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.
-
@aitool/decision-cligithub.com/kurdin/decision-cliupdated this year
CLI tool and MCP server for managing Architectural Decision Records (ADRs). Works with Claude Code, Codex, Cursor, and any MCP-compatible AI agent.
npm MIT -
@chude/latergithub.com/chudeemeke/laterupdated this year
MCP server for deferred decision management - capture decisions with context, revisit later without memory overhead
npm MIT -
cortexgithub.com/rlaksana/cortexupdated this year
Cortex Memory MCP Server - Knowledge management with autonomous decision support
★ 2 -
AI Coding Memory MCP 2026: 20 Tools for Persistent Sprint & Decision Management
-
mcp-adrgithub.com/mauriziomocci/mcp-adrupdated this year
MCP server for Architecture Decision Records — create, manage, diagram, and export ADRs
pypi MIT -
Obsidian MCP Note System for knowledge management, planning, and decision tracking.
★ 3 -
vibe_coding_enhancedstale
MCP server for managing Agent Important Decision Log (AIDL) in Vibe Coding workflows
npm MIT -
idealift-mcp-servergithub.com/Startvest-LLC/idealift-mcp-serverupdated this year
IdeaLift MCP Server - Decision intelligence for AI assistants. Captures product feedback, tracks decisions, and manages your backlog via Model Context Protocol.
MIT ★ 1 -
adr-writergithub.com/haandol/adr-writerupdated this year
MCP server for Architecture Decision Records (ADR) management with PRD traceability
npm Apache-2.0 -
Enterprise-grade Python + React reference app for vendor-agnostic quote-to-cash agentic decision support, using MCP adapters to assemble live CRM, CPQ, Order Management, Subscription, and Install Base context into a canonical schema for auditable renewal risk, pricing, and governance decisions.
-
ledgenter-mcpgithub.com/mschwartz-tech/ledgenter-mcpupdated this year
The shared work-management office for AI agents — MCP server (@ledgenter/mcp): projects, tasks, decisions, knowledge, handoffs.
npm NOASSERTION -
Architecture Decision Records management
ISC -
Project management MCP server for Claude Code & Codex CLI — track tasks, visualize progress, manage decisions across AI coding hosts
pypi MIT ★ 1 -
trapic-mcpgithub.com/nickjazz/trapicupdated this year
AI knowledge management MCP server — automatically capture, search, and connect decisions, facts, and conventions across AI coding sessions
npm MIT -
Structured Decision Optimization Framework (SDOF) MCP Server - Next-generation knowledge management with 5-phase optimization workflow
MIT ★ 1 -
revmng-mcpgithub.com/arikanatakan/revmng-mcpupdated this year
MCP server for revmng: revenue-management decisions for AI agents: seat protection (Littlewood, EMSR, exact DP), overbooking, pricing, group, length-of-stay, network bid prices, and charts.
pypi MIT ★ 3 -
vibepilot-mcpgithub.com/ravindra240385/vibepilotupdated this year
AI-native project management MCP server — 17 consolidated tools, 17 resources, 8 persona prompts for vibe coders. Features, sprints, decisions, knowledge base, session replay, conflict detection, and more.
npm MIT -
principal-architect-servicegithub.com/ryan-norman-cmm/principal-architect-serviceupdated this year
MCP server for managing product initiatives, technical requirements, and architecture decisions
-
@raysker/axon-agent-toolsgithub.com/raysker/axon-agent-tools-mcpupdated this year
AI agent utility MCP server - decision making, task orchestration, memory management
npm MIT -
mcpgithub.com/wheelfor/mcpupdated this year
MCP server for wheelfor.com — create, spin, and manage decision wheels from any MCP-compatible AI client (Claude Desktop, Cursor, Windsurf). No account required. Wheel results are shareable links.
npm MIT -
@saasboard/mcpgithub.com/przemekkijak/saasboardupdated this year
SaaSboard MCP server — query and manage projects, initiatives, tasks, decisions, docs and agent sessions from AI agents (Claude Code, Cursor, etc.)
npm UNLICENSED -
Kioku (記憶, Japanese for "memory") is an MCP (Model Context Protocol) server that provides persistent, self-enriching context management for AI coding assistants. It eliminates the 10-15 minute context setup developer waste each coding session by automatically learning and remembering project architecture, patterns, and decisions across sessions.
★ 1 -
Simple MCP Server — Educational Example This repository contains a minimal MCP (Model Context Protocol) server built for educational purposes. Its goal is to help developers understand how the MCP protocol works and how to manage decision-making processes based on model–client communication.
MIT ★ 11 -
EVC Meshgithub.com/entire-vc/evc-mesh-mcpno update data
EVC Mesh is an open-source task manager built for teams where people and AI agents work side by side. This MCP server connects your agent to a Mesh workspace: it can pick up assigned tasks, check out work, comment, move tasks through your workflow, hand off to teammates, and keep decisions in shared project memory. Two tool profiles: `core` (25 tools, for everyday task work) and `full` (63 tools, including recurring tasks, docs and workspace admin). Every tool is marked read-only or write, so clients can ask before changing anything. You need a Mesh workspace and an agent key from it. Mesh is self-hosted (Apache-2.0, `docker compose` setup in the evc-mesh repository). Set `MESH_API_URL` to your instance and `MESH_AGENT_KEY` to the agent's key. Workspaces on the hosted instance are by invitation.
