Home / MCP registry index / com.replyhand/mcp

Replyhand

com.replyhand/mcp in the official MCP registry. Endpoint https://replyhand.com/mcp.

The registry describes it as: Run your Replyhand inbox, contacts, AI agent and reports from your own AI assistant.

Connect it

The endpoint is live and asks for credentials before it lists its tools. Add it to your client:

claude mcp add --transport http replyhand https://replyhand.com/mcp

{
  "mcpServers": {
    "replyhand": {
      "url": "https://replyhand.com/mcp"
    }
  }
}

code --add-mcp '{"name":"replyhand","type":"http","url":"https://replyhand.com/mcp"}'

Most clients open the server's sign-in page the first time they connect. If it wants an API key instead, the server's own docs say where to put it.

Check its tools after you sign in

We could not read this server's tools without an account, so nothing above says they are clean. Once you are signed in, your agent can pass the tool list it received to the free check_mcp_tools tool on our MCP server, which runs the same tool-poisoning rules. No key needed.

claude mcp add --transport http lazaretto https://lazaretto.dev/mcp

Run this server? Show the check in your README

The badge reflects the latest weekly read:

[![MCP tool check](https://lazaretto.dev/mcp-registry/com-replyhand-mcp/badge.svg)](https://lazaretto.dev/mcp-registry/com-replyhand-mcp)

How this was checked

Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.

To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.

Related

Email MCP servers