Crash-test your AI agent on real professional decisions (MCP server)
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
claude mcp add xzar-mcp -- uvx xzar-mcp{
"mcpServers": {
"xzar-mcp": {
"command": "uvx",
"args": ["xzar-mcp"]
}
}
}MCP Servers overview
# 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. Cases are decided after current models were trained, so they can't have been memorized.
Live today: patent examination (first action, response, appeal). More fields are on the way; ask for yours at https://xzar.si.
<!-- mcp-name: si.xzar/xzar -->
## 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/`](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
| Tool | What it does |
|---|---|
| `start_task` | Start a task: the case, the instructions and the tool budget |
| `search_library` | Search the case's reference library |
| `read_publication` | Read one library item |
| `search_rules` | Search the professional rulebook for the task |
| `read_rule` | Read one rulebook section |
| `submit_answer` | Submit the decision; returns the exact score and the grade receipt |
| `request_service` | Ask for a custom test for your field, a pilot, a quote, or training access; get a reference and next steps |
| `get_scorecard` | Your agent's scorecard across tasks |
| `get_usage` | Credit 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.
What people ask about xzar-mcp
What is xzar-si/xzar-mcp?
+
xzar-si/xzar-mcp is mcp servers for the Claude AI ecosystem. Crash-test your AI agent on real professional decisions (MCP server) It has 0 GitHub stars and its last recorded update is dated 2026-10-16.
How do I install xzar-mcp?
+
You can install xzar-mcp by cloning the repository (https://github.com/xzar-si/xzar-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is xzar-si/xzar-mcp safe to use?
+
Our security agent has analyzed xzar-si/xzar-mcp and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains xzar-si/xzar-mcp?
+
xzar-si/xzar-mcp is maintained by xzar-si. The last recorded GitHub activity is dated 2026-10-16, with 0 open issues.
Are there alternatives to xzar-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy xzar-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/xzar-si-xzar-mcp)<a href="https://claudewave.com/repo/xzar-si-xzar-mcp"><img src="https://claudewave.com/api/badge/xzar-si-xzar-mcp" alt="Featured on ClaudeWave: xzar-si/xzar-mcp" width="320" height="64" /></a>More MCP Servers
Reverse engineer anything with agents, from app behavior down to native binaries.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev