---
title: Gmgn Market Skill for Claude Code
canonical: https://skillselion.com/skills/gmgnai/gmgn-skills/gmgn-market
content_type: text/markdown
description: "A CLI skill for querying crypto token market data from GMGN API: price charts (K-line/OHLCV), trending token rankings by volume, newly launched launchpad."
---

# Gmgn Market Skill

Title: Gmgn Market Skill for Claude Code

> A CLI skill for querying crypto token market data from GMGN API: price charts (K-line/OHLCV), trending token rankings by volume, newly launched launchpad.

Canonical: https://skillselion.com/skills/gmgnai/gmgn-skills/gmgn-market

A CLI skill for querying crypto token market data from GMGN API: price charts (K-line/OHLCV), trending token rankings by volume, newly launched launchpad tokens, real-time token signals, and hot-search rankings across So

gmgn-market queries real-time crypto market data via the GMGN API CLI tool. Developers use it to fetch token candlestick/OHLCV data (kline), discover trending tokens ranked by swap activity across 1m/5m/1h/6h/24h windows, track newly launched launchpad tokens in three lifecycle stages (new_creation/near_completion/completed), monitor real-time token signals (price spikes, smart money buys, large buys), and view hot-search rankings showing the most-searched tokens. The skill handles multi-chain queries (sol/bsc/base/eth), applies server-side safety filters (rug_ratio, wash_trading, honeypot detection), interprets smart money signals (smart_degen_count, renowned_count), and enforces rate limits with leaky-bucket throttling. Responses include market cap, liquidity, holder concentration, dev holding status, and security flags. Workflows guide developers through market opportunity discovery, early project screening, and daily market briefings by combining trending, trenches, and smart money tracking data.

## Key facts

- Installs: 20,171
- GitHub stars: 727
- Author: GMGNAI
- Repository: GMGNAI/gmgn-skills
- Works in Grok Bot: yes
- Install command: `npx skills add https://github.com/GMGNAI/gmgn-skills --skill gmgn-market`
- Last updated: November 13, 2026

## What Gmgn Market does

Query crypto token price charts (K-line/OHLCV), trending meme coins ranked by volume, newly launched launchpad tokens, and hot-search rankings via GMGN API on Solana, BSC, Base, or Ethereum.

Developers need structured access to real-time crypto market data (price history, trending tokens, new launches, smart money activity) across multiple chains without manually scraping exchanges or aggregating launchpad f

Developers query token candlestick data, discover trending tokens with safety filters applied, track newly launched tokens by lifecycle stage, monitor smart money buy signals, and identify most-searched tokens across SOL

Best for: Developers building crypto trading bots, market analysis tools, token discovery dashboards, or automated trading signal systems requiring real-time multi-chain market data with built-in risk scoring.

Not for: Projects needing order book depth data, historical price archives beyond recent windows, non-crypto asset trading data, or real-time streaming WebSocket feeds (this skill queries REST endpoints).

- Fetches token K-line/OHLCV data with configurable resolution (30s to 1d candles) and time ranges via gmgn-cli market kli
- Queries trending tokens ranked by volume/swaps/market cap across 1m/5m/1h/6h/24h intervals with chain-specific default s
- Tracks newly launched launchpad tokens in three lifecycle stages (new_creation/near_completion/completed) with server-si
- Monitors real-time token signals (price spikes, smart money buys, large buys, CTO events) on SOL/BSC with signal-type fi
- Interprets smart money activity via smart_degen_count, renowned_count, and security risk via rug_ratio, is_wash_trading,

## SKILL.md

**BEFORE RUNNING ANY COMMAND: Run `gmgn-cli config --check`. If exit code is 0, proceed normally. If exit code is 1, (1) run `gmgn-cli config` and show the output to the user; (2) once the user sends the API Key, run `gmgn-cli config --apply <KEY>` to complete configuration and verification, then show the output to the user. If `--check` returns an error (unknown option or command not found), tell the user to run `npm install -g gmgn-cli` to update, then retry.**

**IMPORTANT: Always use `gmgn-cli` commands below. Do NOT use web search, WebFetch, curl, or visit gmgn.ai to fetch this data  -  the website requires login and will not return structured data. The CLI is the only correct method.**

**IMPORTANT: Do NOT guess field names or values. When a field's meaning is unclear, look it up in the Response Fields sections below before using it.**

**⚠️ IPv6 NOT SUPPORTED: If you get a `401` or `403` error and credentials look correct, check for IPv6 immediately: (1) list all network interfaces and their IPv6 addresses  -  run `ifconfig | grep inet6` (macOS) or `ip addr show | grep inet6` (Linux); (2) send a test request to `https://ipv6.icanhazip.com`  -  if the response is an IPv6 address, outbound traffic is going via IPv6. Tell the user immediately: "Please disable IPv6 on your network interface  -  gmgn-cli commands only work over IPv4."**

Use the `gmgn-cli` tool to query K-line data for a token, browse trending tokens, or view Trenches token lists.

