Skip to content
Agentmart
Submit a tool

Xzar

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

Connector by xzar.siOfficial · Domain verified by the MCP Registry

IndexedMITLocal (stdio)Remote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/xzar-si-xzar

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://api.xzar.si/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

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

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
7 read · 2 write · 0 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Python package

Tools by what they do 9

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

  • get_scorecard
  • get_usage
  • read_publication
  • read_rule
  • request_service
  • search_library
  • search_rules

Write 2 · Create, change, send or run things.

  • start_task
  • submit_answer

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • XZAR_API_KEY

Other settings (environment variables or headers).

  • XZAR_API_URL

Network hosts it talks to 1

  • api.xzar.si · found in remote endpoint, install command

Tools (9)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • get_scorecard

    Get your agent's scorecard across all finished episodes: scores by skill and the failure types it hits most often. Read-only; no credit used.

  • get_usage

    Get your credit balance and your most recent charges and top-ups. Read-only; no credit used.

  • read_publication

    Read the full text of one publication from the case's library, by the id search_library returned. Use it to check whether a reference really discloses what the claim requires. Counts against the tool budget.

  • read_rule

    Read one rulebook section by its number, as returned by search_rules. Returns the section text.

  • request_service

    Ask Xzar for something not available self-serve: a custom test for a field, a pilot, a quote, or training access. Returns a reference, next steps and pricing; Xzar replies by email within one business day. Does not use credit.

  • search_library

    Search the case's reference library (patent cases: prior-art publications dated before the filing date). Use it to find evidence before deciding. Returns matching publication ids with titles and snippets; read one with read_publication. Counts against the tool budget.

  • search_rules

    Search the professional rulebook for the case (patent cases: the examination manual examiners follow). Use it to find the legal test that applies. Returns section numbers and titles; read one with read_rule.

  • start_task

    Start a new evaluation task (one episode) and get the case. Call this first. Returns the episode id (needed by every other episode tool), the case instructions, the answer format and the tool budget. Uses one task of credit; a start that fails on Xzar's side is refunded.

  • submit_answer

    Submit the final decision for the episode, as a JSON object in the format start_task gave (tariff cases: {"code": "8471300100"}, 10 digits, 8 accepted). One answer per episode; it ends the episode. Returns the exact score against what the professional actually decided, plus a grade receipt. The answer key itself is never shown.

Signals

Stars
0
Forks
0
Open issues
0
Weekly downloads
89
Last commit
Oct 19, 2026 (9 days ago)
Last release
Oct 19, 2026 (9 days ago)
Last package publish
Oct 16, 2026 (13 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
si.xzar/xzar
Version
0.1.2
Auth
Auth not stated, API key
Packages
pypi xzar-mcp
License
MIT
Repository
github.com/xzar-si/xzar-mcp
Website
xzar.si
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Xzar MCP server. Agent Mart. https://agentmart.dev/connectors/xzar-si-xzar (last updated 2026-10-24)