# SCRIPTMASTERLABS — HIVE402 (remote · hive402.scriptmasterlabs.com)

Live x402 market for AI agents: 43k paid endpoints, 2,188 sellers, verified payable, 6 rails.

- Trust score: 64/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `hive402.scriptmasterlabs.com`: 64/100 (this document), [markdown](https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402.md), [page](https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402)

## Channel facts

- Endpoint: `https://hive402.scriptmasterlabs.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**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (submit_mission_payment).
  - 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**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2526 tokens (~148/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 34% 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 17 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 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 SCRIPTMASTERLABS — HIVE402 MCP server?

SCRIPTMASTERLABS — HIVE402 is a hosted endpoint at https://hive402.scriptmasterlabs.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-scriptmasterlabs-hive402 'https://hive402.scriptmasterlabs.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-scriptmasterlabs-hive402": {
      "url": "https://hive402.scriptmasterlabs.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-scriptmasterlabs-hive402": {
      "type": "http",
      "url": "https://hive402.scriptmasterlabs.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-scriptmasterlabs-hive402]
url = "https://hive402.scriptmasterlabs.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-scriptmasterlabs-hive402": {
      "type": "remote",
      "url": "https://hive402.scriptmasterlabs.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-scriptmasterlabs-hive402 --url 'https://hive402.scriptmasterlabs.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-scriptmasterlabs-hive402:
    url: "https://hive402.scriptmasterlabs.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-scriptmasterlabs-hive402": {
      "Transport": "http",
      "Url": "https://hive402.scriptmasterlabs.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-scriptmasterlabs-hive402 -t streamable-http -u 'https://hive402.scriptmasterlabs.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-scriptmasterlabs-hive402": {
      "type": "http",
      "url": "https://hive402.scriptmasterlabs.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 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-18 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 62, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “plan_mission” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 64% → 34%
- [functional improvement] Schema quality: 173 → 143
- [functional] New tool “compare_listings”
- [functional] New tool “get_trust”
- [functional] New tool “proxy_call”
- [functional] New tool “route_task”
- [functional] New tool “search_ranked”
- [functional] New tool “validate_input”
- [cosmetic] “plan_mission” reworded the description of “asset”
- [cosmetic] “search_catalog” reworded the description of “network”

### 2026-11-15 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 62, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-13 (score 62, +1)

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

### 2026-11-12 (score 61, −3)

- [security regression] HSTS header: pass → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “list_endpoint” rewrote its description, which is the text the model reads
- [security] Tool “prepare_mission_step” rewrote its description, which is the text the model reads
- [security] Tool “submit_mission_payment” rewrote its description, which is the text the model reads
- [security] Tool “plan_mission” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 90 → 103
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 43% → 63%
- [functional improvement] Tool coverage: 43% → 52%
- [functional] MCP protocol: Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
- [functional] MCP protocol version: 2026-07-28 → 2025-11-25
- [cosmetic] “list_endpoint” added an optional parameter “settlement_route”
- [cosmetic] “submit_mission_payment” added an optional parameter “paymentPayload”
- [cosmetic] “submit_mission_payment” added an optional parameter “paymentSignature”
- [cosmetic] “submit_mission_payment” reworded the description of “signedTxBlob”
- [cosmetic] “plan_mission” reworded the description of “asset”
- [cosmetic] “plan_mission” reworded the description of “budget”
- [cosmetic] “submit_mission_payment” made “signedTxBlob” optional

## MCP tools (17)

### `search_catalog` (~121 tokens)

Search marketplace catalog

Search live paid x402 endpoints settled by OMNIGATE or 402Proof, filtered by text, network and max price.

Input parameters:

- `limit` (integer): Max results, default 20.
- `max_price` (number): Maximum price per call in the listing's asset units.
- `network` (string): Base, Arc, XRPL, Xahau, Solana, MultiversX, or a CAIP-2 id like eip155:8453.
- `query` (string): Words to match in name, description or seller host.

### `get_listing` (~36 tokens)

Get listing details

Get full details for one marketplace listing by id, including example input and output.

Input parameters:

- `id` (string, required): Listing id from search_catalog.

### `start_purchase` (~52 tokens)

Start a purchase

Request a listing unpaid and return its live x402 payment challenge plus the exact steps to pay through OMNIGATE or 402Proof. Nothing is charged.

