jev-judge-mcp
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
- agent-tools
- ai-agents
- ai-guardrails
- classification
- claude-code
- fact-checking
- guardrails
- llm
- llm-as-a-judge
- llm-evaluation
- mcp
- mcp-server
- mcp-tools
- model-context-protocol
- prompt-injection
- python
- reranking
- structured-output
- uv
- verification
- Stars
- 84
- Forks
- 4
- + today
- +3
- Created
- 10d
Ranking data as of October 1, 2026 (UTC).
Overview
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate. It ranks #127 on GitTiger, gaining +3 stars on October 1, 2026 (UTC).
The project is written in Python and has 4 forks. It was created 10d ago.
Installation
git clone https://github.com/PyModel/jev-judge-mcp.git
cd jev-judge-mcp
# see README for setup