# SendGuard

> Check an email before your AI agent sends it: allow, review or block with reasons.

- name: ai.sendguard/preflight
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 87/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.sendguard%2Fpreflight
- tools: https://api.protogrid.dev/v1/servers/ai.sendguard%2Fpreflight/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "preflight": {
      "type": "http",
      "url": "https://api.sendguard.ai/mcp",
      "headers": {
        "Authorization": "Bearer ${PREFLIGHT_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${PREFLIGHT_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-5d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 87/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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: 86 (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
- pass `tools.annotations`: 1 of 1 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: preflight_email (openWorldHint)
- pass `tools.token_cost`: about 441 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 5 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: 1, about 441 tokens to load them all
- tool set hash: 42697be72629c5371fddbe7ed3a755dd
- tools last changed: 2026-10-16T17:52:38.699Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.sendguard/preflight.svg)](https://protogrid.dev/servers/ai.sendguard/preflight)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-16 `preflight_email` changed (description)
  - before: Check an AI-written email before sending. Returns allow, delay, requires_approval or block with reason codes (recipient validity, sender authentication, content risk, sensitive industries, volume limits) and recommendations. Does not send email. Without an API key: 20 free checks per day per IP.
  - after: Check an AI-written email before sending. Returns allow, delay, requires_approval or block with reason codes (recipient validity, sender authentication, content risk, sensitive industries, volume limits) and recommendations. Does not send email. Without an API key: 3 free checks per day per IP.

Full history: https://api.protogrid.dev/v1/servers/ai.sendguard%2Fpreflight/changes

## Remotes

- https://api.sendguard.ai/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (1)

- `preflight_email`: Check an AI-written email before sending. Returns allow, delay, requires_approval or block with reason codes (recipient validity, sender authentication, content risk, sensitive industries, volume limits) and recommendations. Does not send email. Without an API key: 3 free checks per day per IP.