M

Mcp

MCP server · by decionis

AI Agents npmStreamable HTTP v0.3.0

Authorize consequential AI agent actions before execution

View source ↗ Website ↗ Generate config for multiple servers More servers

Install

registry version 0.3.0

npm
npx -y @decionis/mcp
Streamable HTTP
https://protocol.decionis.com/mcp

Setup by client

Pick your client — the config below is generated for this server (both local and hosted-endpoint forms). Copy respects the “Pin version” switch above.

claude_desktop_config.json

{
  "mcpServers": {
    "mcp-392": {
      "command": "npx",
      "args": [
        "-y",
        "@decionis/mcp"
      ],
      "env": {
        "DECIONIS_PRESENCE_API_KEY": "<YOUR_DECIONIS_PRESENCE_API_KEY>"
      }
    }
  }
}

Remote (hosted) endpoint

https://protocol.decionis.com/mcp

Claude Desktop: Settings → Connectors → Add custom connector, paste this URL.

Format verified against the official Claude Desktop docs ↗.

Environment variables

Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.

  • DECIONIS_POLICY_PATH — Optional path to the policy file; defaults to ./DECIONIS_POLICY.md in the working directory.
  • DECIONIS_PRESENCE_API_KEY secret — Optional Presence tenant API key. When set, decionis_request_presence_verification and decionis_get_presence_verification_status register and call presence.decionis.com; without it the server stays networkless.
  • DECIONIS_PRESENCE_API_URL — Optional Presence base URL (https only); defaults to https://presence.decionis.com.

GitHub

⭐ 688 stars · 最近更新于 16 天前 · Apache-2.0 license

About this server

AgentSafe Put an authority boundary in front of any agent or API. AgentSafe intercepts consequential actions and checks whether they are authorized before forwarding them. An agent, an application or a tool sends its HTTP request to AgentSafe instead of the target; AgentSafe captures the action as a…

Summary from the project README — github.com/decionis/agent-safe-pipeline

Distributed as npm, Streamable HTTP, listed under AI Agents. Review our MCP security guide before granting access to real data.

Frequently asked questions

What does the Mcp MCP server do?

AgentSafe Put an authority boundary in front of any agent or API. AgentSafe intercepts consequential actions and checks whether they are authorized before forwarding them. An agent, an application or a tool sends its HTTP request to AgentSafe instead of the target; AgentSafe captures the action as a

How do I install Mcp?

Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.

Is Mcp free to use?

The MCP server itself is free to install. The source is public on https://github.com/decionis/agent-safe-pipeline. Any third-party service it calls may require its own API key and account.

Which clients support Mcp?

Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.

Add this badge

Publish this server? Link back with a badge on your README or site — copy either snippet.

Listed on MCPNav

Markdown

[![Listed on MCPNav](https://mcpnav.net/badge/mcp-392.svg)](https://mcpnav.net/server/mcp-392/)

HTML

<a href="https://mcpnav.net/server/mcp-392/"><img src="https://mcpnav.net/badge/mcp-392.svg" alt="Listed on MCPNav" height="20"></a>