# org.cieltech.pathguard/pathguard

> Crypto transaction safety tool — screens addresses and transactions for scam risk.

- name: org.cieltech.pathguard/pathguard
- version: 1.0.0
- connection class: R2 (oauth_consent_once)
- trust: 89/100
- quality: 82/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/org.cieltech.pathguard%2Fpathguard
- tools: https://api.protogrid.dev/v1/servers/org.cieltech.pathguard%2Fpathguard/tools

**An agent can connect after a one-time OAuth consent by a human.** Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "pathguard": {
      "type": "http",
      "url": "https://pathguard-v2.up.railway.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 75
- drivers: +repository +dns-namespace +reachable +uptime-97% ~updated-37d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 82/100 (good)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: 83 (weight 15)

- pass `auth.prm`: Protected Resource Metadata (RFC 9728) published
- pass `auth.as_metadata`: authorization server metadata reachable
- warn `auth.cimd`: only Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
- 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: check_transactions_batch (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_usage_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_transaction (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 493 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: 5, about 493 tokens to load them all
- tool set hash: 8c2fa0bdc21381740456fb6a85496d54
- badge: [![protogrid quality](https://protogrid.dev/badge/org.cieltech.pathguard/pathguard.svg)](https://protogrid.dev/servers/org.cieltech.pathguard/pathguard)
- 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://pathguard-v2.up.railway.app/mcp (streamable-http, auth oauth2, reachable true, uptime30d 0.9714286)

## Packages

_none_

## Tools (5)

- `check_transaction`: Check one crypto transaction for scams, address mistakes, and other risk signals.
- `check_transactions_batch`: Check up to 1,000 crypto transactions in one request.

    Returns a compact summary by default so large batches do not overwhelm an
    AI agent's context. Set detail_level='full' when individual results are needed.
    
- `get_usage_status`: Check your current PathGuard plan, monthly scan quota, and usage.
- `preflight_transaction`: Run PathGuard's full transaction checks and return an ALLOW, REVIEW, or BLOCK decision.
- `report_scam_address`: Report a suspected scam address to PathGuard's community reporting system.