Related Servers

No user-submitted related servers found.

Related Servers

• Evidence Gate

  AnotherMeatsack

  A

  license

  -Not graded

  quality

  C

  maintenance

  Enables AI assistants to run local, model-backed decisions on short passages and routing choices, and to check whether exactly supplied text supports a scientific claim, returning the full probability distribution, review-policy status, and provenance details. All evaluation stays on the local machine with no cloud inference, and flagged results are surfaced for human review rather than treated as conclusions.

  Updated 23 days ago (2026-09-26 23:28 UTC)

  MIT

• mcp-laya

  dockndevai

  A

  license

  A

  quality

  B

  maintenance

  Provides fast, offline typed decision tools (classify, score, check, triage) to agents via the Model Context Protocol, enabling safe local inference across 100+ languages with calibrated confidence and no text generation.

  Updated 8 days ago (2026-10-12 03:50 UTC)

  8

  89 PyPI

  MIT

• ember

  shapeandshare

  A

  license

  A

  quality

  A

  maintenance

  Enables coding agents to request calibrated probability judgments over typed questions—yes/no, named choices, or ordered scores—about a described situation, returning one probability per option rather than free text. Runs Cloudflare's Clef model locally on Apple Silicon Macs, with images or video frames optionally attached, and answers delivered as a single MCP tool call.

  Updated 5 days ago (2026-10-15 02:27 UTC)

  1

  671 PyPI

  MIT

• jev-mcp

  codaaiteam

  A

  license

  A

  quality

  C

  maintenance

  Provides agents with fast, typed, calibrated decision tools for classification, scoring, yes/no checks, and gating risky tool calls.

  Updated a month ago (2026-09-22 03:37 UTC)

  5

  317 npm

  2

  MIT

• Jev MCP

  rtf6x

  A

  license

  -Not graded

  quality

  A

  maintenance

  Gives coding agents a judge: twelve tools that accept a state plus typed questions and return a verdict — the chosen option or probability, the full distribution, confidence, and an auto/review/escalate action. Works against any System One-compatible decision endpoint, configured by URL and key rather than code, with a tray app and Claude Desktop bundle for easy setup.

  Updated 15 days ago (2026-10-05 07:53 UTC)

  317 npm

  1

  MIT

• 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 2 hours ago (2026-10-19 22:27 UTC)

  137 PyPI

  6

  MIT