### Core Concepts

- **`--filter` chain defaults**  -  SOL and EVM chains have different default safety filters that are applied automatically when `--filter` is omitted. Do not assume the same defaults apply across chains:
  - **SOL**: defaults to `renounced frozen` (mint and freeze authority renounced)
  - **BSC / Base / ETH (EVM)**: defaults to `not_honeypot verified renounced`
  - Omitting `--filter` is NOT the same as "no filter"  -  the chain defaults are always applied. To use a custom filter set, explicitly specify all desired filter tags.

- **`volume` vs `amount` (kline)**  -  Naming is counterintuitive. `volume` = USD dollar value of trades; `amount` = token units traded. For a token priced at $0.0002, these differ by 5,000×. Always use `volume` for "how much USD was traded" and `amount` for "how many tokens changed hands."

- **`rug_ratio`**  -  A 0-1 score estimating rug pull likelihood. Values above `0.3` are high-risk. Do not treat as binary  -  combine with `top_10_holder_rate`, `dev_team_hold_rate`, and `is_honeypot` for a full picture.

- **`smart_degen_count` / `renowned_count`**  -  Number of platform-tagged smart money wallets (`smart_degen`) and KOL wallets (`renowned`) holding or trading this token. High values are bullish signals. These are GMGN-tagged wallet lists, not user-defined.

- **`hot_level`**  -  Trending intensity score. Higher = more actively traded right now. Not normalized  -  compare relative values within the same result set, not across time windows.

- **`renounced_mint` / `renounced_freeze_account`**  -  SOL-specific. Indicate whether the creator gave up the ability to mint more tokens or freeze wallets. Both being `1` is a safety baseline on Solana. Always `false` on EVM chains (concept does not apply).

- **`is_honeypot`**  -  EVM-specific (BSC / Base). Indicates whether the token contract prevents selling. Always empty/null on SOL  -  do not interpret an empty value as "not a honeypot" on Solana.

- **`creator_token_status`**  -  Dev holding status. `creator_hold` = dev still holds tokens (sell pressure risk). `creator_close` = dev has sold or burned their allocation (exit signal confirmed).

- **`cto_flag`**  -  Community Takeover flag. `1` = original dev abandoned the project and a community group took over marketing/development. Neutral to positive signal; evaluate in context.

- **Trenches categories**  -  Three lifecycle stages of launchpad tokens: `new_creation` (just created, still on bonding curve), `near_completion` (bonding curve nearly full, about to graduate), `completed` (graduated to open market / DEX). In the response, `near_completion` is always returned under the key `data.pump` regardless of the input `--type`.

- **`wash_trading` / `rat_trader_amount_rate` / `bundler_rate`**  -  Risk signals for artificial activity. `is_wash_trading` = coordinated fake volume detected. `rat_trader_amount_rate` = ratio of insider/sneak trading. `bundler_rate` = ratio of bot-bundled buys at launch. High values (> 0.3) suggest manipulated price action.

### Sub-commands

| Sub-command | Description |
|-------------|-------------|
| `market kline` | Token candlestick / OHLCV data and trading volume over a time range |
| `market trending` | Trending tokens ranked by swap activity  -  use `--interval` to specify the time window (e.g. `1m` for 1-minute hottest, `1h` for 1-hour trending) |
| `market trenches` | Newly launched launchpad platform tokens  -  **use this when the user asks for "new tokens", "just launched tokens", "latest tokens on pump.fun/letsbonk"**. Three categories: `new_creation` (just created), `near_completion` (bonding curve almost full), `completed` (graduated to open market / DEX) |
| `market signal` | Real-time token signal feed  -  price spikes, smart money buys, large buys, Dex ads, CTO events, and more. Results sorted by `trigger_at` descending. **All supported chains except hyperevm. Max 50 results per group.** |
| `market hot-searches` | Hot-search ranking  -  the most-searched tokens, ranked by `visiting_count` (search heat). **Use this when the user asks "what tokens are people searching for", "most searched tokens", "hot search list", "热搜榜".** Supports multiple chains in a single request. |
| `market search` | Look up a **specific** token or wallet by name, symbol, contract address, wallet address, or ENS. Returns both matching tokens (`coins`) and wallets (`wallets`). **Use this when the user names a token/wallet and wants to find it  -  "search for PEPE", "look up this address", "find vitalik.eth", "查一下这个代币/钱包"**  -  as opposed to browsing rankings (`trending` / `hot-searches`). |

