# Spamgone

> Spamgone is a freemium MCP server for security. Hosted MCP server that lets AI agents check messages for spam, scams and toxicity. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $20 a month
- **Platforms:** API, Web
- **Website:** https://spamgone.dev/docs/mcp
- **MCP Registry name:** dev.spamgone/spamgone
- **Categories:** security
- **Listing updated:** 2026-11-18

## About

The README-level docs describe a hosted server at spamgone.dev/mcp that AI agents can connect to over Streamable HTTP using an API key. Once connected, an agent can run message checks and also manage the surrounding setup, including rules, keys, settings, the review queue, metrics, logs and usage.

Each key carries its own rights, so the agent only gets what that key allows. Read-only mode, feature-group filters and a team restriction can be set through URL parameters, and a check-only key exposes just check_message, give_feedback and search_docs. Destructive actions such as revoking keys or deleting rules require a second call with confirm set to true after the user approves.

The service is aimed at developers and teams running apps or communities that receive user messages and want an automated screen for spam, scams, toxicity and similar content, with a Claude, Cursor or VS Code client as the interface. Tool calls count against the same rate limit and quota as the regular API.

## Features

- **Hosted Streamable HTTP endpoint:** Clients connect to one remote URL with an API key in the Authorization header, with no local install.
- **Scoped API keys:** Each key limits what the connected agent can see and change, including check-only keys.
- **Read-only and feature filters:** URL options restrict the server to non-mutating tools or to chosen tool groups such as checks and metrics.
- **Confirmation for destructive tools:** Revoking keys and deleting rules do nothing until the agent repeats the call with confirm set to true.
- **Untrusted text handling:** Check results omit the checked text, and requested text is labelled as untrusted user content.

## Good for

- Screening user-generated messages for spam, scams or toxicity from inside an AI assistant
- Letting an agent review the moderation queue and give feedback on borderline checks
- Monitoring check volume, logs and usage while tuning moderation rules
- Connecting a check-only key to an automated pipeline without giving it administrative rights

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http spamgone https://spamgone.dev/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://spamgone.dev/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "spamgone": {
      "url": "https://spamgone.dev/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "spamgone": {
      "type": "http",
      "url": "https://spamgone.dev/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "spamgone": {
      "serverUrl": "https://spamgone.dev/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "spamgone": {
      "type": "http",
      "url": "https://spamgone.dev/mcp"
    }
  }
}
```

## Tools

- `check_message`: Checks a message for spam, scams and toxicity.
- `give_feedback`: Submits feedback on a check result.
- `search_docs`: Searches the Spamgone documentation.

## FAQ

### How do I connect to the Spamgone MCP server?

Point your client at https://spamgone.dev/mcp over Streamable HTTP and send your API key in the Authorization header as a Bearer token. The docs give setup snippets for Claude Code, Cursor and VS Code.

### Do test keys count toward my quota?

No. Test keys return fixed results for building and testing an integration and are never counted.

### What happens when I hit my check limit?

Checks return a 429 error named daily_quota_exceeded or monthly_quota_exceeded until the limit resets. Pro and Scale plans can enable extra checks at a per-1,000 price.

### Does the agent see the text of the messages it checks?

Check results never include the checked text. When an agent requests text with include_text, it is returned marked as untrusted user content.

### Is Spamgone free?

Spamgone has a free plan, with paid plans for more usage or features. Paid plans start at $20 a month.

### How do I add Spamgone to Claude Code?

Run this command in your terminal: claude mcp add --transport http spamgone https://spamgone.dev/mcp

### What are the best alternatives to Spamgone?

The closest alternatives to Spamgone are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [SynomosAI Governance MCP](https://ai-powered.com/mcp/synomosai-governance-mcp-2): SynomosAI Governance MCP is an open-source MCP server for security.

---
Source: https://ai-powered.com/mcp/spamgone
