Related Servers

No user-submitted related servers found.

Related Servers

• ./jevcore-mcp

  Kanokwan89

  A

  license

  -Not graded

  quality

  A

  maintenance

  Exposes three stdio tools that answer typed questions — noul (yes/no), choice, and score — with calibrated probabilities instead of prose, running fully offline on a synthetic mock unless a live credential is explicitly supplied.

  Updated 2 days ago (2026-10-14 15:59 UTC)

  115 npm

  Apache 2.0
• 

  judgment-pack-runtimeofficial

  Judgment-Pack

  A

  license

  -Not graded

  quality

  A

  maintenance

  Serves offline document validation and evaluation operations of the Judgment Pack Specification to MCP clients over stdio, enabling agents to validate and evaluate JPS documents as tool calls. Supports conformance validation, experimental evaluation with disposition and error classes, and corpus testing.

  Updated a day ago (2026-10-15 20:59 UTC)

  2

  Apache 2.0

• poordjaevin

  Icaro0310

  A

  license

  -Not graded

  quality

  A

  maintenance

  Exposes local MCP tools for typed, calibrated LLM decisions — gating risky actions, yes/no judging, classification, ordinal rating, and multi-question decisions in one pass. Runs on the model Devin's CLI already provides via ACP (or a fully offline local backend), so agents get calibrated confidence with no extra API key, no Ollama, and no waitlist.

  Updated a day ago (2026-10-15 16:20 UTC)

  137 PyPI

  6

  MIT

• jev-mcp

  henrykey

  A

  license

  -Not graded

  quality

  B

  maintenance

  Exposes bounded TypeSafe Jev/System One decision primitives as MCP tools, enabling agents to make choices, scores, yes/no judgments, and batched decisions over remote HTTPS with shared state.

  Updated 24 days ago (2026-09-23 04:07 UTC)

  MIT

• decision-lite

  cckyros

  A

  license

  A

  quality

  C

  maintenance

  An MCP server that answers typed noul/choice/score questions about a given state with probability distributions and confidence, for routing, escalation, and gating decisions. It runs on pluggable backends (local Needle 3 or Laya models, or any OpenAI-compatible endpoint) and logs every decision so recorded ground truth can be used to track calibration.

  Updated 10 days ago (2026-10-07 07:57 UTC)

  3

  MIT

• harness-router

  Protocol-Lattice

  A

  license

  -Not graded

  quality

  B

  maintenance

  Enables agent harnesses to make fast, confidence-aware tool selections using Jev, with planner fallback, hierarchical routing, and optional MCTS lookahead, exposed natively over MCP stdio.

  Updated 16 days ago (2026-09-30 18:19 UTC)

  22

  MIT