New: the hosted MCP server is live. Connect your agent in one command.Read the docs →
registry / software / judge0
Judge0
Open-source, sandboxed online code execution system for humans and AI. Robust, scalable online code execution system that can be used to build a wide range of applications that need online code execution features including AI generated code execution, competitive programming platforms, e-learning platforms, candidate assessment and recruitment platforms, online code editors, and online IDEs.
47
DISCOVER93
UNDERSTAND23
ADOPT35
OPERATE35
OverviewGET /v1/profile/judge0
Overall
47
Discover
93
Understand
23
Adopt
35
Operate
35
16/38 applicable signals pass. Open the Capabilities tab for the full signal breakdown, or Issues for the highest-impact gaps.
Agent compatibility
Claude Code✓ TESTED
Codex✓ TESTED
Cursor✓ TESTED
Installed the published MCP server and ran a call end to end.
Score history+8 · 12mo
Do you work at Judge0?
Claim the profile to submit API, MCP, and CLI endpoints, provide test credentials for continuous audits, and embed the badge.
company email · DNS · GitHub org
Badge
agentready47/100
<a href="https://stackresolve.dev/registry/judge0"><img src="https://api.stackresolve.dev/badge/judge0.svg" alt="AgentReady score" /></a>
Frequently asked about Judge0
What is Judge0's AgentReady score?
Judge0 scores 47/100 on the AgentReady: discovery 93, understanding 23, adoption 35, operability 35. The score rates how ready Judge0 is for an AI agent to use without a human.
Does Judge0 have an MCP server?
Yes. Judge0 publishes an MCP server, so an AI agent can connect to it over the Model Context Protocol.
Is Judge0 good for AI agents?
Judge0 is partially ready for AI agents, with an AgentReady of 47/100. It is strongest on discovery.