MCP server for searching Taiwan judicial judgments (司法院裁判書系統) — AI-callable tools over Model Context Protocol

MCP server for searching Taiwan judicial judgments (司法院裁判書系統) — 2 AI-callable tools over Model Context Protocol

Persistent semantic memory + judgment ledger for Claude Code (MCP server)

Human-like memory and a judgment ledger for AI — an MCP server for Claude Code.

Self-hosted MCP server for Taiwanese legal research: statutes (MOJ), court judgments (Judicial Yuan), constitutional interpretations, and legislative history. 14 tools, every result with official source URLs. Free, no API key.

Your taste and judgment, in every AI agent you use. Shared, append-only memory of a human's judgment calls - agents recipe-check via MCP or plain URLs. MIT, self-hostable.

MCP server - Polish court judgments via SAOS API (System Analizy Orzeczen Sadowych)

India Law MCP -- Indian central and state statutes (section text) and Supreme Court of India judgments.

MCP server exposing Arbiter judgment tools to any MCP-capable agent.

DecisionNode MCP server: the decision engine's calibrated judgments as tools for AI agents

India Law MCP -- Indian central and state statutes (section text) and Supreme Court of India judgments.

MCP intelligence layer — intent routing, perception, judgment, and sandboxed code execution across child MCP servers.

MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents

MCP server for HumanRail — route tasks requiring human judgment to vetted workers from any AI agent

Coding agent memory: local-first memory and judgment for AI coding agents. One MCP server for every project; warns before repeating failed fixes.

Human judgment as an API for AI agents. SDKs for JavaScript and Python, and an MCP server.

A local, account-free MCP server that turns data into clean, presentation-ready charts — design judgment baked into the defaults.

An MCP server and CLI that rank postings against your profile, explain every score, and measure the ranking against your own judgment.

A zero-dependency MCP server for TypeSafe's Jev — calibrated, typed judgments for Claude Code, with a local answer cache and cost tracking.

A Jev-first memory layer for AI agents — frozen typed questions, deterministic policy, a sealed judgment log. Model proposes, the ledger decides.

A pocket guide to better judgment, with a library-first MCP for AI. Curated principles, evidence labels, practical cautions and bounded scholarly supplements.

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

MCP server for Pakistani law: search and cite 967 federal statutes and 1,414 Supreme Court judgments, full text, with a strict citation contract.

MCP server, Next.js frontend, and LangGraph chat assistant for Indian legal research (Constitution, IPC, CrPC, CPC, Evidence Act, BNS/BNSS/BSA 2023, commercial statutes, landmark Supreme Court judgments).

MCP server giving coding agents quick judgment tools (route, gate, check, decide) backed by a System One model, with per-project rules in .systemone.json.

MCP server exposing TypeSafe Jev typed judgments: classify, score, check, a batched multi-question ask, a many-item triage with server-side file reads, and model discovery.

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

A Codex plugin that exposes DeepSeek-powered MCP tools for supervised collaboration. Codex delegates, reviews, discusses, and verifies work with DeepSeek while keeping final edits, tests, and judgment inside Codex.

The judgment layer for coding agents: verified picks, traps at your version, skills, and design systems over MCP. Works without a key.

Style and quality linter for Norwegian and English text - MCP server for agents, with TypeSafe's Jev as the judgment layer. Reports findings, never authorship verdicts.

MCP server for 230,000+ Pakistani court judgments - connect Claude, ChatGPT, Gemini, Grok or Cursor to Pakistani case law. Free, read-only, no API key.

MCP server for typed AI judgments: classify, route, score, and flag with calibrated probabilities instead of prose. Powered by Jev via the OpenJEV API.

Practice judgment with AI code in VS Code: predict, inspect, and keep or reject changes with evidence. Open source; ChatGPT and MCP support.

MCP server for UK law - legislation.gov.uk (Acts and SIs across all four nations), Find Case Law judgments, and the GOV.UK Search API (tribunals, HMRC manuals, CMA). Keyless, OGL v3.0. Apache-2.0.

Teach your AI once. It never forgets. Voice-captured engineering memory for AI coding agents — dictate the judgment your agent can't see, via MCP + rules export. Built for No Hands: The Wispr Challenge.

MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code

Coding agent memory — local-first memory and judgment for AI coding agents. One MCP server for every project; warns before repeating failed fixes.

An inbox with judgment. MCP server that files every note, link and meeting line by itself: TypeSafe's Jev decides the kind, the project, the urgency and the duplicates, and your text is never rewritten.

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.

A Swiss Army knife that lets AI agents get the most out of decision models, simply. Typed yes/no, choice and score judgments over MCP, REST and a CLI, to gate and triage agent work. Written in Rust.

Frame Check MCP server: deterministic structural framing analysis for AI-generated documents, with default-on frame-divergence block per FRAME_DIVERGENCE_CONTRACT_v1 c1.0. MCP surface delegates V4.2 judgment to the caller's agent model; zero Frame Check LLM cost per query.

Salesforce AI skill library: 1,040 skill packages, 70 run-time agents and an MCP server that give Claude Code and other AI assistants senior-practitioner Apex, LWC, Flow, Agentforce and admin judgment, grounded in official Salesforce docs. Source-available (PolyForm Small Business).

A control plane for trustworthy AI agents: write product judgment once, then enforce it through typed MCP tools, git gates, demolition-first stories, evidence-judged checkboxes, and zero-trust monitoring. Ships with Claude Code and Cursor plugins, Agent Skills, and a FastMCP server.

AI analyst agent (Gemini + MCP tools over SQLite) tested on 22,641 clothing reviews. Compares its judgments with an ML baseline on 200 held-out reviews, audits disagreements, fixes a silent wrong-question bug (2/5 to 5/5), documents governance and limits. Includes a no-setup replay site.

AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibility-tree targeting, window-scoped input, clipboard-safe paste, read-back verification. Ships a pip CLI, a pi package and a DeepSeek Harness plugin.

A standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP servers