# io.github.winter0x/lighter-mcp (io.github.winter0x/lighter-mcp@0.1.1)

> Source: <https://mcpindex.ai/server/io-github-winter0x-lighter-mcp>
> Published: 2026-08-26 10:13:31+00:00

[← Index](/leaderboard)

# io.github.winter0x/lighter-mcp

Read Lighter perpetual markets and place guarded orders, including the H100 compute-price market.

The current version, v0.1.1, was published to the official MCP registry on 2026-08-26. It is distributed as lighter-mcp on npm, filed under Other by this index, and declares 7 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; [the index's current counts](/stats) put this record in context.

## Using io.github.winter0x/lighter-mcp in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and **HOLDs the call** when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use **Install this server** for that).

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

```
uv tool install mcpindex-gate && mcpindex-config-wire
```

[method](/methodology)

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: [the eval, four-state verdict, honest limits](/methodology).

Own this server? [Screen its description →](/screen)

## That verdict was true at screening time (snapshot 2026-08-26).

Contracts can change after screening, with no version bump. The gate pins io.github.winter0x/lighter-mcp’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

[See your first HOLD in 2 minutes →](/guides/install-the-gate-first-hold)

Related: [how to trust an MCP server](/guides/how-to-trust-an-mcp-server) · [screen before install](/guides/screen-mcp-server-before-install) · [silent contract drift](/guides/mcp-silent-contract-drift)

`LIGHTER_NETWORK`

Deployment to read: mainnet, testnet, or robinhood. Defaults to mainnet.

`LIGHTER_ACCOUNT_INDEX`

Sub-account the agent trades from. Read-only tools work without it.

`LIGHTER_API_KEY_INDEX`

API key slot bound to the sub-account, 0 to 254.

`LIGHTER_API_KEY_PRIVATE_KEY`

API key private key. Full write authority over the account it is bound to, so use a dedicated sub-account.

`LIGHTER_MAX_NOTIONAL_USD`

Per-order notional ceiling in USD. Required before any order can be signed.

`LIGHTER_CHAIN_ID`

Layer-2 chain id bound into every signature. Mainnet uses 304 and testnet 300, so this is only needed on a deployment that publishes none.

`LIGHTER_READ_ONLY_TOKEN`

Read-only token for account observation without a signing key.

[methodology](/methodology)

[AgentRoamai.agentroam/agentroam](/server/ai-agentroam-agentroam)

Buy travel eSIMs, gift cards and mobile top-ups with crypto — user confirms before any order.

[Authoryzeai.authoryze/authoryze](/server/ai-authoryze-authoryze)

Give your AI agent a spending limit: approval controls and single-use virtual cards.

[io.github.wisdomrock/code-context-gateio.github.wisdomrock/code-context-gate](/server/io-github-wisdomrock-code-context-gate)

Context-aware code retrieval MCP server — ranked, gated results for AI coding agents