Safety-first MCP server exposing Lighter perpetual-DEX trading to AI agents (Cursor, Claude, Codex, Claude Desktop, OpenClaw).
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"lighter-mcp-toolkit-lighter-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Lighter MCP Toolkit [](https://github.com/iamgoatedaf/lighter-mcp/actions/workflows/ci.yml) [](https://pyproject.toml) [](LICENSE) [](https://modelcontextprotocol.io) > **Read this first:** live orders and withdrawals on Lighter are > irreversible. Read [DISCLAIMER.md](DISCLAIMER.md) before flipping > `mode = "live"` or `mode = "funds"`. A portable Model Context Protocol server that exposes Lighter trading to any MCP-capable agent — Cursor, Claude Code, Claude Desktop, Codex, OpenClaw, and generic MCP clients — with **safety as a first-class concern**, not an afterthought. The server wraps the official [`lighter-agent-kit`](https://github.com/elliottech/lighter-agent-kit) Python scripts via subprocess and adds: - **Typed Pydantic input schemas** with regex-validated symbols and asset codes (no command-line argument injection). - **Mode-based safety gates** (`readonly` → `paper` → `live` → `funds`): the tool catalog grows monotonically; live and funds tools physically do not exist in the catalog until you opt in. - **Two-step confirmations** for every fund-loss path: first call returns a preview + single-use token, second call with the token executes. Tokens are bound to tool name + argument digest and TTL-limited. - **Atomic, UTC-keyed daily-notional ledger** that fail-safes to `cap exhausted` if its file is corrupt — never silently resets to 0. - **Append-only audit log** with sanitized argv/result, intra-process lock + POSIX `flock`, and soft-fail on disk errors. - **Streamable-HTTP transport** that refuses to bind non-loopback hosts unless `--allow-remote` is passed (the server has no built-in auth). ## Why not just use the kit directly? The kit is…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.