# AgentZ (remote · agent-z.app)

Daily 8 long calls on Hyperliquid, wallet health checks, order building and risk sizing.

- Trust score: 25/100 (low)
- Change this week: −49
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agent-z.app`: 25/100 (this document), [markdown](https://verifymcp.io/servers/jafrancis021-max-agentz/api-public-mcp-2.md), [page](https://verifymcp.io/servers/jafrancis021-max-agentz/api-public-mcp-2)

## Channel facts

- Endpoint: `https://agent-z.app/api/public/mcp?src=registry`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.3.1`

## 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 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - 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**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the AgentZ MCP server?

AgentZ is a hosted endpoint at https://agent-z.app/api/public/mcp?src=registry, 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 jafrancis021-max-agentz 'https://agent-z.app/api/public/mcp?src=registry'
```

### Cursor

```json
{
  "mcpServers": {
    "jafrancis021-max-agentz": {
      "url": "https://agent-z.app/api/public/mcp?src=registry"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jafrancis021-max-agentz": {
      "type": "http",
      "url": "https://agent-z.app/api/public/mcp?src=registry"
    }
  }
}
```

### Codex

```toml
[mcp_servers.jafrancis021-max-agentz]
url = "https://agent-z.app/api/public/mcp?src=registry"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jafrancis021-max-agentz": {
      "type": "remote",
      "url": "https://agent-z.app/api/public/mcp?src=registry",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jafrancis021-max-agentz --url 'https://agent-z.app/api/public/mcp?src=registry' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  jafrancis021-max-agentz:
    url: "https://agent-z.app/api/public/mcp?src=registry"
```

### Netclaw

```json
{
  "McpServers": {
    "jafrancis021-max-agentz": {
      "Transport": "http",
      "Url": "https://agent-z.app/api/public/mcp?src=registry"
    }
  }
}
```

### Vellum

```bash
assistant mcp add jafrancis021-max-agentz -t streamable-http -u 'https://agent-z.app/api/public/mcp?src=registry'
```

### Other

