# Token Safety (Base)

> Base token safety: one-call verdict, risk score, rug check, holders, momentum. x402 + free demo.

- name: dev.workers.restockalarm.token-safety-mcp/token-safety
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.workers.restockalarm.token-safety-mcp%2Ftoken-safety
- tools: https://api.protogrid.dev/v1/servers/dev.workers.restockalarm.token-safety-mcp%2Ftoken-safety/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "token-safety": {
      "type": "http",
      "url": "https://token-safety-mcp.restockalarm.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-1d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 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: token_risk (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); momentum_score (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); token_safety_demo (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 834 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 1 of the 7 days needed

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

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

- tools: 6, about 834 tokens to load them all
- tool set hash: 4eefa5494976288695e403057dc6d2bf
- tools last changed: 2026-10-19T22:02:56.267Z
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.workers.restockalarm.token-safety-mcp/token-safety.svg)](https://protogrid.dev/servers/dev.workers.restockalarm.token-safety-mcp/token-safety)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `token_safety_demo` changed (description, inputSchema)
  - before: Free demo (5 calls/day per IP): run one of token_risk, rug_check, holder_check, momentum_score without payment. Same output as the paid tool.
  - after: Free demo (5 calls/day per IP): run one of token_verdict, token_risk, rug_check, holder_check, momentum_score without payment. Same output as the paid tool.
- 2026-10-19 `token_verdict` added
  - One-call verdict for an ERC-20 on Base: runs token risk, rug-pull, holder and momentum checks plus contract flags (proxy, blacklist, pause, selfdestruct) and returns avoid / high_risk / caution / low_risk with a one-line English summary. Use once before buying or listing an unknown Base token. $0.05 via x402. Not investment advice.

Full history: https://api.protogrid.dev/v1/servers/dev.workers.restockalarm.token-safety-mcp%2Ftoken-safety/changes

## Remotes

- https://token-safety-mcp.restockalarm.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `holder_check`: Holder analysis for an ERC-20 on Base: top 10 holders typed wallet/contract/LP/burn, wallet concentration, distribution and bundling check. Use to judge supply concentration. $0.02 via x402.
- `momentum_score`: Momentum score 0-100 for an ERC-20 on Base from 24 h volume, volume vs liquidity and price change, with confidence low/medium/high. Null for stablecoins. Use to rank Base tokens by activity. $0.02 via x402.
- `rug_check`: Rug-pull check for an ERC-20 on Base: rug_pull true/false, confidence and 5 signals (liquidity removal, wash trading, LP lock, owner wallet, honeypot/tax). Use before buying a new Base token. $0.02 via x402.
- `token_risk`: Risk score 0-100 (higher = riskier) for an ERC-20 on Base: liquidity, top-5 holder concentration, honeypot/tax flags. Use before buying or listing an unknown Base token. $0.02 via x402. Not investment advice.
- `token_safety_demo`: Free demo (5 calls/day per IP): run one of token_verdict, token_risk, rug_check, holder_check, momentum_score without payment. Same output as the paid tool.
- `token_verdict`: One-call verdict for an ERC-20 on Base: runs token risk, rug-pull, holder and momentum checks plus contract flags (proxy, blacklist, pause, selfdestruct) and returns avoid / high_risk / caution / low_risk with a one-line English summary. Use once before buying or listing an unknown Base token. $0.05 via x402. Not investment advice.