Input parameters:

- `id` (string, required): Listing id from search_catalog.

### `list_endpoint` (~151 tokens)

List a paid endpoint

List your own x402 endpoint in the market for free. It is called unpaid and listed only if it returns a valid x402 v2 challenge on an OMNIGATE or 402Proof network. Settlement defaults to direct to your payTo at 0% HIVE402 take; pass settlement_route 'omnigate' to opt in to OMNIGATE routing (Base USDC only: receipt token per settlement, 0.005 USDC fee inside settlement, waived inside the daily budget).

Input parameters:

- `method` (string): HTTP method buyers use, default GET.
- `settlement_route` (string): Settlement route, default 'direct'.
- `url` (string, required): Full https URL of the paid endpoint.

### `plan_mission` (~217 tokens)

Plan a budgeted mission

Suggest up to three live catalog services for a task on one payment rail, within a spending ceiling. No payment or task execution occurs; review endpoint inputs and fee legs. Rail and asset must be a settleable pair (canonical map, src/rails.mjs): Base/Arc/Solana settle in USDC, XRPL in XRP or RLUSD, Xahau in XAH, MultiversX in EGLD, MEX or USDC — any other pair is rejected with an error, never silently re-railed.

Input parameters:

- `asset` (string, required): Asset label; must pair with network: Base→USDC, Arc→USDC, XRPL→XRP or RLUSD, Xahau→XAH, Solana→USDC, MultiversX→EGLD, MEX or USDC.
- `budget` (string, required): Spending ceiling as a decimal string, up to 6 decimal places.
- `maxSteps` (integer)
- `network` (string, required)
- `task` (string, required)

### `get_recipes` (~39 tokens)

Get live service recipes

Get reusable catalog-matched task templates with current listing IDs on a single rail. Templates are not verified completed workflows; budget is expressed in atomic units.

### `check_services` (~45 tokens)

Check and rank service responses

Probe up to three catalog endpoints unpaid and rank valid live payment challenges by observed response time. Does not measure historical uptime, paid success or outcome quality.

Input parameters:

- `ids` (array, required)

### `prepare_mission_step` (~120 tokens)

Prepare an approved mission step

Recheck an approved listing's current x402 challenge against expected payout, rail, price and remaining atomic budget. For XRP (402Proof, website-verified sellers) and Base USDC (OMNIGATE, verified-payable sellers) steps the result carries execution.available with an executionToken when tracked execution is offered. Caller must inspect fees and sign; this tool never pays.

Input parameters:

- `approved` (boolean, required): Confirm the caller reviewed and approved the plan. Not wallet authorization.
- `remainingAtomic` (string, required)
- `snapshot` (object, required)

### `check_watchlist` (~48 tokens)

Check listing changes

Compare caller-held snapshots with the live public catalog for price, payment-term and catalog-presence changes. Callers retain snapshots and schedule polling; no push delivery.

Input parameters:

- `previous` (array, required)

### `submit_mission_payment` (~316 tokens)

Submit a caller-signed Mission payment

Submit a caller-signed Mission payment for a prepared step and record confirmed settlement once. XRP steps: signedTxBlob (the caller's signed XRP transaction) settles through the verified seller's 402Proof key; fees accrued = HIVE402 platform fee 10% plus 402Proof facilitator fee $0.0100, kept separate. Base USDC steps: paymentPayload (decoded x402 payload object carrying the EIP-3009 signature + authorization) or paymentSignature (the same payload base64-encoded, as in the PAYMENT-SIGNATURE header) settles through OMNIGATE; fees accrued = HIVE402 platform fee 10% plus the OMNIGATE facilitator fee from the settlement receipt (0.005 USDC when charged, 0 when waived), kept separate. Base settlement is recorded only after OMNIGATE success AND on-chain confirmation. Exactly one payment form must be supplied, matching the prepared step's rail. Never signs or holds funds; does not execute seller task inputs.

Input parameters:

- `executionToken` (string, required)
- `feeApproved` (boolean, required)
- `paymentPayload` (object): Base steps only: the decoded x402 payment payload object (alternative to paymentSignature).
- `paymentSignature` (string): Base steps only: base64-encoded x402 payment payload (the PAYMENT-SIGNATURE value) carrying the caller's EIP-3009 signature and authorization.
- `signedTxBlob` (string): XRP steps only: the caller-signed XRP transaction blob (hex).