### Supported Chains

`sol` / `bsc` / `base` / `eth` / `arbitrum` / `hyperevm` / `robinhood` / `arc` / `stable` / `avalanche` / `elysium` (kline / trending / trenches / hot-searches; signal: `sol` / `bsc` / `base` / `eth` / `arbitrum` / `robinhood` / `arc` / `stable` / `avalanche` / `elysium` (no `hyperevm`); search: `--chain` is **optional**  -  omit to search all chains; accepts `all` and any chain the search module has enabled, including dynamically-enabled chains such as `tron` / `monad` / `megaeth` / `xlayer`)

### Prerequisites

- `gmgn-cli` installed globally  -  if missing, run: `npm install -g gmgn-cli`
- `GMGN_API_KEY` configured in `~/.config/gmgn/.env`

### Rate Limit Handling

All standard market routes used by this skill use GMGN's plan-based leaky bucket: Free `5/5`, Plus `20/20`, Pro `50/50` (rate/capacity). Sustained throughput is roughly `tier rate ÷ weight` requests/second, and the max burst is roughly `floor(tier capacity ÷ weight)`. The Pro-only `1s` K-line route instead uses the Pro API-key bucket plus its separate shared global bucket.

| Command | Route | Weight |
|---------|-------|--------|
| `market kline` (standard resolutions) | `GET /v1/market/token_kline` | 2 |
| `market kline --resolution 1s` (**Pro only**) | `GET /v1/market/token_kline` | 3 against the Pro API-key bucket; shared global limit: 500 req/s |
| `market trending` | `GET /v1/market/rank` | 3 |
| `market trenches` | `POST /v1/trenches` | 2 |
| `market signal` | `POST /v1/market/token_signal` | 1 |
| `market hot-searches` | `POST /v1/market/hot_searches` | 3 |
| `market search` | `GET /v1/market/search` | 1 |

When a request returns `429`:

- On `RATE_LIMIT_EXCEEDED`, tell the user exactly: `已达到当前套餐的限频上限，点击 https://gmgn.ai/ai?chain=bsc&tab=paid_plans 升级套餐，获得更高速率限制`. Show this upgrade guidance at most once per user task. Do not repeat it for subsequent `RATE_LIMIT_BANNED` responses during the same cooldown.

- Read `X-RateLimit-Reset` from the response headers. It is a Unix timestamp in seconds that marks when the limit is expected to reset.
- If the response body contains `reset_at` (e.g., `{"code":429,"error":"RATE_LIMIT_BANNED","message":"...","reset_at":1775184222}`), extract `reset_at`  -  it is the Unix timestamp when the ban lifts (typically 5 minutes). Convert to local time and tell the user exactly when they can retry.
- The CLI may wait and retry once automatically when the remaining cooldown is short. If it still fails, stop and tell the user the exact retry time instead of sending more requests.
- For `RATE_LIMIT_EXCEEDED` or `RATE_LIMIT_BANNED`, repeated requests during the cooldown can extend the ban by 5 seconds each time, up to 5 minutes. Do not spam retries.
- On `RATE_LIMIT_BANNED_MAX`, the ban has hit the 5-minute ceiling because requests kept arriving during the cooldown. Stop **all** GMGN calls for this task (not just the failing one) and tell the user the exact reset time; any request before `reset_at` resets the ban to 5 minutes again.
- On `403 PLAN_UPGRADE_REQUIRED`, the endpoint costs more rate-limit weight than the user's plan capacity, so it can never succeed on this plan  -  do not retry or wait. Tell the user the endpoint is unavailable on their current plan and show the `upgrade_message` from the response (it contains the upgrade link `https://gmgn.ai/ai?chain=bsc&tab=paid_plans`).

### `market kline` Parameters

| Parameter | Required | Description |
|-----------|----------|-------------|
| `--chain` | Yes | `sol` / `bsc` / `base` / `eth` / `arbitrum` / `hyperevm` / `robinhood` / `arc` / `stable` / `avalanche` / `elysium` |
| `--address` | Yes | Token contract address |
| `--resolution` | Yes | Candlestick resolution: `1s` (**Pro only; at most 500 candles per request**) / `30s` / `1m` / `5m` / `15m` / `1h` / `4h` / `1d` |
| `--from` | No | Start time (Unix seconds) |
| `--to` | No | End time (Unix seconds) |

### `market kline` Response Fields

The response is an object with a `list` array. Each element in `list` is one candlestick:

| Field | Type | Description |
|-------|------|-------------|
| `time` | number | Candle open time  -  Unix timestamp in **seconds** |
| `open` | string | Opening price in USD at the start of the period |
| `close` | string | Closing price in USD at the end of the period |
| `high` | string | Highest price in USD during the period |
| `low` | string | Lowest price in USD during the period |
| `volume` | string | Trading volume in **base token units** (number of tokens traded) |
| `amount` | string | Trading volume in **USD** (dollar value of all trades in this period) |

**Important distinctions (naming is counterintuitive  -  do not guess):**
- `volume` = token count (e.g. `5379110` means ~5.38M tokens changed hands)
- `amount` = USD dollar value (e.g. `1214` means ~$1,214 traded)  -  use this for "how much was traded in USD"
- For tokens not priced at $1, `volume` and `amount` will differ by orders of magnitude (e.g. $1,214 amount = 5,379,110 tokens for a $0.0002 token)
- To get **total USD volume over a time range**, sum `amount` across all candles in the range
- To get **price trend**, read `close` values in chronological order (`time` ascending)
- To detect **volatility**, compare `high` vs `low` within each candle
- Candles are returned in chronological order (oldest first)

### `market trending` Options

**`--interval` selection guide  -  always match to the user's stated time window:**

| User says | `--interval` |
|-----------|-------------|
| "1m trending" / "hottest right now" | `1m` |
| "5m" / "5 minute" | `5m` |
| "1h" / "1 hour" / no time specified (default) | `1h` |
| "6h" / "6 hour" | `6h` |
| "24h" / "today" / "daily" | `24h` |

| Option | Description |
|--------|-------------|
| `--chain` | Required. `sol` / `bsc` / `base` / `eth` / `arbitrum` / `hyperevm` / `robinhood` / `arc` / `stable` / `avalanche` / `elysium` |
| `--interval` | Required. `1m` / `5m` / `1h` / `6h` / `24h` (default `1h`) |
| `--limit <n>` | Number of results (default 100, max 100) |
| `--order-by <field>` | Sort field: `default` / `swaps` / `marketcap` / `history_highest_market_cap` / `liquidity` / `volume` / `holder_count` / `smart_degen_count` / `renowned_count` / `gas_fee` / `price` / `change1m` / `change5m` / `change1h` / `creation_timestamp` |
| `--direction <asc\|desc>` | Sort direction (default `desc`) |
| `--filter <tag...>` | Repeatable filter tags (chain-specific). **⚠️ SOL defaults: `renounced frozen`; BSC/Base/ETH defaults: `not_honeypot verified renounced`.** Omitting `--filter` is NOT "no filter"  -  chain defaults always apply. **sol** tags: `renounced` / `frozen` / `burn` / `token_burnt` / `has_social` / `not_social_dup` / `not_image_dup` / `dexscr_update_link` / `not_wash_trading` / `is_internal_market` / `is_out_market`. **evm** tags: `not_honeypot` / `verified` / `renounced` / `locked` / `token_burnt` / `has_social` / `not_social_dup` / `not_image_dup` / `dexscr_update_link` / `is_internal_market` / `is_out_market` |
| `--platform <name...>` | Repeatable platform filter (chain-specific). **sol**: `Pump.fun` / `pump_mayhem` / `pump_mayhem_agent` / `pump_agent` / `letsbonk` / `bonkers` / `bags` / `memoo` / `liquid` / `bankr` / `zora` / `surge` / `anoncoin` / `moonshot_app` / `wendotdev` / `heaven` / `sugar` / `token_mill` / `believe` / `trendsfun` / `trends_fun` / `jup_studio` / `Moonshot` / `boop` / `xstocks` / `ray_launchpad` / `meteora_virtual_curve` / `pool_ray` / `pool_meteora` / `pool_pump_amm` / `pool_orca`. **bsc**: `fourmeme` / `fourmeme_agent` / `bn_fourmeme` / `four_xmode_agent` / `cubepeg` / `likwid` / `goplus_creator` / `goplus_skills` / `openfour` / `flap` / `flap_stocks` / `flap_aioracle` / `clanker` / `lunafun` / `pool_uniswap` / `pool_pancake`. **base**: `clanker` / `bankr` / `flaunch` / `zora` / `zora_creator` / `baseapp` / `basememe` / `virtuals_v2` / `klik`. **eth**: `trench` / `clanker` / `klik` / `livo` / `stroid` / `pool_uniswap_v2` / `pool_uniswap_v3` / `printr` |

