npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@tronchartsxyz/mcp-server

v0.2.0

Published

Model Context Protocol server for Tron Charts — trade perps + predictions from Claude / GPT / any MCP client.

Readme

@tronchartsxyz/mcp-server

A Model Context Protocol server that exposes Tron Charts' OMS as tools Claude / GPT / any MCP-capable client can call. Trade perps on Hyperliquid + Aster, observe predictions on Polymarket, and run autonomous strategies — without writing a single REST call.

┌──────────────────┐   stdio MCP    ┌────────────────────┐   HTTPS    ┌──────────────┐
│ Claude Desktop / │ ◀───tools────▶ │  tron-charts-mcp   │ ◀──REST──▶ │ Tron Charts  │
│ Claude Code /    │                │  (this package)    │            │ Provider API │
│ Cursor / etc.    │                │                    │            └──────┬───────┘
└──────────────────┘                │  agent key signs   │                   │
                                    │  HL intents locally│                   ▼
                                    └────────────────────┘            ┌──────────────┐
                                                                       │  HL / Aster  │
                                                                       │  /exchange   │
                                                                       └──────────────┘

With TRON_CHARTS_AGENT_KEY, Hyperliquid actions can be signed locally; that private key never leaves the MCP process. Without it, the OMS uses existing backend-provisioned venue credentials. Aster and Polymarket require backend signing; the wizard-generated local key does not provision those venues. Risk envelope caps and the kill switch are enforced by the API. Paper accounts use the platform's simulated matching engine and no agent key.


Install

npm install -g @tronchartsxyz/mcp-server

# or one-off via npx:
npx -y @tronchartsxyz/mcp-server

Live Hyperliquid credentials

In Tron Charts → Lab → MCP → mint a new key (also available in Settings → API Clients):

  1. Pick a tier (readonly / liquidation / fullTrading)
  2. Set risk envelope caps (max position notional, daily loss cap)
  3. Generate an agent keypair (FE-side; private key shown ONCE)
  4. Sign approveAgent with your main wallet (HL relay happens server-side)
  5. Copy:
    • TRON_CHARTS_API_KEY=pk_…
    • TRON_CHARTS_API_SECRET=sk_… ← never recoverable
    • TRON_CHARTS_AGENT_KEY=0x… ← 32-byte hex; never recoverable

The agent address is pre-authorized via HL's approveAgent primitive — your main wallet stays cold; the agent key only has trading permission within its scope + expiry.

Simulated / prop-firm accounts

Select the paper-backed prop or simulated account before opening Lab → MCP. Minting a key for that account needs no wallet approval or agent private key. Copy API key + secret and the generated configuration; paper credentials remain active until revoked. Existing account trading-group, prop and OMS risk rules still apply.

Pass venue: "paper" to place_market_order, place_limit_order, place_stop_order or flatten_position. Symbols use the platform's normal format, including B3. The backend rejects paper mode against a live account. Use cancel_order with the paper working order ID. Paper execution returns mode: "paper"; a dispatched order is not necessarily filled. Give every logical order a unique clientOrderId. If a tool call times out, first use query_order with that ID to recover the current state. Repeating the exact order with the same ID returns the original intent, even after the 24-hour HTTP idempotency cache expires. Changing the order while reusing its ID is rejected.

For example, a simulated market tool call is:

{ "venue": "paper", "symbol": "BTC.HL", "side": "buy", "qty": 0.001, "clientOrderId": "strategy-20260922-001" }

Live funded prop accounts are not paper accounts. Their custody/signing requirements remain separate. To test unpublished changes, build this package and use node /absolute/path/to/mcp-server/dist/index.js as the stdio command; npx only receives the new tools once this version is published.

Configure Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "tron-charts": {
      "command": "npx",
      "args": ["-y", "@tronchartsxyz/mcp-server"],
      "env": {
        "TRON_CHARTS_API_KEY": "pk_...",
        "TRON_CHARTS_API_SECRET": "sk_...",
        "TRON_CHARTS_AGENT_KEY": "0x...",
        "TRON_CHARTS_BASE_URL": "https://api.troncharts.xyz"
      }
    }
  }
}

Restart Claude Desktop and check that the server connects and exposes its tools.

Configure Claude Code

claude mcp add --transport stdio --scope user \
  --env TRON_CHARTS_API_KEY=pk_... \
  --env TRON_CHARTS_API_SECRET=sk_... \
  --env TRON_CHARTS_AGENT_KEY=0x... \
  --env TRON_CHARTS_BASE_URL=https://api.troncharts.xyz \
  tron-charts -- npx -y @tronchartsxyz/mcp-server

Configure Cursor

Use the same JSON above in Cursor's MCP configuration. The platform wizard sets TRON_CHARTS_BASE_URL to the current application origin, which must proxy /api to this backend. Use your deployment's API origin if it does not. Omit TRON_CHARTS_AGENT_KEY for Aster/Polymarket or backend signing.

