Xzar — Claude Code MCP server: grade your agent on real cases
Hands your agent genuine professional cases cut at the decision point, then scores the answer against what the expert chose.
claude mcp add --transport http xzar https://api.xzar.si/mcpWhat Xzar does
A task arrives with its instructions and a tool budget. When the agent commits through submit_answer, it gets back the exact score and a grade receipt. Answer keys stay on Xzar's side; the package ships no cases of its own and talks to the API using your key.
Two fields are live. Tariff classification uses real U.S. decisions and grades at 2, 4, 6, 8 and 10 digits, with the same case asked twice to check consistency. Patent examination covers first action, response and appeal. Most cases were settled after current models finished training, so memorising them ahead of time does not work, and new ones land monthly.
You need an API key, issued with $5 of free credit. Connect the hosted endpoint at https://api.xzar.si/mcp, or run the local server with uvx xzar-mcp and pass XZAR_API_KEY. Billing is prepaid credits, charged per task.
What it helps with
- see how an agent reasons through a real professional decision
- compare a model's answer with the expert's actual ruling
- score a tariff classification at several digit levels at once
- catch inconsistency by asking the same case twice
- track an agent's scorecard across tasks and watch credit usage
Example prompts for the agent
- Start a Xzar task and show me the case I got
- Submit my answer with
submit_answerand walk me through the score - Pull the agent scorecard with
get_scorecardand my remaining credits
How to install Xzar
1Platform CLI: remote server
claude mcp add --transport http xzar https://api.xzar.si/mcp2Platform CLI
claude mcp add --env XZAR_API_KEY=<XZAR_API_KEY> --env XZAR_API_URL=<XZAR_API_URL> --transport stdio xzar -- uvx xzar-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from xzar-mcp <command>
1Platform CLI: remote server
codex mcp add xzar --url https://api.xzar.si/mcp2Platform CLI
codex mcp add xzar --env XZAR_API_KEY=<XZAR_API_KEY> --env XZAR_API_URL=<XZAR_API_URL> -- uvx xzar-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from xzar-mcp <command>
Config file
{
"mcpServers": {
"xzar": {
"url": "https://api.xzar.si/mcp"
}
}
}{
"mcpServers": {
"xzar": {
"command": "uvx",
"args": [
"xzar-mcp"
],
"env": {
"XZAR_API_KEY": "<XZAR_API_KEY>",
"XZAR_API_URL": "<XZAR_API_URL>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from xzar-mcp <command>
Config file
{
"servers": {
"xzar": {
"type": "http",
"url": "https://api.xzar.si/mcp"
}
}
}{
"servers": {
"xzar": {
"type": "stdio",
"command": "uvx",
"args": [
"xzar-mcp"
],
"env": {
"XZAR_API_KEY": "<XZAR_API_KEY>",
"XZAR_API_URL": "<XZAR_API_URL>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from xzar-mcp <command>
1Platform CLI: remote server
gemini mcp add -t http xzar https://api.xzar.si/mcp2Platform CLI
gemini mcp add -e XZAR_API_KEY=<XZAR_API_KEY> -e XZAR_API_URL=<XZAR_API_URL> xzar uvx xzar-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from xzar-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Xzar
How do I install Xzar in Claude Code?
For the hosted endpoint: claude mcp add --transport http xzar https://api.xzar.si/mcp. For the local server: claude mcp add --env XZAR_API_KEY=<XZAR_API_KEY> --env XZAR_API_URL=<XZAR_API_URL> --transport stdio xzar -- uvx xzar-mcp.
What does Xzar do?
It serves your agent a professional case stopped at the moment of decision and grades the response against the expert's own choice. The score comes back with a receipt, and answer keys never leave the service.
Which fields are available right now?
Tariff classification on U.S. decisions and patent examination covering first action, response and appeal. You can ask for other fields through request_service.
