MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Local MCP server for TypeSafe Jev typed decisions, with Codex integration
npm MIT ★ 1 -
A typed decision API for agents, powered by Microsoft-Decision-1 on Azure.
npm MIT -
Local decision workflows for AI assistants: typed questions, scoped confidence checks, caching and MCP, powered by Ollama and Tev1.
MIT -
MCP server that triages a Jira board with typed, calibrated decisions from a small local model — confidence, human-review flags, held-out evaluation. Synthetic bank-themed data.
-
Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.
npm Apache-2.0 ★ 5 -
A Jev-compatible decision layer as an MCP server: typed noul/choice/score questions with probability distributions and confidence. Pluggable backends (local needle/laya models or any OpenAI-compatible endpoint), calibration tracking, conditions v1, eval harness.
MIT -
A Rust System-1 decision layer: typed decisions with calibrated confidence over MCP stdio, feeding deterministic DAG route nodes
MIT -
MCP server exposing TypeSafe Jev as typed, calibrated decision tools for coding agents
npm MIT -
JEV and local LAYA for MCP. Typed decisions, bounded inference and durable decision records.
Apache-2.0 ★ 1 -
MCP server for Jevx (jevx.org): run Jev AI typed decisions from any MCP client
npm NOASSERTION -
MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe
go Apache-2.0 ★ 3 -
🧠 Typed AI decisions for agent workflows. CLI and MCP server powered by Jev.
MIT -
Typed decision tools for AI agents, powered by TypeSafe Jev
pypi MIT -
Veya is a local decision engine with typed choices, scores and yes/no decisions, retention-aware caching, local MCP tools and Python, TypeScript, Java and .NET integrations.
Apache-2.0 -
One rubric, every decision model. Run the same typed questions on Jev, Clef and OpenAI's Decisions API, and see where they disagree on your own cases.
npm MIT -
MCP server for Laya typed decisions (noul / choice / score): warm model sidecar, token-budget preflight, persisted calibration, honest confidence.
Apache-2.0 ★ 5 -
Bridge Laya typed-decision engine (choice/score/noul) into MiMo Desktop via local stdio MCP + skill trigger rules
MIT ★ 1 -
Local typed probabilistic decision service for agents - Choice/Noul/Score via OpenJev + LM Studio logprobs, as MCP server + CLI.
MIT ★ 1 -
@ambih/central-mdactive
A project's history — intents, decisions, rollbacks, rules, ideas, follow-ups — kept as typed records your AI agents read and write through MCP.
npm Apache-2.0 -
Generic MCP server for System One typed-decision endpoints (/v1/systemone). Works with TypeSafe Jev, Bailian decision models, and any compatible provider; tolerates endpoints that omit usage.output_tokens.
npm MIT -
Map decisions and research as typed graphs with provenance — TypeScript monorepo with CLI, MCP server, and local web UI. Plain JSON boards, no DB, no cloud.
MIT -
MCP server that gives coding agents a judge: twelve jev_* tools for typed decisions and probabilities, plus a tray app and a Claude Desktop bundle.
MIT ★ 1 -
A zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding agent.
pypi MIT ★ 55 -
Verdict — typed decisions with calibrated probabilities for agents (an open-source alternative to a decision-model API): rules, Laya over the System One protocol, LLM logprobs, cascade, calibration, an MCP server and a System One-compatible HTTP server.
npm Apache-2.0 -
Headless workflow engine for typed decisions, model calls and HTTP calls, wired in a graph. HTTP API, MCP server, chat channels and a TypeScript library.
npm Apache-2.0 -
Context engineering, with receipts. AURORA Agent compiles a typed query into the smallest decision-sufficient context and issues a machine-checkable Context Certificate for every omission. 259-tool local MCP server, Rust.
npm Apache-2.0 ★ 1 -
redraftgithub.com/KaelinGraf/redraftupdated this year
Typed, versioned design records for engineering projects — decisions, rationale, and the roads not taken, kept as plain Markdown and driven by your agent over MCP.
Apache-2.0 ★ 3 -
cevgithub.com/sshworld/cevactive
A decision tool for coding agents that would rather ask a human than guess. Typed questions in, a confident answer or an escalation out. Claude Code plugin + MCP, no API key.
MIT -
A local wiki your agents write for you. Nimbalyst Wiki plugin for Claude Code and Codex: capture decisions, track typed pages, read and edit in your browser.
MIT ★ 36 -
MIMIRgithub.com/abderahmane-ai/mimirno update data
Typed, calibrated and certified decisions over a context, with abstention and evidence.
pypi -
Local-first retrieval over long design conversations. Find where a decision was made, why, and what replaced it. Every answer carries a turn and line range you can open. Hybrid retrieval, typed judgment rerank, exact search, five tools over MCP.
