# ai.shumi/mcp (remote · mcp.shumi.ai)

Crypto market intelligence: prices, funding rates, narratives, regime, and delta-neutral research.

- Trust score: 81/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `mcp.shumi.ai`: 81/100 (this document), [markdown](https://verifymcp.io/servers/ai-shumi-mcp/mcp.md), [page](https://verifymcp.io/servers/ai-shumi-mcp/mcp)
- npm · `@shumi-ai/mcp`: 85/100, [markdown](https://verifymcp.io/servers/ai-shumi-mcp/shumi-ai-mcp.md), [page](https://verifymcp.io/servers/ai-shumi-mcp/shumi-ai-mcp)

## Channel facts

- Endpoint: `https://mcp.shumi.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 31 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 88/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 3094 tokens (~93/item across 33 items; 31 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 31 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 33 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the ai.shumi/mcp server?

ai.shumi/mcp is a hosted endpoint at https://mcp.shumi.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-shumi-mcp 'https://mcp.shumi.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-shumi-mcp": {
      "url": "https://mcp.shumi.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-shumi-mcp": {
      "type": "http",
      "url": "https://mcp.shumi.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-shumi-mcp]
url = "https://mcp.shumi.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-shumi-mcp": {
      "type": "remote",
      "url": "https://mcp.shumi.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-shumi-mcp --url 'https://mcp.shumi.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-shumi-mcp:
    url: "https://mcp.shumi.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-shumi-mcp": {
      "Transport": "http",
      "Url": "https://mcp.shumi.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-shumi-mcp -t streamable-http -u 'https://mcp.shumi.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-shumi-mcp": {
      "type": "http",
      "url": "https://mcp.shumi.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-11 (score 81, +1)

- [security] Stability: 0.97 → pass

### 2026-09-09 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes. Other categories moved too: Schema Quality & AI Usability fell 1.

### 2026-09-07 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-04 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-02 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-31 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-29 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-27 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (31)

### `get_coin_risk` (~122 tokens)

Coin risk context

Bundled risk context for one or more coins: price, funding APR, deterministic funding_paying_side, funding_receiving_side, carry_if_long and carry_if_short fields, daily/weekly trend, sentiment stance, and BTC correlation. Funding applies to perpetual positions only; spot positions neither pay nor receive it. Relay the carry fields exactly rather than inferring direction from crowding. The best single tool for "should I be worried about X".

Input parameters:

- `symbols` (array, required): One or more coin symbols, e.g. ["BTC","ETH","SOL"].

Output parameters:

- `data`
- `error`
- `meta`

### `lookup_coin` (~107 tokens)

Look up a coin

Look up a single coin and its core metrics (price, trend, metadata) by symbol, name, CoinGecko/internal id, or on-chain contract address.

Input parameters:

- `by` (string): How `identifier` is interpreted.
- `chain` (string): Chain for contract lookups (ethereum, bsc, solana, base, …). Required when by="contract".
- `identifier` (string, required): The symbol (BTC), name (Bitcoin), id (bitcoin), or contract address.

Output parameters:

- `data`
- `error`
- `meta`

### `resolve_coin` (~65 tokens)

Resolve a coin (fuzzy)

Fuzzily resolve a symbol, name, or contract to canonical coin candidates. Use this first when the user input is ambiguous, before calling other tools.

Input parameters:

- `limit` (integer): Max candidates to return.
- `query` (string, required): Symbol, name, or contract to resolve.

Output parameters:

- `data`
- `error`
- `meta`

### `get_coin_sentiment` (~34 tokens)

Coin sentiment

On-chain/social sentiment aggregates for a single coin.

Input parameters:

- `symbol` (string, required): Coin symbol, e.g. BTC.

Output parameters:

- `data`
- `error`
- `meta`

### `get_coin_historical` (~152 tokens)

Coin metrics at a past point in time

Market cap, volume, open interest, funding rate and price for a coin AS OF a chosen point in the past. Returns a single snapshot, not a series: call it once per point you want to compare (e.g. amount=7 interval=d for a week ago, then again with no offset for now). Use this to answer "how has funding/open interest changed since…".

Input parameters:

- `amount` (integer): How far back to look, in units of `interval`. Omit for the most recent snapshot.
- `interval` (string): Unit for `amount`: h (hours) or d (days). Defaults to hours.
- `symbol` (string, required): Coin symbol, e.g. ETH.

Output parameters:

- `data`
- `error`
- `meta`

### `get_market_health` (~55 tokens)

Market health

Overall market health: the UP/HODL/DOWN trend distribution and extreme movers. Set context for the full bundle.

Input parameters:

- `context` (boolean): Include the full market-context bundle (breadth velocity, regime age, leadership).

Output parameters:

- `data`
- `error`
- `meta`

### `get_global_market` (~23 tokens)

Global market aggregates

Global market aggregates: BTC dominance, total market cap, total volume.

Output parameters:

- `data`
- `error`
- `meta`

### `get_market_crossing` (~58 tokens)

Market trend crossing

The most recent regime crossing — when one trend cohort (UP/HODL/DOWN) overtook another market-wide. Answers "has the market flipped?". Returns an empty `crossings` array plus a message when no crossing has fired.

Output parameters:

- `data`
- `error`
- `meta`

### `get_prices` (~127 tokens)

Bulk live prices

Bulk live prices, optionally with 4h/24h/7d baseline overlays. Omit symbols for the full tracked set.

Input parameters:

- `baselines` (boolean): Include 4h/24h/7d baseline price overlay.
- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `symbols` (string): Comma-separated symbols, e.g. "BTC,ETH,SOL". Omit for all tracked coins.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `scan_trends` (~127 tokens)

Scan trends

Trend scanner. state=fresh (newly started), stale (longest running), aligned (multi-timeframe agreement), extreme (biggest moves), historical.

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `interval` (string): Trend interval: 1d (daily) or 1w (weekly).
- `limit` (integer): Max results.
- `state` (string): Which trend slice to return.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `scan_coins` (~169 tokens)

Scan / filter coins

Filter the tracked universe by trend direction, category, market-cap band, and exchange.

Input parameters:

- `category` (string): Filter by category name, e.g. "Layer 2".
- `exchange` (string): Filter by exchange listing.
- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `interval` (string): Trend interval: 1d (daily) or 1w (weekly).
- `limit` (integer): Max results.
- `mcap_max` (number): Maximum market cap in USD.
- `mcap_min` (number): Minimum market cap in USD.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `trend` (string): Filter by trend direction.

Output parameters:

- `data`
- `error`
- `meta`

### `get_market_sentiment` (~96 tokens)

Market sentiment

Aggregate market sentiment. view=market/latest/summary (overall), narratives, categories, slopes/entity-slopes (what is trending), health (pipeline status).

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `view` (string): Which sentiment view to return.

Output parameters:

- `data`
- `error`
- `meta`

### `list_narratives` (~72 tokens)

List narratives

List the currently active market narratives (e.g. "AI coins", "DeFi summer").

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `get_narrative` (~36 tokens)

Narrative sentiment

Sentiment and momentum for a single named narrative.

Input parameters:

- `name` (string, required): Narrative name, e.g. "AI coins".

Output parameters:

- `data`
- `error`
- `meta`

### `list_categories` (~68 tokens)

List categories

List all tracked crypto categories (DeFi, Layer 2, memes, …).

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `get_category` (~99 tokens)

Category detail

Detail for one category. view=info (trend breakdown), coins (member coins), sentiment.

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `name` (string, required): Category name, e.g. "Layer 2".
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `view` (string): Which category view to return.

Output parameters:

- `data`
- `error`
- `meta`

### `get_funding_momentum` (~101 tokens)

Funding momentum

Perpetual funding-rate positioning context, market-wide or for one symbol. APR is already in percent units (1.7 = 1.7%). Positive funding means longs pay and shorts receive; negative funding means shorts pay and longs receive. Funding is context only, not a standalone directional, timing, or entry signal.

Input parameters:

- `symbol` (string): Restrict to one symbol, e.g. BTC. Omit for the market-wide view.

Output parameters:

- `data`
- `error`
- `meta`

### `get_funding_alerts` (~74 tokens)

Funding alerts

Discrete funding-rate alert events (asset, trigger zone, funding at trigger, fired-at time).

