jev-mcp

About jev-mcp

Jev MCP Fast, cheap, typed judgments from TypeSafe's Jev model, as MCP tools. Give your agent three judgment tools: checks claims against evidence, judges content before it enters context, ranks candidates by meaning with no embeddings. Each call returns verdicts with probability distributions and confidence in roughly 150 to 500 ms, for a fraction of a cent. The cheap mechanical checks agents otherwise skip, because a frontier model is too slow to run on every page, claim, or candidate list.

Quick Facts

Compatible Skills

These tools work well together with jev-mcp for enhanced workflows:

• jev-review — semantic(0.44)+complementary+same_lang+similar_pop+shared_platform (65%)
• blink — semantic(0.44)+complementary+same_lang+similar_pop+shared_platform (65%)
• jev-axi — semantic(0.41)+complementary+same_lang+similar_pop+shared_platform (64%)
• typesafe-ai-benchmark — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (62%)
• pi-jev — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (62%)

More MCP Server Tools

Explore other popular mcp server tools:

• rea ⭐ 310.0k
• ECC ⭐ 283.1k
• n8n ⭐ 207.8k
• everything-claude-code ⭐ 186.6k
• dify ⭐ 158.8k
• open-webui ⭐ 155.9k
• cc-switch ⭐ 145.6k
• graphify ⭐ 128.2k
• browser-use ⭐ 118.3k
• gemini-cli ⭐ 107.4k

Popular JavaScript Agent Tools

• ECC ⭐ 283.1k · MCP Server
• everything-claude-code ⭐ 186.6k · MCP Server
• ponytail ⭐ 166.3k · Agent Tool
• agent-skills ⭐ 106.2k · Codex Skill
• taste-skill ⭐ 96.3k · Codex Skill

Frequently Asked Questions