```json
{
  "mcpServers": {
    "jafrancis021-max-agentz": {
      "type": "http",
      "url": "https://agent-z.app/api/public/mcp?src=registry"
    }
  }
}
```

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.

### 2026-11-02 (score 25, −50)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.63 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-10-31 (score 75, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “risk_check” rewrote its description, which is the text the model reads
- [security] Tool “request_capability” rewrote its description, which is the text the model reads
- [security] Tool “ask_agentz” rewrote its description, which is the text the model reads
- [security] Tool “build_order” rewrote its description, which is the text the model reads
- [security] Tool “get_agentz_index” rewrote its description, which is the text the model reads
- [security] Tool “get_daily_8” rewrote its description, which is the text the model reads
- [security] Tool “get_exits_due” rewrote its description, which is the text the model reads
- [security] Tool “get_owner_brief” rewrote its description, which is the text the model reads
- [security] Tool “get_track_record” rewrote its description, which is the text the model reads
- [cosmetic] “ask_agentz” reworded the description of “message”
- [cosmetic] “ask_agentz” reworded the description of “signature”
- [cosmetic] “get_daily_8” reworded the description of “message”
- [cosmetic] “get_daily_8” reworded the description of “signature”
- [cosmetic] “get_exits_due” reworded the description of “message”
- [cosmetic] “get_exits_due” reworded the description of “signature”
- [cosmetic] “get_open_calls” reworded the description of “message”
- [cosmetic] “get_open_calls” reworded the description of “signature”
- [cosmetic] Tool “ask_agentz” changed its title: Ask AgentZ → Ask EDGE
- [cosmetic] Tool “get_agentz_index” changed its title: AgentZ indexes and funding rate → EDGE indexes and funding rate
- [cosmetic] Tool “get_track_record” changed its title: AgentZ track record → EDGE track record

### 2026-10-29 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] New tool “get_agentz_index”

### 2026-10-22 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-18 (score 69, +44)

- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “ask_agentz” rewrote its description, which is the text the model reads
- [security] Tool “get_exits_due” rewrote its description, which is the text the model reads
- [security] Tool “get_open_calls” rewrote its description, which is the text the model reads
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.17
- [functional improvement] MCP protocol: unverified → pass

## MCP tools (18)

### `get_access_message` (~50 tokens)

Get wallet access message

Free. Returns a message for your wallet to sign (valid 24h). Signing costs nothing and cannot move funds.

Input parameters:

- `wallet` (string, required): Your Hyperliquid wallet address (0x…).

### `request_capability` (~90 tokens)

Request a capability

Free. Tell EDGE what market data, analysis or trading tool you need that is not in this list (any market or venue). Requests decide what is built next.

Input parameters:

- `example` (string): Optional. An example input and the answer you would want back.
- `need` (string, required): What you need, in plain words, e.g. 'liquidation levels for SOL on Hyperliquid'.

### `get_daily_8_preview` (~67 tokens)

DAILY 8 preview

Free, no wallet or signature needed. Today's DAILY 8 long calls on Hyperliquid (symbol, category, rank; entry, stop and size withheld) plus every live call closed since 27 Sep 2026 with its result, and the steps to unlock live orders.

### `get_daily_8` (~182 tokens)

DAILY 8 calls

Today's assigned EDGE basket as execution-ready Hyperliquid orders: symbol, entry reference, stop, exit time and max size in USD for your wallet. 8 calls on normal days, 4 on defensive days. Pass your wallet: if it has approved EDGE's builder fee, no signature is needed; otherwise sign the access message (first day free). Without either it returns the free preview.

Input parameters:

- `message` (string): Optional if the wallet has approved EDGE's builder fee. The exact message returned by get_access_message.
- `risk_pct` (number): Risk per trade in percent. Default 0.375, max 0.5.
- `signature` (string): Optional if the wallet has approved EDGE's builder fee. personal_sign signature of message by wallet.
- `wallet` (string, required): Your Hyperliquid wallet address (0x…).

### `get_exits_due` (~103 tokens)

Calls due to exit

EDGE calls your wallet still holds that have reached their exit time and should be closed now. Free and open; pass wallet.

Input parameters:

- `message` (string): Optional if the wallet has approved EDGE's builder fee. The exact message returned by get_access_message.
- `signature` (string): Optional if the wallet has approved EDGE's builder fee. personal_sign signature of message by wallet.
- `wallet` (string, required): Your Hyperliquid wallet address (0x…).

### `get_open_calls` (~96 tokens)

Open calls

Your assigned calls still inside their 48-hour hold window. Free and open; pass wallet.

Input parameters:

- `message` (string): Optional if the wallet has approved EDGE's builder fee. The exact message returned by get_access_message.
- `signature` (string): Optional if the wallet has approved EDGE's builder fee. personal_sign signature of message by wallet.
- `wallet` (string, required): Your Hyperliquid wallet address (0x…).

### `get_track_record` (~41 tokens)

EDGE track record

Free. EDGE's canonical record, months labelled replay or live. Replay calls after an estimated 0.15% cost per trade; live calls before costs.

### `get_owner_brief` (~60 tokens)

Owner brief

Free. A short factual summary for the agent's human owner: what EDGE is, price, record, risks and how to revoke. Pass wallet to record it.

Input parameters:

- `wallet` (string): Your Hyperliquid wallet address (0x…).

### `agent_health_check` (~93 tokens)

Trading health check

Free. A factual review of any wallet's public Hyperliquid perp trading over the last 30 days: volume, realised P&L, win rate, fees in bps, holding time, weekend vs weekday results, largest fill vs market volume, and builder-code share. Describes and compares only; not advice.

