About HiveClear
HiveClear is an MCP server for multi-party USDC settlement, where a validator network votes on transactions and settlement requires approval from 67% of total voting power. It also provides settlement status, network statistics, and validator information.
Key features
- 01Submit multi-party settlement requests
- 02Approve transactions through validator voting
- 03Finalize at a 67% voting-power threshold
- 04Check settlement status and vote breakdown
- 05View network statistics and active validators
Use cases
- 01Coordinate USDC settlements among multiple parties
- 02Track votes on pending settlements
- 03Review clearing network data and validator details
MCP support
The MCP server provides tools to submit settlements, check their status, view network statistics, and list validators. Clients send JSON-RPC 2.0 requests to the `/mcp` endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://hiveclear.onrender.com/mcpclaude mcp add --transport http srotzin-hiveclear https://hiveclear.onrender.com/mcp{"mcpServers":{"srotzin-hiveclear":{"type":"http","url":"https://hiveclear.onrender.com/mcp"}}}Open in Cursor{"servers":{"srotzin-hiveclear":{"type":"http","url":"https://hiveclear.onrender.com/mcp"}}}Open in VS Code{"mcpServers":{"srotzin-hiveclear":{"type":"http","url":"https://hiveclear.onrender.com/mcp"}}}{"mcpServers":{"srotzin-hiveclear":{"serverUrl":"https://hiveclear.onrender.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| memo | string | No | Human-readable memo or description for the settlement |
| parties | array | Yes | The parties involved in the settlement |
| settlement_type | string | Yes | Type of settlement (e.g. payment, escrow, refund) |
Details
From the project READMEHiveClear — Multi-Party Settlement — MCP Server
HiveClear is an MCP server for multi-party settlement with validator consensus. It coordinates USDC settlements between multiple parties, using a network of validators that vote to approve, reject, or dispute each transaction. Settlements are finalized when 67% of total voting power approves.
MCP Tools
| Tool | Description |
|---|---|
hiveclear_submit_settlement | Submit a settlement for multi-party validator consensus. Accepts an array of parties (DID, role, amount), settlement type, and optional memo. |
hiveclear_get_status | Get the current status of a settlement by ID, including vote breakdown from each validator. |
hiveclear_get_stats | Get clearing network statistics: volume today, fees today, consensus approval rate, and total settlement count. |
hiveclear_list_validators | List all active validators in the consensus network with voting power, bond amount, uptime, and earnings. |
Usage
Send JSON-RPC 2.0 requests to the /mcp endpoint:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "hiveclear_get_stats",
"arguments": {}
}
}
Settlement Flow
- Submit a settlement with two or more parties via
hiveclear_submit_settlement - Validators vote to approve or reject (67% threshold required)
- Check status with
hiveclear_get_statusto see vote progress and final outcome - Approved settlements have fees distributed: 70% to validators, 20% to reward pool, 10% to platform
Running
npm install
npm start
The server listens on port 3001 by default (PORT env var to override).
License
Proprietary
Hive Civilization
Hive Civilization is the cryptographic backbone of autonomous agent commerce — the layer that makes every agent transaction provable, every payment settable, and every decision defensible.
This repository is part of the SETTABLE pillar.
- thehiveryiq.com
- hiveagentiq.com
- agent-card: https://hivetrust.onrender.com/.well-known/agent-card.json
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.