Hosted endpoint

For a browser-based connector, add https://<your app host>/api/mcp as a remote Streamable HTTP server and choose OAuth. Discovery advertises a public client registration endpoint, authorization-code + S256 PKCE, and rotating refresh tokens. The browser opens Tron Charts, where you sign in and approve one owned paper account and the requested tier. Full-trading consent requires positive notional and daily-loss caps. The connector receives a one-hour account/resource-scoped bearer; it never sees an API key or wallet secret. Revoking the connection in Lab → MCP immediately disables the credential.

The local stdio flow above still exchanges its API key and secret at POST /api/auth/api-token. For manual hosted clients, the JWT from that endpoint can be used as Authorization: Bearer <token>; the API key itself is not a bearer token. Hosted MCP sessions bind to their initializing bearer, so refreshed tokens start a new MCP session. Unknown session IDs return 404. The package's standalone HTTP mode is a separate, single-credential service.

Tools

Tier-filtered. Your credential's tier (returned at JWT mint) decides which tools are advertised.

Always available (readonly+)

  • query_account — { accountId, accountNumber, kind, tier, agentAddress }. Call once at session start.
  • query_order — current canonical intent state, by intent ID or paper clientOrderId.
  • query_balance — per-venue equity / balance / margin / unrealized PnL.
  • query_positions — open positions with side / qty / entry / mark / liq / leverage / uPnL.
  • query_open_orders — working orders with venueOrderId / type / qty / price.
  • query_recent_trades — closed round-trip trades with realized PnL + fees (default 50).
  • query_recent_fills — raw per-leg fills (default 100).
  • get_agent_context — risk envelope notes + error code reference.

Adds at liquidation tier

  • cancel_order — cancel by venueOrderId. Signs + dispatches synchronously.

Adds at fullTrading tier

  • place_market_order — IOC market, slip-capped at 5% per HL semantics.
  • place_limit_order — Gtc / Ioc / Alo (post-only). Subject to risk envelope.
  • place_stop_order — trigger-based order.
  • flatten_position — close one symbol via reduceOnly market. Fast-fails on "already flat".

Example agent prompts

"Show me my BTC position and current liquidation price."

"If BTC is below $80,000 right now, place a limit buy for 0.001 at $79,500 with post-only."

"Cancel my oldest working order and place a new one 100 USD lower."

"What's my worst trade this week, and what should I learn from it?"

The LLM reads tool descriptions to decide which to call. Structured errors (e.g. risk_envelope_position_notional, kill_switch_engaged, already_flat) come back as tool results so the model self-corrects rather than crashing the conversation.

Risk envelope

Every place_* call hits a compose-time gate that enforces:

  • kill_switch — operator hard-stop. Engage via Settings → API Clients → Kill Switch when something goes wrong. All place_* return kill_switch_engaged until reset.
  • max_position_notional_usd — single-order notional cap. Order rejects with risk_envelope_position_notional if qty × refPrice exceeds it.
  • daily_loss_cap_usd — rolling 24h realized-loss limit. Once tripped, place_* returns risk_envelope_daily_loss until the cap rolls forward.

Caps are enforced BE-side because this process runs on the user's machine — client-side enforcement is worthless. Even if the MCP server were tampered with, the BE gate would still cap exposure.

What's not in v1

  • Local Aster + Polymarket signing. These venues require existing backend credentials. Only the Hyperliquid local signer ships in this package.
  • Local signing for orchestration tools. modify_order, reverse_position, attach_brackets and cancel_all_orders require backend signing. Query tools/list for the tier-filtered catalog.
  • Long-lived streams (positions / quotes pushed in real-time). MCP's tool model is request/response. For high-frequency strategies use the Tron Charts WSS Provider API directly.
  • Multi-account. The bearer is account-scoped. One MCP server instance per account; run two if you need two.

Trust model

| What | Where | Why | |---|---|---| | API key + secret | env on user's machine | rotates via re-mint; revocable via Settings | | 24h JWT bearer | in-memory in this process | auto-refreshed; revocable via blocklist | | Agent private key | env on user's machine | never on BE; venue verifies signature | | approveAgent envelope | signed once by main wallet at mint | grants the agent address trading permission within scope + expiry | | Risk envelope | BE-side enforcement | trust boundary; client-side caps are worthless | | Audit trail | BE order_intents.api_client_id | every agent-placed order tagged + queryable |

Source

Built and maintained alongside the Tron Charts platform. Open issues + feature requests on the main repo.

License

MIT.