# KerbTape weekend board (remote · kerbtape.com)

Read-only data on Hyperliquid stock, index and pre-IPO perps: closes, weekend gaps, reopens, history

- Trust score: 75/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `kerbtape.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape.md), [page](https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape)

## Channel facts

- Endpoint: `https://kerbtape.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1055 tokens (~81/item across 13 items; 10 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 40% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 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 KerbTape weekend board MCP server?

KerbTape weekend board is a hosted endpoint at https://kerbtape.com/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 com-kerbtape-weekend-board 'https://kerbtape.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-kerbtape-weekend-board": {
      "url": "https://kerbtape.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-kerbtape-weekend-board": {
      "type": "http",
      "url": "https://kerbtape.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-kerbtape-weekend-board]
url = "https://kerbtape.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-kerbtape-weekend-board --url 'https://kerbtape.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-kerbtape-weekend-board:
    url: "https://kerbtape.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-kerbtape-weekend-board": {
      "Transport": "http",
      "Url": "https://kerbtape.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-kerbtape-weekend-board -t streamable-http -u 'https://kerbtape.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-kerbtape-weekend-board": {
      "type": "http",
      "url": "https://kerbtape.com/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.

### 2026-11-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 74, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 73 → 81
- [functional] Server version: 1.0.1 → 1.1.0
- [functional] New tool “get_market_history”

### 2026-11-17 (score 74, +1)

- [security] Tool “get_scorecard” rewrote its description, which is the text the model reads
- [security] Tool “get_weekend_gaps” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 66 → 73
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0 → 1.0.1
- [cosmetic] Tool “get_weekend_gaps” changed its title: Closed markets by gap → Markets by gap vs last close

### 2026-11-16 (score 73)

First indexed and scored.

## MCP tools (10)

### `search_markets` (~93 tokens)

Find a market

Find Hyperliquid markets (HIP-3 stocks, indices, commodities, pre-IPO, and crypto) by name, ticker or alias. Returns coin ids (for example xyz:NVDA) to pass to the other tools.

Input parameters:

- `limit` (integer)
- `query` (string, required): Name, ticker or alias, e.g. 'nvidia', 'SP500', 'gold', 'nasdaq'

Output parameters:

- `source` (object)

### `get_market` (~80 tokens)

One market now

One Hyperliquid market now: price, last official close, gap vs that close, when real pricing resumes, funding, open interest, price band. Pre-IPO markets come back flagged, without a close.

Input parameters:

- `coin` (string, required): A coin id like xyz:NVDA, a ticker like NVDA, or a name like Nvidia or gold.

Output parameters:

- `source` (object)

### `get_last_close` (~75 tokens)

Last official close

The last official close KerbTape uses for a market: price, time, venue and how it was captured (oracle at the close minute, or estimated from Hyperliquid trades).

Input parameters:

- `coin` (string, required): A coin id like xyz:NVDA, a ticker like NVDA, or a name like Nvidia or gold.

Output parameters:

- `source` (object)

### `get_weekend_gaps` (~125 tokens)

Markets by gap vs last close

The weekend or overnight gap: markets whose home exchange is shut now (nights, weekends, holidays), by their gap vs its last close, largest first, with when real pricing resumes. Markets trading in a real session (cash, extended, overnight) come back apart under moving_now, with their move since the last close, which is not a gap. Optional group: us_stocks, etfs, indices, commodities, korea, japan, china_hk, india, fx, other.

Input parameters:

- `group` (string)
- `limit` (integer)

Output parameters:

- `source` (object)

### `get_reopen_times` (~42 tokens)

Reopen times

When each market group's real pricing resumes (overnight session, futures, cash open), in UTC and New York time, and each home exchange's session state.

Output parameters:

- `source` (object)

### `get_scorecard` (~88 tokens)

Weekend scorecard

The Monday scorecard, as /scorecard leads with it: headline = the weekly scorecard (on how many board markets Hyperliquid's weekend price was closer to the reopen than Friday's close, with the median errors); then, labelled, our posts graded at each market's first real print and the running rate over every weekend. Each with its definition. History, not a forecast.

Output parameters:

- `source` (object)

### `get_ipo` (~55 tokens)

IPO board

An IPO board (default ANT, Anthropic): offer range with its filing and source, pricing and first trade dates with their status, and Hyperliquid's pre-IPO market as data.

Input parameters:

- `ticker` (string)

Output parameters:

- `source` (object)

### `get_preipo_markets` (~48 tokens)

Pre-IPO markets

Every pre-IPO perp listed on Hyperliquid's HIP-3 deployers, with mark, implied valuation where a share count is on record, and listing status. Data only.

Output parameters:

- `source` (object)

### `get_market_history` (~155 tokens)

One market's graded weekends

One market's graded weekends, newest first: the last close before the weekend, Hyperliquid's weekend price 5 minutes before real pricing returned, the actual reopen, the grade (was the weekend price closer to the reopen than the close?) and the dates, plus the market's hit rate with its 95% interval. The same rows as /history and /scorecard. Paginated (page, limit up to 52). History, not a forecast; pre-IPO markets have no graded weekend.

Input parameters:

- `coin` (string, required): A coin id like xyz:NVDA, a ticker like NVDA, or a name like Nvidia or gold.
- `limit` (integer)
- `page` (integer)

Output parameters:

- `source` (object)

### `get_fees` (~46 tokens)

KerbTape fees

KerbTape's builder fee schedule (basis points by tier and market class, the approved maximum), added on top of Hyperliquid's own fees. The data board is free.

Output parameters:

- `source` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 75
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 74
- 2026-11-16: 73

## Common questions

### What is the KerbTape weekend board MCP server?

KerbTape weekend board is an MCP server listed in the public MCP registry as com.kerbtape/weekend-board. Read-only data on Hyperliquid stock, index and pre-IPO perps: closes, weekend gaps, reopens, history. This page covers its hosted endpoint (https://kerbtape.com/mcp).

### Is the KerbTape weekend board MCP server safe to use?

KerbTape weekend board scores 75 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 KerbTape weekend board MCP server expose?

KerbTape weekend board exposes 10 tools: search_markets, get_market, get_last_close, get_weekend_gaps, get_reopen_times, and 5 more. Their descriptions and schemas cost roughly 807 tokens of context every time the server is loaded.

### Does the KerbTape weekend board MCP server require authentication?

No. We connected to KerbTape weekend board without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the KerbTape weekend board MCP server still maintained?

KerbTape weekend board is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the KerbTape weekend board MCP server?

VerifyMCP ran 13 checks on KerbTape weekend board, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://kerbtape.com/mcp
- Website: https://kerbtape.com/ai
- Changelog RSS feed: https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape.json
- HTML version of this page: https://verifymcp.io/servers/com-kerbtape-weekend-board/kerbtape
