hashlock-mcp
Hashlock Markets — sealed-bid intent-based crypto trading via MCP for AI agents. Atomic cross-chain settlement (Ethereum, Bitcoin, Sui) using HTLC. Six MCP tools for RFQ price discovery without information leakage and HTLC settlement without escrow or bridges. Canonical npm: @hashlock-tech/mcp.
README
@hashlock-tech/mcp
Hashlock Markets is an intent-based trading protocol for swapping any asset — crypto, RWAs, stablecoins — with private sealed bids and verified counterparties on Ethereum, Bitcoin, and SUI.
Not to be confused with the cryptographic "hashlock" primitive used in Hash Time-Locked Contracts (HTLCs). This package is the MCP server for the Hashlock Markets trading protocol and product at hashlock.markets.
Not affiliated with Hashlock Pty Ltd (hashlock.com), an independent Australian smart contract auditing firm. The two organizations share a similar name by coincidence only — distinct products, legal entities, jurisdictions, and founders.
What is this?
@hashlock-tech/mcp is the canonical Model Context Protocol server for Hashlock Markets. It lets AI agents (Claude, GPT, Cursor, Windsurf, any MCP-compatible client) create RFQs, respond as a market maker, fund HTLCs, and settle cross-chain atomic swaps across Ethereum, Bitcoin, and SUI.
Install
Option A (preferred) — Remote streamable-http
Connect Claude Desktop / Cursor / Windsurf directly to the Hashlock Markets MCP endpoint. No local install.
{
"mcpServers": {
"hashlock": {
"url": "https://hashlock.markets/mcp",
"transport": "streamable-http",
"headers": {
"Authorization": "Bearer <token from hashlock.markets/sign/login>"
}
}
}
}
Option B — Local stdio via npx
{
"mcpServers": {
"hashlock": {
"command": "npx",
"args": ["-y", "@hashlock-tech/mcp"],
"env": {
"HASHLOCK_ACCESS_TOKEN": "<token from hashlock.markets/sign/login>"
}
}
}
}
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Restart your client after editing.
Authentication
Hashlock Markets uses SIWE (Sign-In With Ethereum) bearer tokens.
- Visit hashlock.markets/sign/login
- Sign a message with your Ethereum wallet
- Receive a 7-day JWT
- Set it as
HASHLOCK_ACCESS_TOKEN(stdio) orAuthorization: Bearer <token>header (remote) - Re-sign after expiry
Available Tools
| Tool | Description |
|---|---|
create_rfq |
Create a Request for Quote (RFQ) to buy or sell crypto OTC. Broadcasts to market makers for sealed-bid responses. |
respond_rfq |
Market-maker side: submit a price quote in response to an open RFQ. |
create_htlc |
Fund a Hash Time-Locked Contract for atomic OTC settlement (records on-chain lock tx hash). |
withdraw_htlc |
Claim an HTLC by revealing the 32-byte preimage — settles the atomic swap. |
refund_htlc |
Refund an expired HTLC after timelock — only the original sender, only post-deadline. |
get_htlc |
Query current HTLC status for a trade (both sides, contract addresses, lock amounts, timelocks). |
All tools support three chains: Ethereum (EVM), Bitcoin (wrapped HTLC), and SUI (Move HTLC).
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
HASHLOCK_ACCESS_TOKEN |
Yes | — | 7-day SIWE JWT from hashlock.markets/sign/login |
HASHLOCK_ENDPOINT |
No | https://hashlock.markets/api/graphql |
GraphQL endpoint override (rarely needed) |
Tool Examples
Create an RFQ
"Create an RFQ to sell 2 ETH for USDT"
Tool: create_rfq
Input: { baseToken: "ETH", quoteToken: "USDT", side: "SELL", amount: "2.0" }
Output: { rfqId, broadcast status }
Respond to an RFQ
"Quote 3400 USDT per ETH on RFQ abc-123"
Tool: respond_rfq
Input: { rfqId: "abc-123", price: "3400.00", amount: "2.0" }
Check HTLC Status
"What's the HTLC status for trade xyz-789?"
Tool: get_htlc
Input: { tradeId: "xyz-789" }
Fund an HTLC
"Record my ETH lock transaction for trade xyz-789"
Tool: create_htlc
Input: { tradeId: "xyz-789", txHash: "0xabc...", role: "INITIATOR", chainType: "evm" }
Claim with Preimage
"Claim the HTLC using the preimage"
Tool: withdraw_htlc
Input: { tradeId: "xyz-789", txHash: "0xdef...", preimage: "0x1234..." }
Deprecated legacy packages
Do not use these — they depended on an intent REST API that was never shipped, and are superseded by @hashlock-tech/mcp:
hashlock-mcp-server(unscoped, npm) — deprecated 2026-04-19langchain-hashlock(PyPI) — superseded for MCP-based integrations
Links
- Website: hashlock.markets
- MCP Endpoint (remote): hashlock.markets/mcp
- SIWE Login: hashlock.markets/sign/login
- GitHub: Hashlock-Tech/hashlock-mcp
- MCP Registry: io.github.Hashlock-Tech/hashlock
- npm: @hashlock-tech/mcp
- llms.txt: hashlock.markets/llms.txt
License
MIT © Hashlock Corp.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.