#### `market trending` Range Filters

Optional `--min-*` / `--max-*` flags apply server-side numeric range filtering (inclusive). Unknown metrics are ignored by the service.

| Option | Description |
|--------|-------------|
| `--min-volume` / `--max-volume` | Trading volume (USD) |
| `--min-liquidity` / `--max-liquidity` | Liquidity (USD) |
| `--min-marketcap` / `--max-marketcap` | Market cap (USD) |
| `--min-history-highest-marketcap` / `--max-history-highest-marketcap` | Historical highest market cap (USD) |
| `--min-swaps` / `--max-swaps` | Swap count |
| `--min-holder-count` / `--max-holder-count` | Holder count |
| `--min-gas-fee` / `--max-gas-fee` | Gas fee |
| `--min-renowned-count` / `--max-renowned-count` | KOL / renowned wallet count |
| `--min-smart-degen-count` / `--max-smart-degen-count` | Smart-money holder count |
| `--min-bot-degen-count` / `--max-bot-degen-count` | Bot-degen wallet count |
| `--min-visiting-count` / `--max-visiting-count` | Visitor count |
| `--min-price-change-percent` / `--max-price-change-percent` | Price change ratio over the interval |
| `--min-insider-rate` / `--max-insider-rate` | Insider trading ratio (0-1); tokens lacking this field are excluded |
| `--min-bundler-rate` / `--max-bundler-rate` | Bundle-bot trading ratio (0-1); tokens lacking this field are excluded |
| `--min-entrapment-ratio` / `--max-entrapment-ratio` | Entrapment trading ratio (0-1); tokens lacking this field are excluded |
| `--min-top10-holder-rate` / `--max-top10-holder-rate` | Top-10 holder concentration (0-1) |
| `--min-top70-sniper-hold-rate` / `--max-top70-sniper-hold-rate` | Top-70 sniper holding ratio (0-1) |
| `--min-dev-team-hold-rate` / `--max-dev-team-hold-rate` | Dev-team holding ratio (0-1); `--min-dev-team-hold-rate` also excludes creator-close tokens |

Excerpt. The rest of the file is on the canonical page and in the source repository.

## Gmgn Market FAQ

### What is the difference between volume and amount in kline data?

volume = USD dollar value of trades (e.g. $1,214); amount = token units traded (e.g. 5,379,110 tokens). For tokens not priced at $1, these differ by orders of magnitude. Use volume for 'how much USD was traded' and amount for 'how many tokens changed hands'.

### How do I filter trending tokens for safety?

SOL defaults to renounced+frozen filters; EVM chains default to not_honeypot+verified+renounced. Omitting --filter is NOT no filter  -  chain defaults always apply. Add --filter tags explicitly to override. Quick disqualification: skip if rug_ratio > 0.3 OR is_wash_trading = true O

### What do smart_degen_count and renowned_count mean?

smart_degen_count = number of GMGN-tagged smart money wallets holding the token; renowned_count = number of KOL wallets holding. High values (smart_degen_count >= 3) are bullish signals. These are platform-tagged lists, not user-defined.

### How do I install Gmgn Market Skill?

npx skills add https://github.com/GMGNAI/gmgn-skills --skill gmgn-market

## Machine access

- [Sitemap](https://skillselion.com/sitemap.xml)
- [llms.txt](https://skillselion.com/llms.txt)
- [llms-full.txt](https://skillselion.com/llms-full.txt)
- [Developer resources](https://skillselion.com/developers)
- [OpenAPI spec](https://skillselion.com/openapi.json)
- [MCP handshake](https://skillselion.com/.well-known/mcp)
- [API catalog](https://skillselion.com/.well-known/api-catalog)
- [AI catalog](https://skillselion.com/.well-known/ai-catalog.json)
- [Pricing](https://skillselion.com/pricing.md)
- [Auth](https://skillselion.com/auth.md)
- [AGENTS.md](https://skillselion.com/AGENTS.md)
- [Contact](https://skillselion.com/contact)
- [Home](https://skillselion.com/)
