbull-otc.svg" alt="MCP server status"></a>
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:08e064e201b7ccb8…, first seen 2026-11-22, included at leaf 383609 of 384,122. Version history · verify what your client received.
Compare: most reliable finance servers · most reliable other servers · most reliable knowledge servers · most reliable retrieval servers · most reliable data servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp?ref=install-server"
}
}
}
A free Glimind key lets your agent check whether a server works right now before it calls it, and switch to a live one when it doesn't. No signup, no card.
As of 2026-11-22 15:07 UTC, the Bull OTC MCP server is up with a Glimind reliability score of 93/100 (grade A). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 7 minutes.
Bull OTC MCP server advertises 34 tools, including bull_accept_quote, bull_agent_reputation, bull_agreement_create, bull_agreement_feed, bull_agreement_from_template.
Point your MCP client at this streamable-http endpoint: https://www.bull.family/api/mcp
Glimind scanned all 34 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.