Xzar

si.xzarPublished by xzar.siOfficial publisherv0.1.2Updated Oct 27, 2026

Crash-test your AI agent on real professional decisions, graded against what actually happened.

VerifiedStreamable HTTPWeb executableBusiness & CommerceAI & ML

Overview

AI-generated overview

Xzar gives an AI agent real professional decision cases and grades its answers against what the professional actually decided.

What you can do
  • Start a task and receive the case, instructions and tool budget
  • Search the case's reference library and read individual publications
  • Search the professional rulebook and read individual rule sections
  • Submit a decision and get an exact score with a grade receipt
  • Review the agent's scorecard across tasks and check credit balance and usage
  • Request a custom test, pilot, quote or training access for a field
When to use it
Useful when you want to benchmark or crash-test an agent on real professional decisions, currently U.S. tariff classification and patent examination, and compare its answers with the actual outcome. Cases were mostly decided after current models were trained, so they are unlikely to be memorized.
Requirements
A Xzar API key, supplied as the XZAR_API_KEY environment variable for the local package or at sign-in for the hosted connector. The local option runs the xzar-mcp package via uvx; the hosted option connects to the remote endpoint. Network access to the Xzar API is required.
Before you install
Usage is paid: prepaid credits are charged per task, and the free credit is limited. The API key is a secret and should be kept out of shared configuration. Submitting answers and requesting services send data to Xzar's servers; answer keys stay server-side.

Installation

In SourceWeft

  1. Open Xzar in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/si.xzar%2Fxzar/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "xzar": {
      "type": "http",
      "url": "https://api.xzar.si/mcp"
    }
  }
}

README

Xzar MCP server

Crash-test your AI agent on real professional decisions. Xzar gives your agent real cases, cut at the moment of decision, and grades its answer against what the professional actually decided. Most cases were decided after current models were trained, so they can't have been memorized; fresh ones are added monthly.

Live today:

  • Tariff classification: real U.S. classification decisions, graded exactly at 2, 4, 6, 8 and 10 digits, with a consistency check (the same case asked twice). Testing a tariff classifier? See https://xzar.si/scorecard
  • Patent examination: first action, response and appeal.

More fields are on the way; ask for yours at https://xzar.si.

Setup

  1. Get an API key (with $5 of free credit) at https://xzar.si/signup.html
  2. Add the server to your MCP client:
json
{  "mcpServers": {    "xzar": {      "command": "uvx",      "args": ["xzar-mcp"],      "env": { "XZAR_API_KEY": "your-key" }    }  }}

Hosted connector (no install)

In Claude or any MCP client that supports remote servers: add https://api.xzar.si/mcp and sign in with your Xzar API key.

Claude plugin

The plugin/ folder is the Xzar plugin for Claude. It bundles the hosted connector with two skills: crash-test, which runs a task end to end and explains the score, and xzar-request, for custom tests, pilots, quotes and training access. In Claude Code:

/plugin install xzar --marketplace xzar-si/xzar-mcp

Tools

ToolWhat it does
start_taskStart a task: the case, the instructions and the tool budget
search_librarySearch the case's reference library
read_publicationRead one library item
search_rulesSearch the professional rulebook for the task
read_ruleRead one rulebook section
submit_answerSubmit the decision; returns the exact score and the grade receipt
request_serviceAsk for a custom test for your field, a pilot, a quote, or training access; get a reference and next steps
get_scorecardYour agent's scorecard across tasks
get_usageCredit balance and usage

Answer keys never leave Xzar's servers. This package holds no tasks; it calls the Xzar API with your key.

Pricing

Prepaid credits, charged per task. See https://xzar.si/docs.html. Pilots and ongoing testing: https://xzar.si.

Source: README.md at commit a6ae2a7

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.2LatestOct 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts