# Perp Gap API (remote · perp-gap-api.perpgap.workers.dev)

Stock-perp gaps, verdicts and Hyperliquid prediction-market odds vs perp-implied probability. x402.

- Trust score: 60/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `perp-gap-api.perpgap.workers.dev`: 60/100 (this document), [markdown](https://verifymcp.io/servers/dev-workers-perpgap-perp-gap-api-perp-gap/perp-gap-api.md), [page](https://verifymcp.io/servers/dev-workers-perpgap-perp-gap-api-perp-gap/perp-gap-api)

## Channel facts

- Endpoint: `https://perp-gap-api.perpgap.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.4.0`

## 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 2026-10-18.

- **Endpoint Security**: 46/100
  - 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 12 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 enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1913 tokens (~159/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Perp Gap API MCP server?

Perp Gap API is a hosted endpoint at https://perp-gap-api.perpgap.workers.dev/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 dev-workers-perpgap-perp-gap-api-perp-gap 'https://perp-gap-api.perpgap.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-workers-perpgap-perp-gap-api-perp-gap": {
      "url": "https://perp-gap-api.perpgap.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-workers-perpgap-perp-gap-api-perp-gap": {
      "type": "http",
      "url": "https://perp-gap-api.perpgap.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-workers-perpgap-perp-gap-api-perp-gap]
url = "https://perp-gap-api.perpgap.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-workers-perpgap-perp-gap-api-perp-gap": {
      "type": "remote",
      "url": "https://perp-gap-api.perpgap.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-workers-perpgap-perp-gap-api-perp-gap --url 'https://perp-gap-api.perpgap.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-workers-perpgap-perp-gap-api-perp-gap:
    url: "https://perp-gap-api.perpgap.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-workers-perpgap-perp-gap-api-perp-gap": {
      "Transport": "http",
      "Url": "https://perp-gap-api.perpgap.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-workers-perpgap-perp-gap-api-perp-gap -t streamable-http -u 'https://perp-gap-api.perpgap.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-workers-perpgap-perp-gap-api-perp-gap": {
      "type": "http",
      "url": "https://perp-gap-api.perpgap.workers.dev/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.

### 2026-10-18 (score 60, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1370 → 1913
- [functional] Server version: 1.4.0 → 1.5.0
- [functional] New tool “get_funding”
- [functional] New tool “get_quote”
- [functional] New tool “list_markets”

### 2026-10-17 (score 60, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 887 → 1370
- [functional] Server version: 1.1.0 → 1.4.0
- [functional] New tool “get_pm_implied”
- [functional] New tool “get_pm_scan”
- [functional] New tool “list_pm_markets”

### 2026-10-15 (score 59, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-14 (score 58)

First indexed and scored.

## MCP tools (12)

### `list_markets` (~186 tokens)

FREE. Catalog of every stock perp and tokenized stock agents can trade: Hyperliquid trade.xyz, Aster and Lighter perps plus Solana xStocks and Ondo Global Markets tokens. Per market: ticker, venue, symbol / Lighter market_id / Solana mint / Ondo contract, type, live and tradable_now. Use first to see where a ticker trades before get_quote or get_funding.

Input parameters:

- `instrument` (string): perp or token
- `ticker` (string): Comma-separated tickers, e.g. TSLA or TSLA,NVDA. Recommended: without it you get 2,000+ rows.
- `tradable` (boolean): Only markets accepting orders now
- `venue` (string): Comma-separated: hyperliquid-xyz, aster, lighter, xstocks-solana, ondo-gm

### `get_quote` (~142 tokens)

PAID $0.01 (x402, USDC on Base or Solana). Unified live quote for 1-10 stock tickers: perp mark and bid/ask mid on trade.xyz, Aster and Lighter, Solana xStock and Ondo per-share prices, last US close and the reference used (pre/regular/after-hours/overnight/closed), gap % vs reference, perp spread, best bid/ask, cross-venue arb bps, freshness.

Input parameters:

- `ticker` (string): One ticker, e.g. TSLA
- `tickers` (string): Up to 10 comma-separated tickers instead of ticker

### `get_funding` (~147 tokens)

PAID $0.02 (x402, USDC on Base or Solana). Stock-perp funding on trade.xyz, Aster and Lighter normalized to hourly and APR, interval, next funding time, cheapest venue to long or short, carry spread, optional history (24h/7d/30d). tickers='all' returns the board for every stock perp.

Input parameters:

- `history` (string): History window (single ticker)
- `min_spread_apr` (number): Board: minimum APR spread between venues
- `ticker` (string): One ticker, e.g. TSLA
- `tickers` (string): 'all' for the full board

### `get_gap_sample` (~70 tokens)

FREE. Basic perp-vs-stock gap for ONE trade.xyz stock perp (e.g. TSLA): perp mark, reference stock price, gap %. Use get_gaps for xStock gap, basis, funding and open interest.

Input parameters:

- `ticker` (string, required): One ticker, e.g. TSLA

### `get_gaps` (~179 tokens)

PAID $0.01 (x402, USDC on Base or Solana). Gap table for up to 60 trade.xyz stock perps (tickers=all for every auto-discovered US stock perp): perp mark/oracle vs reference stock price and Solana xStock, basis, hourly and annualized funding, open interest. Set venues='all' for a cross-venue comparison: trade.xyz vs Aster vs Lighter mark prices, gap % between venues, and each venue's funding (hourly and annualized).

Input parameters:

- `tickers` (string): Comma-separated tickers or 'all', max 60 per call, e.g. TSLA,NVDA,GME. Defaults to 20 large names.
- `venues` (string): 'all' adds the trade.xyz vs Aster vs Lighter comparison

### `get_verdict` (~153 tokens)

PAID $0.03 (x402, USDC on Base or Solana). Rule-based long/short/watch/avoid verdict for one trade.xyz stock perp, using the perp-vs-stock gap, basis, funding and SEC EDGAR insider and filing signals, with reasons and confidence. Includes a news block (up to 5 items in 48h: SEC 8-K filings, Fed/BLS macro releases, press-wire items as our own one-line summary + link) and a heuristic news_context label (likely news-driven / news present, move small / possibly macro-driven / no matching news). Data, not financial advice.

Input parameters:

- `ticker` (string, required): One ticker, e.g. GME

### `get_history` (~142 tokens)

PAID $0.02 (x402, USDC on Base or Solana). Historical gap time series for one trade.xyz stock perp (up to 90 days; interval 30m/1h/4h/1d): perp vs stock and xStock gaps, basis, funding, OI, plus Aster and Lighter marks and cross-venue gaps.

Input parameters:

- `from` (string): ISO start (UTC), default 7 days ago
- `interval` (string): Default 1h
- `ticker` (string, required): One ticker, e.g. TSLA
- `to` (string): ISO end (UTC), default now

### `get_export` (~72 tokens)

PAID $0.25 (x402, USDC on Base or Solana). Bulk JSON export of one UTC day of 30-minute snapshots for all 20 tracked stock perps (cross-venue gaps, funding, OI).

Input parameters:

- `date` (string): UTC day YYYY-MM-DD, default yesterday

### `get_research_card` (~172 tokens)

PAID $0.03 (x402, USDC on Base or Solana). One-call research card for a single stock perp: spot quote and market session, perp prices on trade.xyz, Aster and Lighter, gap % per venue vs spot and vs the Solana xStock, funding and basis, recent 72h gap history, and the rule-based verdict. Includes a news block (up to 5 items in 48h: SEC 8-K filings, Fed/BLS macro releases, press-wire items as our own one-line summary + link) and a heuristic news_context label (likely news-driven / news present, move small / possibly macro-driven / no matching news). Data, not financial advice.

Input parameters:

- `ticker` (string, required): One ticker, e.g. TSLA

### `list_pm_markets` (~122 tokens)

FREE. Live Hyperliquid HIP-4 binary price outcome markets ('BTC above 82,268 at 2026-10-18 08:00 UTC'): outcome id, asset, strike, expiry, settlement source, bid, ask, depth; empty books filtered. Use first to see what get_pm_implied and get_pm_scan cover. Data, not advice.

Input parameters:

- `asset` (string): Optional underlying, e.g. BTC, ETH, HYPE, SP500, XYZ100, META
- `kind` (string): Default all

### `get_pm_implied` (~176 tokens)

PAID $0.02 (x402, USDC on Base or Solana). Is a Hyperliquid prediction market on a crypto or stock price cheap or expensive? For every live binary price outcome on one asset: bid, ask, depth, the probability implied by the live perp price and 7d realized vol, edge in pp vs bid and ask, liquidity flag and signal. Bad input or no live market is a free error. Data, not advice.

Input parameters:

- `asset` (string): Underlying perp, e.g. BTC, ETH, HYPE, SP500, META (default BTC)
- `min_depth_usd` (number): Hide markets with less USDC within 5 pp of the touch on either side; default 0
- `outcome` (integer): Optional Hyperliquid outcome id

### `get_pm_scan` (~147 tokens)

PAID $0.05 (x402, USDC on Base or Solana). Ranked list of the most mispriced liquid Hyperliquid prediction markets right now across crypto and tokenized-stock binary price markets: model probability vs bid/ask, edge in pp, spread, depth and book age; empty and illiquid books filtered. Data, not advice.

Input parameters:

- `kind` (string): Default all
- `limit` (integer): 1-50, default 20
- `max_spread_pp` (number): Default 10
- `min_depth_usd` (number): Both sides; default 50
- `min_edge_pp` (number): Default 2

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-workers-perpgap-perp-gap-api-perp-gap/perp-gap-api#diagnostics

## Score history

- 2026-10-18: 60
- 2026-10-17: 60
- 2026-10-16: 59
- 2026-10-15: 59
- 2026-10-14: 58

## Common questions

### What is the Perp Gap API MCP server?

Perp Gap API is an MCP server listed in the public MCP registry as dev.workers.perpgap.perp-gap-api/perp-gap. Stock-perp gaps, verdicts and Hyperliquid prediction-market odds vs perp-implied probability. x402. This page covers its hosted endpoint (https://perp-gap-api.perpgap.workers.dev/mcp).

### Is the Perp Gap API MCP server safe to use?

Perp Gap API scores 60 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 Perp Gap API MCP server expose?

Perp Gap API exposes 12 tools: list_markets, get_quote, get_funding, get_gap_sample, get_gaps, and 7 more. Their descriptions and schemas cost roughly 1,708 tokens of context every time the server is loaded.

### Does the Perp Gap API MCP server require authentication?

No. We connected to Perp Gap API without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Perp Gap API MCP server still maintained?

Perp Gap API is still listed as active in the MCP registry. We last reached this channel on 18 October 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://perp-gap-api.perpgap.workers.dev/mcp
- Website: https://perp-gap-api.perpgap.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-workers-perpgap-perp-gap-api-perp-gap/perp-gap-api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-workers-perpgap-perp-gap-api-perp-gap/perp-gap-api.json
- HTML version of this page: https://verifymcp.io/servers/dev-workers-perpgap-perp-gap-api-perp-gap/perp-gap-api