InnerVault

Reins

Stale Official MCP Registry, io.github.R2Rlabs

Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.

Open the source (opens github.com) https://github.com/r2rlabs/reins

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
  • Needs credentials: REINS_PRIVATE_KEY. Use a key with the least access you can.

What it is

MCP servers from io.github.R2Rlabs.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

npm package (stdio)

@r2rlabs/reins@0.1.8

From the server's entry in the official MCP Registry

Settings it asks for

  • REINS_SYMBOLS required · Markets the agent may trade, comma separated, e.g. BTC,ETH. Every other market is refused.
  • REINS_MAX_POSITION_USD required · Largest position per market, in USD.
  • REINS_DAILY_LOSS_USD required · Realised loss in a UTC day after which new risk is refused.
  • REINS_MAX_LEVERAGE · Largest total exposure as a multiple of account value.
  • REINS_MODE · paper (live prices, simulated fills, nothing signed) or live.
  • REINS_NETWORK · Hyperliquid network for prices and, in live mode, orders. Mainnet spends real money.
  • REINS_REQUIRE_STOP_LOSS · true to refuse any order that adds risk without a stop-loss.
  • REINS_LOG_FILE · Decision log, one JSON line per action with the agent's stated reason. In memory if unset.
  • REINS_PAPER_FILE · Where the paper account is kept between runs. In memory if unset.
  • REINS_ACCOUNT_ADDRESS · Live mode: the Hyperliquid account traded. Approve Reins' 2 bp builder fee from it first: npx @r2rlabs/reins approve-builder
  • REINS_PRIVATE_KEY secret · Live mode: an API wallet's key, which can trade but not withdraw. Never the account's own key.

Related

  1. agentenv-framework

    MCP servers

    Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.

    Indexed GitHub, scaleapi 441 ★Apache-2.0Updated today

    git clone https://github.com/scaleapi/agentenv-framework.git
  2. Rein Agent Risk Scale

    MCP servers

    Agent Risk Rating, A–D (NR = not rated): self-declared and unverified; not a credit rating.

    Stale Official MCP Registry, io.github.reinlayer Updated 38 days ago 1 note

  3. Reins

    MCP servers

    Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.

    Stale Official MCP Registry, io.github.R2Rlabs Updated 49 days ago 3 notes

    @r2rlabs/reins@0.1.5
  4. Rein

    MCP servers

    Spend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.

    Stale Official MCP Registry, io.github.bugiiiii11 Updated 29 days ago 2 notes

    @reinconsole/mcp@0.8.0
  5. Task-by-task AI exposure assessment of a job (Spain): 0-100 index, task map, weekly plan.

    Stale Official MCP Registry, es.reinventa Updated 17 days ago 1 note

  6. Checks whether a name is on the UK's financial sanctions list (HM Treasury), for compliance and AML

    Stale Official MCP Registry, io.github.mcp-dir Updated 3 months ago 1 note