Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

claude mcp add --transport http preflight https://api.sendguard.ai/mcp --header "Authorization: Bearer ${PREFLIGHT_TOKEN}"

[mcp_servers.preflight]
url = "https://api.sendguard.ai/mcp"
bearer_token_env_var = "PREFLIGHT_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "preflight": {
      "type": "remote",
      "url": "https://api.sendguard.ai/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:PREFLIGHT_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "preflight": {
      "type": "http",
      "url": "https://api.sendguard.ai/mcp",
      "headers": {
        "Authorization": "Bearer ${PREFLIGHT_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=preflight&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnNlbmRndWFyZC5haS9tY3AiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgJHtQUkVGTElHSFRfVE9LRU59In19"
}

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

{
  "mcpServers": {
    "preflight": {
      "httpUrl": "https://api.sendguard.ai/mcp",
      "headers": {
        "Authorization": "Bearer ${PREFLIGHT_TOKEN}"
      }
    }
  }
}

extensions:
  "preflight":
    enabled: true
    name: "preflight"
    type: streamable_http
    uri: "https://api.sendguard.ai/mcp"
    headers:
      "Authorization": "Bearer ${PREFLIGHT_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${PREFLIGHT_TOKEN}. The registry never accepts secret values.

Quality 87 / 100new

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene86 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations1 of 1 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: preflight_email (openWorldHint)
pass
tools.token_costabout 441 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 5 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

1 tools, about 441 tokens to load them all · tool set 42697be72629 · tools last changed 2026-10-16 · checked 2026-10-20 11:40 UTC

Tool changes

2026-10-16preflight_emailchangeddescription
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 · 95% of words in common
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: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository

provenance55

liveness100

freshness100

hygiene80

+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. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.sendguard.ai/mcp` streamable-http	none	yes	100%	389 ms	2026-07-28, 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05	2026-10-20

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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.sendguard/preflight",
  "title": "SendGuard",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.sendguard.ai/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "description": "Optional. \"Bearer sk_...\" API key from https://app.sendguard.ai for paid credits; without it you get 20 free checks per day."
        }
      ]
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://sendguard.ai",
  "description": "Check an email before your AI agent sends it: allow, review or block with reasons."
}