MIT -
Jev MCP Serverno update data
MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
pypi -
Browser automation MCP server whose decisions are made by Jev (TypeSafe System One) typed decisions instead of an LLM reading the DOM.
npm MIT -
jevjamgithub.com/beremaran/jevjamno update data
Typed decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU
oci -
autologygithub.com/Curt-Park/autologyupdated this year
A Claude Code plugin that turns AI-assisted work into a shared living ontology. Captures decisions, conventions, and context autonomously into typed, interlinked knowledge nodes (git-committed markdown). Navigate the ontology as a graph, trace conceptual paths between ideas, and catch doc-code drift before every commit.
MIT ★ 25 -
Local calibrated decision engine for crypto market-making: typed decisions with conformal prediction, Avellaneda-Stoikov quoting, hard risk engine, MCP agent interface. 44-paper research base, $0/call, fully local.
-
Local-first, open-source platform for AI agents and business workflows with typed, calibrated decisions. Ready-to-run flows for finance, sales, IT and customer service; visual builder, human approvals, evaluations, RAG, MCP, REST API, SDK and CLI. One command on your own computer; Docker Compose for servers.
Apache-2.0 -
A standard Model Context Protocol (MCP) server that exposes SubQ's Snap decision model as typed tools.
npm MIT -
MCP server that gives coding agents fast typed decisions, file triage, and a bounded headless browser.
npm MIT -
bridgegithub.com/DanielSoCra/bridgeupdated this year
Local-first operator hub for AI agent sessions — typed todos, blocking decisions, and a debounced dispatch engine over MCP
MIT -
Pre release MCP server for structured design decisions, typed routing, compatibility checks, validation, and automated tests.
MIT -
Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool.
MIT ★ 2 -
A standard Model Context Protocol (MCP) server that exposes TypeSafe AI's Jev decision model as typed tools.
npm MIT -
mcpgithub.com/Smeldr/mcpactive
MCP server for Smeldr. Typed tools for content, decisions, relations and approvals, so AI agents work under the same rules as people.
go AGPL-3.0 ★ 1 -
A trustworthy context layer for AI that remembers, plans and acts — free text into typed commitments, decisions and memories, each with its evidence, in a SQLite file you own. MCP, HTTP, library and typed client.
npm Apache-2.0 ★ 95 -
Safe-by-default MCP server for Laya — fast, local, non-autoregressive typed decisions (classify / score / yes-no) for AI agents, in 100+ languages.
pypi MIT -
Local Laya decision tools for Codex, Claude Code, Cursor and ChatGPT via MCP. One-command setup for source ranking and typed judgments.
Apache-2.0 -
Audit any agent decision across its past, present, and future, on one typed graph.
pypi Apache-2.0 ★ 31 -
MCP server + CLI: send files and typed questions to TypeSafe's Jev decision model, get the raw answer back. One session folder per request.
npm MIT ★ 1 -
MCP server: control any Android phone over ADB (USB/wireless) with JEV, TypeSafe's fast decision model — typed UI understanding, explicit user consent, safety gates
MIT -
Local Laya System-1 judge MCP server + skill for oh-my-pi: typed decisions in milliseconds, zero LLM tokens
NOASSERTION ★ 13 -
jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.
npm MIT ★ 2 -
MCP server for Jev (TypeSafe AI's System One model) — give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com
MIT ★ 3 -
MCP server that runs plain-language browser steps. Jev, a typed decision model, picks the control on each page instead of an LLM reading the DOM.
npm MIT -
sensei-mcpgithub.com/amarodeabreu/sensei-mcpupdated this year
Your engineering standards mentor - Active context injection for 50+ file types with session memory. Sensei transforms your engineering standards from passive documentation into an active mentor that injects relevant guidelines **before** Claude reasons, maintaining session memory of architectural decisions.
pypi Apache-2.0 ★ 1 -
Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.
cargo MIT ★ 32 -
MCP server that gives AI agents typed decisions instead of prose: classify, route, score, and flag with calibrated probabilities. npx -y openjev-mcp
npm MIT ★ 1 -
Ragnitegithub.com/sunamebr/Ragniteupdated this year
Confidence-Aware RAG Memory Engine for LLMs and coding agents - typed memory (facts, decisions, episodes, code), confidence scoring with answer modes, context packing, semantic caching, hybrid retrieval, MCP server, and Invoke Mode for Claude Code.
MIT -
OpenBrain is an open-source machine-readable memory layer for agentic systems. It stores typed, versioned memory objects (claims, decisions, tasks, artifacts, entities, relations, thought summaries), supports structured queries + semantic search, and exposes a standard plug-in protocol via MCP.
Apache-2.0 ★ 5 -
A local ledger coding agents write their reasoning into and read back before they act. Codex and Claude Code share one store: typed decisions, handoffs, and ranked future projections, recalled by repo, topic, or event id.
MIT