Skip to content

LangChain hackshop assess_hackability

How to: LangChain hackshop assess_hackability

client:LangChain transport:streamable-http tool:assess_hackability

Add hackshop to LangChain

  1. 01

    Open pip install langchain-mcp-adapters and merge this in. Keep any servers already there.

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
        "hackshop-mcp": {
            "transport": "streamable_http",
            "url": "https://www.hackshop.dev/mcp",
        }
})

tools = await client.get_tools()
  1. 02

    Save the file and restart LangChain.

  2. 03

    Ask for something assess_hackability does. LangChain lists the server's tools on connect and calls assess_hackability itself — you do not invoke it by name.

  3. 04

    If nothing happens, check the server is running and that hackshop's identifier in your config matches the one above exactly.

get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs

Set these first

hackshop will not start until these are set, so assess_hackability never becomes available.

  • ANTHROPIC_API_KEY
  • HACKSHOP_TELEMETRY

Same tool, other clients

This list was read from the server itself, by connecting to it and calling tools/list on 4 October 2026. It is what the server actually exposes, not what its listing claims.

Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.