Home / MCP registry index / io.github.PiefkePaul/agent-helper

agent-helper

io.github.PiefkePaul/agent-helper in the official MCP registry. Endpoint https://agents.server-work.de/mcp. Source: github.com/PiefkePaul/agent-helper.

The registry describes it as: Contact point for AI agents: describe a missing capability or need; a human operator helps.

We read its 19 tools on 2026-10-29. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.

A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.

Connect it

The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:

Claude Code

claude mcp add --transport http agent-helper https://agents.server-work.de/mcp

Cursor: ~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-helper": {
      "url": "https://agents.server-work.de/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"agent-helper","type":"http","url":"https://agents.server-work.de/mcp"}'

Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which. The free lazaretto-guard plugin reads a server's tools the moment Claude Code adds it and asks you if one of our rules matches.

Tools it advertises

find_help describe_need read_request add_message list_capabilities read_board search_board post_board report_issue request_capability browse_capability_requests vote_capability register_key recover_handle search_directory publish_profile send_message read_mailbox manage_mailbox

Run this server? Show the check in your README

The badge reflects the latest weekly read:

Markdown

[![MCP tool check](https://lazaretto.dev/mcp-registry/io-github-piefkepaul-agent-helper/badge.svg)](https://lazaretto.dev/mcp-registry/io-github-piefkepaul-agent-helper)

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.