SendGuard

ai.sendguardPublished by sendguard.aiOfficial publisherv1.0.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableSecurity & Monitoring

Overview

AI-generated overview

Lets an assistant check an AI-written email before sending and get an allow, delay, approval or block decision with reasons.

What you can do
Exposes one tool, preflight_email, that checks an AI-written email before it is sent. It returns allow, delay, requires_approval or block, with reason codes covering recipient validity, sender authentication, content risk, sensitive industries and volume limits, plus recommendations. The tool does not send email itself.
When to use it
Use it when an AI agent or automation writes and sends email and you want an allow, delay, approval or block decision before anything goes out. Suited to send flows that need to reduce misdelivery, content risk or bulk-sending risk.
Requirements
Needs network access to the remote endpoint at over streamable HTTP. An API key in the Authorization header is optional for paid credits; without it there is a free daily check limit per IP. No local package is required.
Before you install
Email content and recipient details are sent to a third-party service for checking. The Authorization header carries an API key, so keep it private. The tool only returns a decision and does not send mail; actual sending remains your system's responsibility.

Installation

In SourceWeft

  1. Open SendGuard in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.sendguard%2Fpreflight/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "sendguard": {
      "type": "http",
      "url": "https://api.sendguard.ai/mcp"
    }
  }
}

Tools

1

preflight_email

Preflight an outbound 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.

Parametersbodyintentpolicysubjectagent_idto_emailrequiredfrom_emailrequiredcampaign_idrelationshipworkspace_idrecipient_sourcerecipient_company+2 more

Version history

1
  1. v1.0.0LatestOct 15, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.