# m2m.monster (Devnet sandbox) (remote · sandbox.m2m.monster)

Non-custodial x402 payments between AI agents on Solana. Returns unsigned transactions.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `sandbox.m2m.monster`: 63/100 (this document), [markdown](https://verifymcp.io/servers/monster-m2m-m2m-monster/sandbox.md), [page](https://verifymcp.io/servers/monster-m2m-m2m-monster/sandbox)

## Channel facts

- Endpoint: `https://sandbox.m2m.monster/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-10-17.

- **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 3 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**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 826 tokens (~82/item across 10 items; 10 tools + 0 resources), lean.
  - 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**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "build_refund" implies "refund" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 10 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 m2m.monster (Devnet sandbox) MCP server?

m2m.monster (Devnet sandbox) is a hosted endpoint at https://sandbox.m2m.monster/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 monster-m2m-m2m-monster 'https://sandbox.m2m.monster/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "monster-m2m-m2m-monster": {
      "url": "https://sandbox.m2m.monster/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "monster-m2m-m2m-monster": {
      "type": "http",
      "url": "https://sandbox.m2m.monster/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.monster-m2m-m2m-monster]
url = "https://sandbox.m2m.monster/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "monster-m2m-m2m-monster": {
      "type": "remote",
      "url": "https://sandbox.m2m.monster/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add monster-m2m-m2m-monster --url 'https://sandbox.m2m.monster/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  monster-m2m-m2m-monster:
    url: "https://sandbox.m2m.monster/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "monster-m2m-m2m-monster": {
      "Transport": "http",
      "Url": "https://sandbox.m2m.monster/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add monster-m2m-m2m-monster -t streamable-http -u 'https://sandbox.m2m.monster/mcp'
```

### Other

```json
{
  "mcpServers": {
    "monster-m2m-m2m-monster": {
      "type": "http",
      "url": "https://sandbox.m2m.monster/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.

### 2026-10-16 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 62, +1)

- [security] Tool “build_payment” rewrote its description, which is the text the model reads
- [security] Tool “build_refund” rewrote its description, which is the text the model reads
- [security] Tool “submit_payment” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-10-13 (score 61)

First indexed and scored.

## MCP tools (10)

### `get_pricing` (~28 tokens)

Agent-to-agent fee formula, referral program and the whitelisted token mints of this network.

### `quote_payment` (~151 tokens)

Price a payment to a payee: gross amount, net amount to the payee, fee_gross, discount, fee_net, treasury, mint and a 30-second expiry. Returns a signed quote.

Input parameters:

- `amount` (string, required): Integer amount in base units of the mint
- `idempotency_key` (string): Reuse the same key when retrying
- `mint` (string, required): Payment token mint (exact whitelisted address)
- `network` (string, required): CAIP-2 network id, e.g. solana:EtWTRABZaYq6iMfeYKouRu166VU2xqa1
- `payee` (string, required): Wallet that receives the payment

### `build_payment` (~156 tokens)

Build the m2m-split transaction for a quote: the payer's transfer to the payee and the USDC fee transfer to the treasury, in one atomic transaction where the payer pays its own gas. Checks that the receiving token accounts exist and that the payer holds USDC for the fee, and simulates it. Unsigned. Sign it locally with your own Solana key; m2m.monster never sees or uses agents' private keys.

Input parameters:

- `max_compute_unit_price` (string): Lower priority fee cap in micro-lamports per compute unit
- `payer` (string, required): The payer wallet; it signs and pays the network fee
- `quote` (object, required): The signed quote exactly as returned by quote_payment

### `verify_payment` (~74 tokens)

For the payee: check a payer-signed transaction against its quote (net amount, fee to the treasury, whitelisted mints, quote id and expiry) and simulate it before submitting.

Input parameters:

- `quote` (object, required): The signed quote exactly as returned by quote_payment
- `transaction` (string, required): Base64 wire transaction

### `submit_payment` (~88 tokens)

Broadcast a transaction the payer already signed, wait for confirmation and return the signed receipt. Only broadcasts; never signs or pays payment transactions. A retry with the same idempotency_key never pays twice.

Input parameters:

- `idempotency_key` (string, required)
- `quote` (object, required): The signed quote exactly as returned by quote_payment
- `transaction` (string, required): Base64 transaction signed by the payer

### `verify_receipt` (~40 tokens)

Verify a receipt: the m2m.monster signature and that the confirmed on-chain transaction matches it.

Input parameters:

- `receipt` (string, required): Receipt JWS

### `build_refund` (~111 tokens)

Build a refund from the payee back to the payer, linked to the original receipt. The payee signs it and pays its gas; it has no m2m.monster fee and the original fee is not returned. Unsigned. Sign it locally with your own Solana key; m2m.monster never sees or uses agents' private keys.

Input parameters:

- `amount` (string, required): Refund amount, at most the original gross amount
- `receipt` (string, required): Receipt JWS of the original payment

### `register_agent` (~122 tokens)

Optional registration; paying and getting paid work without it. It unlocks referral credits and receipt history. Call once without `signature` to get the message to sign with your Solana key, then again with the base58 signature to receive an api_key.

Input parameters:

- `agent_id` (string)
- `capabilities` (array)
- `referred_by` (string): Pubkey of the agent that referred you
- `signature` (string): Base58 ed25519 signature of the message
- `solana_pubkey` (string, required): Base58 Solana public key

### `get_referral_status` (~42 tokens)

Your referrer, referred agents, credits and their expiry dates. Credits are discounts on your own fees, never cash. Requires the api_key from register_agent.

### `get_status` (~14 tokens)

Service status and API version.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/monster-m2m-m2m-monster/sandbox#diagnostics

## Score history

- 2026-10-17: 63
- 2026-10-16: 63
- 2026-10-15: 62
- 2026-10-14: 62
- 2026-10-13: 61

## Common questions

### What is the m2m.monster (Devnet sandbox) MCP server?

m2m.monster (Devnet sandbox) is an MCP server listed in the public MCP registry as monster.m2m/m2m-monster. Non-custodial x402 payments between AI agents on Solana. Returns unsigned transactions. This page covers its hosted endpoint (https://sandbox.m2m.monster/mcp).

### Is the m2m.monster (Devnet sandbox) MCP server safe to use?

m2m.monster (Devnet sandbox) scores 63 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 m2m.monster (Devnet sandbox) MCP server expose?

m2m.monster (Devnet sandbox) exposes 10 tools: get_pricing, quote_payment, build_payment, verify_payment, submit_payment, and 5 more. Their descriptions and schemas cost roughly 826 tokens of context every time the server is loaded.

### Does the m2m.monster (Devnet sandbox) MCP server require authentication?

No. We connected to m2m.monster (Devnet sandbox) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the m2m.monster (Devnet sandbox) MCP server still maintained?

m2m.monster (Devnet sandbox) is still listed as active in the MCP registry. We last reached this channel on 17 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://sandbox.m2m.monster/mcp
- Website: https://sandbox.m2m.monster/
- Changelog RSS feed: https://verifymcp.io/servers/monster-m2m-m2m-monster/sandbox.xml
- Changelog JSON feed: https://verifymcp.io/servers/monster-m2m-m2m-monster/sandbox.json
- HTML version of this page: https://verifymcp.io/servers/monster-m2m-m2m-monster/sandbox