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `get_regime` (~73 tokens)

Market regime

Market regime signals. view=active (current positions), signals (all), confidence (scores). Provide symbol to get that symbol's regime history instead.

Input parameters:

- `symbol` (string): If set, returns regime history for this symbol.
- `view` (string): Which regime view to return (ignored when symbol is set).

Output parameters:

- `data`
- `error`
- `meta`

### `get_signal` (~38 tokens)

Synthesized signal

Synthesized verdict for a coin, combining trend, funding, sentiment and regime.

Input parameters:

- `symbol` (string, required): Coin symbol, e.g. SOL.

Output parameters:

- `data`
- `error`
- `meta`

### `get_signal_quality` (~59 tokens)

Signal quality

Signal validation envelope for an asset: Sharpe ratio, win rate, sample size, reliability tier.

Input parameters:

- `asset` (string, required): Asset symbol, e.g. BTC.
- `signal_type` (string): Signal type (default: mean_reversion).

Output parameters:

- `data`
- `error`
- `meta`

### `get_pair_suggestions` (~206 tokens)

Pair / delta-neutral suggestions

Pair-trading and delta-neutral funding-arbitrage intelligence. mode=suggestions (pair ideas), delta-neutral (funding arb), history (backtest), signal (state for a specific pair — needs token_a & token_b).

Input parameters:

- `dex_only` (boolean): DEX exchanges only (delta-neutral).
- `exchange` (string): Filter by exchange (delta-neutral).
- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `limit` (integer): Max results.
- `mode` (string): Which pair view to return.
- `symbol` (string): Filter by symbol (suggestions / delta-neutral).
- `token_a` (string): First token (required for mode="signal"), e.g. ETH.
- `token_b` (string): Second token (required for mode="signal"), e.g. SOL.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `list_rwa_assets` (~152 tokens)

List real-world assets

List the tradable real-world assets — stocks and ETFs (AAPL, NVDA, SPY), metals and commodities (GOLD, SILVER, BRENT), stock indices (SP500, JP225) and FX. These trade as perps on Hyperliquid builder DEXes and are NOT crypto tokens; the crypto tools will not find them. Use this to answer "which stocks/commodities can I look at?".

Input parameters:

- `dex` (string): Filter by builder-DEX slug, e.g. "xyz".
- `top` (integer): Max assets to return (server default 200; the full universe is ~94).
- `type` (string): Filter by asset class.

Output parameters:

- `data`
- `error`
- `meta`

### `get_rwa_asset` (~143 tokens)

Real-world asset detail

Price, daily/weekly trend and perp funding for one real-world asset (stock, ETF, commodity, index, FX). Look up by ticker (AAPL, GOLD) or by namespaced id (xyz:AAPL). Funding belongs to the PERPETUAL CONTRACT, not the underlying — `funding.apr` is the annualized rate in percent, `funding.rate` is the raw per-hour fraction. Do not use the crypto coin tools for these.

Input parameters:

- `by` (string): How `identifier` is interpreted.
- `identifier` (string, required): Ticker (AAPL, GOLD, SP500) or namespaced id (xyz:AAPL).

Output parameters:

- `data`
- `error`
- `meta`

### `get_holders` (~128 tokens)

Token holder tracking

Tracked token-holder cohorts. view=watchlist (which token contracts are tracked), movements (recent holder-count changes for one contract). Answers "is the holder base growing or bleeding?".

Input parameters:

- `contract` (string): Token contract address. Required when view="movements".
- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `limit` (integer): Max results.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `view` (string): Which holder view to return.

Output parameters:

- `data`
- `error`
- `meta`

### `get_wallets` (~123 tokens)

Wallet tracking

Tracked wallets. view=watchlist (which wallets are tracked), movements (recent balance changes for one wallet address). Answers "what did this wallet do recently?".

Input parameters:

- `address` (string): Wallet address. Required when view="movements".
- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `limit` (integer): Max results.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `view` (string): Which wallet view to return.

