Hashlock MCP Server

Hashlock Markets — the settlement layer for the agent economy, as MCP tools. Non-custodial cross-chain OTC: sealed RFQ + price negotiation + HTLC atomic settlement (both legs settle or both refund; no custodian). BTC ↔ EVM / TRON. TESTNETS. Exposed over MCP by the hashlock mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

The canonical Model Context Protocol server for Hashlock Markets. It gives AI agents (Claude, Cursor, Windsurf, any MCP client) the full OTC trading loop:

Its toolset

Everything the assistant can do here goes through one of these:

• list_assets — Asset registry (SYMBOL@chain refs, decimals)
• list_open_rfqs — Public RFQ board, filterable
• get_rfq — One RFQ / private order
• create_rfq — Post a public RFQ or private fixed-price order
• cancel_rfq — Cancel your own request
• respond_to_rfq — Respond with a price → opens a deal thread
• negotiate — message / propose / accept_proposal / accept / reject
• deal_status — Thread + negotiation history + HTLC swap state
• set_settlement_address — Your receive/refund address per chain
• get_deal_secret — The locally-stored swap preimage (gated on both legs funded)
• reveal_claim — Report an out-of-band claim (secret + tx) so the other leg settles
• whoami — The account you're authenticated as

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at pnpm on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Configuration

You will need 8 environment variables: HASHLOCK_EVM_KEY, HASHLOCK_TRON_KEY, HASHLOCK_BTC_KEY, HASHLOCK_TOKEN, HASHLOCK_API_URL, HASHLOCK_APP_URL, HASHLOCK_TRON_HOST, HASHLOCK_SECRETS_PATH. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Hashlock MCP's toolset — list_assets, list_open_rfqs, get_rfq and 9 more — is a fair guide to whether it matches your workflow. It is maintained by hashlock-tech; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Hashlock MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Hashlock MCP.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the hashlock mcp mcp server does with a few real requests.