# SendCheck — EVM address verification (x402)

> Pre-send EVM address checks: free pre-check, $0.01 check, $0.05 deep scan. x402: payment is auth.

- name: org.pennyforge.api/sendcheck
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 89/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/org.pennyforge.api%2Fsendcheck
- tools: https://api.protogrid.dev/v1/servers/org.pennyforge.api%2Fsendcheck/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "sendcheck": {
      "type": "http",
      "url": "https://api.pennyforge.org/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 98
- freshness: 85
- provenance: 75
- drivers: +repository +dns-namespace +reachable +uptime-96% ~updated-42d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: validate_address (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_address (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); deep_scan (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 476 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 476 tokens to load them all
- tool set hash: 739145e8bc33dbfcdac3122f20167764
- badge: [![protogrid quality](https://protogrid.dev/badge/org.pennyforge.api/sendcheck.svg)](https://protogrid.dev/servers/org.pennyforge.api/sendcheck)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://api.pennyforge.org/mcp (streamable-http, auth none, reachable true, uptime30d 0.95689654)

## Packages

_none_

## Tools (3)

- `check_address`: Paid pre-send verification of one EVM address on one chain ($0.01 USDC via x402, EIP-3009 on Base): checksum, wallet-vs-contract, outgoing activity, native/USDC/USDT balances, leveled verdict with reasons and next action. TWO-PHASE: call without x_payment first to get the exact payment challenge (payTo, amount, asset), sign the USDC transfer, then call again with x_payment = the resulting X-Payment header to get the report. No account, no API key — the payment is the authentication.
- `deep_scan`: Paid deep scan: the full verification across ALL FIVE chains (Base, Ethereum, Arbitrum, Optimism, Polygon) incl. wrong-network detection and USDC/USDT token-mismatch flags ($0.05 USDC via x402, EIP-3009 on Base). TWO-PHASE like check_address: first call returns the payment challenge; second call with x_payment returns the report.
- `validate_address`: FREE pre-send check of an EVM address: EIP-55 checksum verification (catches typos, dropped characters, clipboard malware) + a note that a passing checksum is a spell-check, not payee verification. Run this before paying for check_address.