Output parameters:

- `data`
- `error`
- `meta`

### `get_futures_signals` (~118 tokens)

Futures signals

Perpetual-futures signal engine. view=state (currently open signals), log (recent fires), history (one asset's past signals — needs asset).

Input parameters:

- `asset` (string): Asset symbol, e.g. BTC. Required when view="history".
- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `view` (string): Which futures view to return.

Output parameters:

- `data`
- `error`
- `meta`

### `get_basket` (~65 tokens)

Basket snapshots

Daily snapshots of the tracked basket — composition and performance over time.

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.

Output parameters:

- `data`
- `error`
- `meta`

### `get_transcripts` (~110 tokens)

Transcript highlights

Highlights mined from tracked video/podcast transcripts. view=highlights (extracted claims with the coins, sectors and macro tags they mention), sources (which channels are tracked). Answers "what are people actually saying about X?".

Input parameters:

- `fields` (string): Token-saving: comma-separated top-level fields to keep.
- `top` (integer): Keep only the first N items (default 50). Raise for more, lower to save tokens.
- `view` (string): Which transcript view to return.

Output parameters:

- `data`
- `error`
- `meta`

### `ask_shumi` (~104 tokens)

Ask Shumi (free-form)

Ask Shumi any crypto-market question in natural language. Shumi classifies the query, fetches the relevant data, and returns a synthesized answer. Use this when no specific typed tool fits, or for multi-part / comparative questions.

Input parameters:

- `archetype` (string): Specialization path (default "base"; e.g. "perp-dex").
- `query` (string, required): The natural-language question, e.g. "is funding extreme on SOL right now?".

Output parameters:

- `answer` (string): The synthesized natural-language answer. Absent only when the engine produced no prose.
- `steps`: Raw engine steps. Present only as a fallback when `answer` is absent.

### `search_web` (~59 tokens)

Search the web

Search the web for crypto information, or get a direct answer. Backed by Shumi's web-search tool.

Input parameters:

- `answer` (boolean): Return a direct synthesized answer instead of raw search results.
- `query` (string, required): What to search for.

Output parameters:

- `answer` (string): The synthesized natural-language answer. Absent only when the engine produced no prose.
- `steps`: Raw engine steps. Present only as a fallback when `answer` is absent.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-shumi-mcp/mcp#diagnostics

## Score history

- 2026-09-20: 81
- 2026-09-19: 81
- 2026-09-18: 81
- 2026-09-17: 81
- 2026-09-16: 81
- 2026-09-15: 81
- 2026-09-14: 81
- 2026-09-13: 81
- 2026-09-12: 81
- 2026-09-11: 81
- 2026-09-10: 80
- 2026-09-09: 80
- 2026-09-08: 79
- 2026-09-07: 79
- 2026-09-06: 78
- 2026-09-05: 78
- 2026-09-04: 78
- 2026-09-03: 77
- 2026-09-02: 77
- 2026-09-01: 76
- 2026-08-31: 76
- 2026-08-30: 75
- 2026-08-29: 75
- 2026-08-28: 74
- 2026-08-27: 74
- 2026-08-26: 73
- 2026-08-25: 72
- 2026-08-24: 72
- 2026-08-23: 71
- 2026-08-22: 71

## Common questions

### What is the ai.shumi/mcp server?

ai.shumi/mcp is listed in the public MCP registry as ai.shumi/mcp. Crypto market intelligence: prices, funding rates, narratives, regime, and delta-neutral research. This page covers its hosted endpoint (https://mcp.shumi.ai/mcp).

### Is the ai.shumi/mcp server safe to use?

ai.shumi/mcp scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ai.shumi/mcp server expose?

ai.shumi/mcp exposes 31 tools: get_coin_risk, lookup_coin, resolve_coin, get_coin_sentiment, get_coin_historical, and 26 more. Their descriptions and schemas cost roughly 2,963 tokens of context every time the server is loaded.

### Does the ai.shumi/mcp server require authentication?

No. We connected to ai.shumi/mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ai.shumi/mcp server still maintained?

ai.shumi/mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.shumi.ai/mcp
- Repository: https://github.com/shumi-ai/shumi-mcp
- Website: https://shumi.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-shumi-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-shumi-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-shumi-mcp/mcp