### `list_board_posts` (~93 tokens)

Read the HIVE402 Board

Read the HIVE402 Board — the market's public message board: ScriptMasterLabs announcements, system posts generated at read time from live catalog and subscription data (aggregate counts only), and posts from claimed operator profiles (new products, upgrades, announcements, requests). Free and read-only. The same content is at GET /api/public/board.

Input parameters:

- `limit` (integer): Max posts to return, default 20.

### `route_task` (~96 tokens)

Route a task to the best live endpoint

Describe what you need; get the best payable x402 endpoint plus fallbacks, each re-challenged live seconds ago, with payment requirements and exact call instructions. Optionally validates your input against each candidate's schema.

Input parameters:

- `asset` (string)
- `input` (object)
- `limit` (integer)
- `max_usd` (number)
- `network` (string)
- `task` (string, required)

### `proxy_call` (~94 tokens)

Call a listed endpoint (unpaid or with your payment signature)

Forwards one call to a catalog listing. Without payment_signature returns the decoded 402 challenge. With payment_signature (base64 PAYMENT-SIGNATURE you signed) forwards it untouched and returns the seller's response and receipt. HIVE402 never signs or re-sends a paid call.

Input parameters:

- `id` (string)
- `input` (object)
- `payment_signature` (string)
- `url` (string)

### `search_ranked` (~96 tokens)

Ranked search

Search the catalog ranked by relevance × trust × on-chain demand × latency × price, with score breakdowns and intel fields.

Input parameters:

- `has_spec` (boolean)
- `limit` (integer)
- `max_usd` (number)
- `min_trust` (integer)
- `network` (string)
- `payable_only` (boolean)
- `query` (string)
- `sort` (string)

### `get_trust` (~49 tokens)

Trust report

Explained 0–100 trust score for one listing: probe uptime, on-chain demand, call spec, latency, operator claim, and junk/sanctions flags.

Input parameters:

- `id` (string, required)

### `compare_listings` (~36 tokens)

Compare listings

Side-by-side price, trust, uptime, latency and real demand for 2–10 listings.

Input parameters:

- `ids` (array, required)

### `validate_input` (~39 tokens)

Validate input before paying

Check an input against a listing's call spec and get the exact request to send.

Input parameters:

- `id` (string, required)
- `input` (object, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402#diagnostics

## Score history

- 2026-11-21: 64
- 2026-11-20: 64
- 2026-11-19: 63
- 2026-11-18: 63
- 2026-11-17: 62
- 2026-11-16: 63
- 2026-11-15: 63
- 2026-11-14: 62
- 2026-11-13: 62
- 2026-11-12: 61
- 2026-11-11: 64
- 2026-11-10: 63

## Common questions

### What is the SCRIPTMASTERLABS — HIVE402 MCP server?

SCRIPTMASTERLABS — HIVE402 is an MCP server listed in the public MCP registry as com.scriptmasterlabs/hive402. Live x402 market for AI agents: 43k paid endpoints, 2,188 sellers, verified payable, 6 rails. This page covers its hosted endpoint (https://hive402.scriptmasterlabs.com/mcp).

### Is the SCRIPTMASTERLABS — HIVE402 MCP server safe to use?

SCRIPTMASTERLABS — HIVE402 scores 64 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 SCRIPTMASTERLABS — HIVE402 MCP server expose?

SCRIPTMASTERLABS — HIVE402 exposes 17 tools: search_catalog, get_listing, start_purchase, list_endpoint, plan_mission, and 12 more. Their descriptions and schemas cost roughly 1,648 tokens of context every time the server is loaded.

### Does the SCRIPTMASTERLABS — HIVE402 MCP server require authentication?

No. We connected to SCRIPTMASTERLABS — HIVE402 without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SCRIPTMASTERLABS — HIVE402 MCP server still maintained?

SCRIPTMASTERLABS — HIVE402 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 SCRIPTMASTERLABS — HIVE402 MCP server?

VerifyMCP ran 13 checks on SCRIPTMASTERLABS — HIVE402, 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://hive402.scriptmasterlabs.com/mcp
- Website: https://hive402.scriptmasterlabs.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402.json
- HTML version of this page: https://verifymcp.io/servers/com-scriptmasterlabs-hive402/hive402