Input parameters:

- `wallet` (string, required): The Hyperliquid wallet address to review (0x…).

### `build_order` (~212 tokens)

Build an unsigned order

Free. Returns a ready-to-sign Hyperliquid order for your own wallet or API wallet: entry (limit-first post-only at the best price, with a market fallback, or market), optional protective stop, and leverage action, all carrying EDGE's 5 bps builder code. Also checks whether the wallet has approved the builder fee. EDGE never holds your keys.

Input parameters:

- `leverage` (number): Leverage for the leverage action, default 2.
- `market` (string, required): Hyperliquid market, e.g. BTC, ETH or xyz:TSLA.
- `order_type` (string): Default limit_first.
- `reduce_only` (boolean): True to only reduce an existing position.
- `side` (string, required)
- `size_usd` (number, required): Order size in USD notional (minimum 10).
- `stop_pct` (number): Optional protective stop distance in percent, e.g. 4.
- `wallet` (string): Optional. Your wallet, to check builder-fee approval.

### `risk_check` (~152 tokens)

Risk check

Free. Describes a proposed trade against your Hyperliquid account and the market: risk in USD and % of equity at the stop, margin needed vs free margin, and the order as a share of the market's 24-hour volume, compared with EDGE's own limits. Factual, not advice.

Input parameters:

- `leverage` (number): Leverage, default 2.
- `market` (string, required): Hyperliquid market, e.g. BTC or xyz:TSLA.
- `size_usd` (number, required): Proposed size in USD notional.
- `stop_pct` (number): Stop distance in percent, default 4.
- `wallet` (string, required): Your Hyperliquid wallet address (0x…).

### `weekend_gap` (~75 tokens)

Weekend gap

Free. A tokenized stock, index or commodity on Hyperliquid vs its Hyperliquid price at the last Friday US close: gap %, range since, and hours to the next US open.

Input parameters:

- `market` (string, required): Hyperliquid market, e.g. xyz:TSLA, xyz:GOLD, xyz:CL.

### `trade_conditions` (~81 tokens)

Trade conditions by hour

Free. When a Hyperliquid market trades most and least (UTC hours), volatility by hour, weekend vs weekday volume, and the spread right now.

Input parameters:

- `days` (number): Look-back in days, 3 to 30. Default 14.
- `market` (string, required): Hyperliquid market, e.g. BTC or xyz:TSLA.

### `event_calendar` (~92 tokens)

Market event calendar

Free. Scheduled releases that move markets: Fed decisions, US CPI, jobs report, PPI, JOLTS, and EIA oil and gas reports. Optionally filtered to what affects one market.

Input parameters:

- `days` (number): Days ahead, 1 to 60. Default 14.
- `market` (string): Optional Hyperliquid market to filter by, e.g. xyz:CL or BTC.

### `crypto_positioning` (~58 tokens)

Crypto funding and open interest

Free. Funding (per 8 hours and annualised) and open interest for a crypto coin across Hyperliquid, Bybit, OKX and Binance.

Input parameters:

- `coin` (string, required): Coin, e.g. BTC, ETH, SOL.

### `get_agentz_index` (~98 tokens)

EDGE indexes and funding rate

Free. The EDGE index family on Hyperliquid prices (Silicon, Backbone, Frontier, Core, Private AI, HL 10): level, constituents and month-by-month change, plus the EDGE Funding Rate (the cost of leverage across Hyperliquid) and the hash-chained public record. Pass index to get one.

Input parameters:

- `index` (string): Optional: silicon, backbone, frontier, core, private_ai or hl10.

### `wallet_intel_menu` (~63 tokens)

Wallet intelligence menu

Free. Headlines on how ~7-8k tracked Hyperliquid wallets are positioned in the biggest markets, plus the paid wallet answers (smart-money, liquidation-map, wallet-profile) with their x402 URLs and price ($0.02 USDC on Base).

### `ask_agentz` (~108 tokens)

Ask EDGE

Ask the EDGE assistant a question (record, prices, risk, integration). Free and open; pass wallet.

Input parameters:

- `message` (string): Optional if the wallet has approved EDGE's builder fee. The exact message returned by get_access_message.
- `question` (string, required): Your question.
- `signature` (string): Optional if the wallet has approved EDGE's builder fee. personal_sign signature of message by wallet.
- `wallet` (string, required): Your Hyperliquid wallet address (0x…).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/jafrancis021-max-agentz/api-public-mcp-2#diagnostics

## Score history

- 2026-11-05: 25
- 2026-11-04: 25
- 2026-11-03: 25
- 2026-11-02: 25
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 74
- 2026-10-29: 74
- 2026-10-28: 73
- 2026-10-27: 73
- 2026-10-26: 72
- 2026-10-25: 72
- 2026-10-24: 72
- 2026-10-23: 71
- 2026-10-22: 71
- 2026-10-21: 70
- 2026-10-20: 70
- 2026-10-19: 69
- 2026-10-18: 69
- 2026-10-17: 25
- 2026-10-16: 68
- 2026-10-15: 68
- 2026-10-14: 67
- 2026-10-13: 67

## Common questions

### What is the AgentZ MCP server?

AgentZ is an MCP server listed in the public MCP registry as io.github.jafrancis021-max/agentz. Daily 8 long calls on Hyperliquid, wallet health checks, order building and risk sizing. This page covers its hosted endpoint (https://agent-z.app/api/public/mcp?src=registry).

### Is the AgentZ MCP server safe to use?

AgentZ scores 25 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 AgentZ MCP server expose?

AgentZ exposes 18 tools: get_access_message, request_capability, get_daily_8_preview, get_daily_8, get_exits_due, and 13 more. Their descriptions and schemas cost roughly 1,721 tokens of context every time the server is loaded.

### Does the AgentZ MCP server require authentication?

Its publisher declares no required credentials for AgentZ. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the AgentZ MCP server still maintained?

AgentZ is still listed as active in the MCP registry. We last reached this channel on 5 November 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://agent-z.app/api/public/mcp?src=registry
- Website: https://agent-z.app/
- Changelog RSS feed: https://verifymcp.io/servers/jafrancis021-max-agentz/api-public-mcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/jafrancis021-max-agentz/api-public-mcp-2.json
- HTML version of this page: https://verifymcp.io/servers/jafrancis021-max-agentz/api-public-mcp-2