hashlock

hashlock is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from Hashlock-Tech/hashlock-mcp. Its token cost is not measured, scanned A, original, MIT.

A locally run MCP server for non-custodial over-the-counter cryptocurrency trading across multiple blockchains. It supports sealed requests for quotes, negotiation, and hash time-locked atomic swaps on a test network.

In plain words
What is it for?
Use it to connect an agent to Hashlock’s testnet trading service across EVM chains, Tron, and Bitcoin. It is intended for configuring and running the Hashlock MCP package locally.
Why use it?
It provides a way for AI agents to arrange these trades without handing custody of funds to the service. Running it requires seven environment variables, including wallet keys and network settings.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

Good fit Use it to connect an agent to Hashlock’s testnet trading service across EVM chains, Tron, and Bitcoin. It is intended for configuring and running the Hashlock MCP package locally.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/hashlock-tech/hashlock-mcp/hashlock
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Hashlock-Tech/hashlock-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hashlock

README.md
[![agentmods](https://agentmods.dev/badge/mcp/hashlock-tech/hashlock-mcp/hashlock/github.svg)](https://agentmods.dev/mcp/hashlock-tech/hashlock-mcp/hashlock)
Your own site
<a href="https://agentmods.dev/mcp/hashlock-tech/hashlock-mcp/hashlock"><img src="https://agentmods.dev/badge/mcp/hashlock-tech/hashlock-mcp/hashlock/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hashlock

Your own site · 80×15
<a href="https://agentmods.dev/mcp/hashlock-tech/hashlock-mcp/hashlock"><img src="https://agentmods.dev/badge/mcp/hashlock-tech/hashlock-mcp/hashlock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

hashlock scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 20 lines

What it actually says

{
  "hashlock": {
    "command": "npx",
    "args": [
      "-y",
      "@hashlock-tech/mcp",
      "-y"
    ],
    "env": {
      "HASHLOCK_EVM_KEY": "",
      "HASHLOCK_TRON_KEY": "",
      "HASHLOCK_BTC_KEY": "",
      "HASHLOCK_SOLANA_KEY": "",
      "HASHLOCK_TOKEN": "",
      "HASHLOCK_API_URL": "https://dev.hashlock.markets/api",
      "HASHLOCK_EVM_RPC": "https://ethereum-sepolia-rpc.publicnode.com",
      "HASHLOCK_TRON_HOST": "https://nile.trongrid.io"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 24d ago Changed · +1 lines 7265843244be
  2. 1mo ago First seen · 19 lines scan A aa230c0f1e6c

Subscribe to this mod's changes

hashlock is an MCP server published in the GitHub repository Hashlock-Tech/hashlock-mcp (0 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other mcp servers, from other repositories

alloc-context

Portfolio-aware crypto context — CEX or wallet holdings, holdings-scoped market, optional allocation analysis. Runs locally from the alloc-context Python package.

AllocContext/alloc-context · not measured

bitcoin-mcp

MCP server for Bitcoin — 50 tools for AI agents using Bitcoin Core or a compatible API. Runs locally from the bitcoin-mcp Python package. Needs 5 environment variables to run.

Bortlesboat/bitcoin-mcp · not measured

coingecko-mcp-server

Crypto market data via CoinGecko — prices, markets, history, trending, and deep coin metadata. Runs locally from the @cyanheads/coingecko-mcp-server npm package. Needs 2 environment variables to run.

cyanheads/coingecko-mcp-server · not measured

crypto-prices-mcp

Live and historical cryptocurrency prices via CoinGecko free API. Remote server at crypto-prices-mcp.atlasword.workers.dev.

guptaprakhariitr/crypto-prices-mcp · not measured

verdictswarm

Every tool has an answer — your agent needs a decision. MCP server for the VerdictSwarm pre-trade check: a machine-readable avoid/caution/clear before your agent trades, plus intended-size exit feasibility and holder-cluster attribution on Solana. Runs locally from the verdictswarm-mcp Python package. Needs 3…

sentien-labs/verdictswarm-mcp · not measured

verdictswarm-mcp

Every tool has an answer — your agent needs a decision. MCP server for the VerdictSwarm pre-trade check: a machine-readable avoid/caution/clear before your agent trades, plus intended-size exit feasibility and holder-cluster attribution on Solana. Runs locally from the verdictswarm-mcp Python package. Needs 1…

sentien-labs/verdictswarm-mcp · not measured