smithery -
figma-edit-mcpno update data
Connect AI assistants to Figma via Model Context Protocol to read designs, create and modify elements, and manage design systems programmatically. This plugin empowers your AI assistant to become an active design co-pilot, executing updates and modifications Safer, Cleaner, and Faster than manual entry. By offloading repetitive, error-prone manual operations to automated systems, designers are freed to focus entirely on creative decision-making and product strategy. ### Core Principles * **🛡️ Safer**: The server enforces robust programmatic checks and validations that exceed the Figma Desktop app's default protections. For instance, it prevents deleting variables currently in use to avoid dangling references. By validating all writes against a locked editable scope and strict name checks before execution, it protects files from human error and AI hallucinations. * **✨ Cleaner**: System-driven, programmatic operations guarantee that no layers, text nodes, or components are skipped or forgotten during complex updates. Every design file stays consistent and conforms exactly to your design system. * **⚡ Faster**: Bulk edits like propagating instance overrides, batch-updating copy, or restructuring auto-layout frames are handled via high-performance APIs. Hours of tedious, click-heavy manual work are completed in seconds. ### How it Works (Prerequisites) This server runs locally on your machine. To operate, it requires: 1. The Figma Desktop App to be open. 2. The `Figma Edit` plugin to be active on the file you want to modify (listening on local port `3845`).
smithery -
Local-first control plane for evidence-linked decision memory, governed tasks, deterministic evals, and human-approved actions.
MIT -
gyrusgithub.com/ewgenius/gyrusupdated this year
Model-agnostic knowledge management CLI with MCP server support
npm MIT -
toban-mcpgithub.com/totte-dev/toban-mcpupdated this year
Cross-project task management MCP server for AI coding agents
npm MIT -
owigithub.com/YOKurnaz/owiactive
OWI — Ollaya Web Interface: decide playground, model manager, MCP control, users & API keys
-
Decisions that survive the session. A local project record that AI agents keep through MCP, skills and hooks.
npm Apache-2.0 -
Always-on companion for Claude that remembers your decisions and their evolution. Local-first memory using SQLite + transformers.js embeddings.
-
Org-level memory for coding agents: shared decisions and policies in a git repo, with a CLI and MCP server.
MIT -
Declarative team knowledge for coding agents: decisions declared in git, approved in pull requests, served to every agent over MCP.
Apache-2.0 ★ 1 -
aion-memory-nexusgithub.com/234194027-cpu/aion-memory-nexusupdated this year
Predictive AI Agent Memory & Second Brain — trusted long-term memory, vector search, temporal knowledge graph, decision intelligence, and MCP.
MIT -
MIRSAD (مِرصاد) — a shared, living memory hub for AI agents: bi-temporal facts, first-class decisions, owner-resolved conflicts, and a live graph view. Local-first
pypi MIT ★ 2 -
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 -
The why behind every screen: self-hosted ticketing with a second brain
Apache-2.0 -
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
go MIT ★ 15 -
Compiles git-backed markdown into a verifiable, read-optimized index for AI coding agents.
pypi MIT -
@nonbot/mcpactive
The non.bot MCP server — one server for your portfolios, decision graph, and Runs. Runs over stdio (Claude Code, Cursor, VS Code) with a pat_ token. Built on MCP protocol 2025-11-25.
npm UNLICENSED -
Mémoire décisionnelle d'équipe, git-native. CLI + interface web + serveur MCP pour capturer, indexer et consulter les ADR depuis n'importe quel agent IA.
pypi MIT ★ 1 -
Shared project memory for coding agents: a block tree of designs, plans and decisions with role-shaped views, served over MCP.
npm MIT -
capability-atlasgithub.com/TreyEvreux/capability-atlasupdated this year
Decide what to reuse instead of rebuild — local-first research intelligence, operated by agents, governed by you.
Apache-2.0 -
Risk-feature mining toolkit for customer-level wide tables: adaptive-binning IV/WOE, segment logistic regression, decision-tree rule mining, customer trigger scanning and Word reports, plus an LLM indicator agent and MCP server. Synthetic/public data only.风险特征挖掘流水线
MIT -
dingdawg-planning-agentgithub.com/dingdawg/dingdawg-planning-agentupdated this year
Governance receipts for AI agents — project planning with sprint estimation, task breakdown, and risk assessment that sharpens with every sprint. Every decision signed and receipted for EU AI Act, Colorado AI Act (SB 24-205), and NIST AI RMF audit trails.
npm BUSL-1.1 -
mnemexgithub.com/notsointresting/mnemexupdated this year
Anchored memory MCP server for AI coding agents — binds decisions to code symbols, delivers context just-in-time. Works with Claude Code, Codex CLI, Cursor, Windsurf, Gemini CLI. No ML required. One SQLite file. 56x token compression.
MIT ★ 1 -
Native deterministic engine and read-only MCP server for engineering decisions.
cargo Apache-2.0 ★ 301 -
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 -
Evidence-grounded vulnerability decision support MCP server for federal analysts
MIT -
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.
-
varvegithub.com/varve-sh/varveupdated this year
Decision memory for AI coding agents. A local-first Go binary and MCP server: records decisions with evidence, scope, provenance and expiry, packs the relevant ones into each agent session within a token budget, and links commits back to the decisions that were in scope when they landed.
go Apache-2.0 ★ 9 -
keagithub.com/jpsanders/keaactive
A second brain that checks its facts, for you and your AI agents. Facts with sources and dates, decisions that come back, predictions scored against what happened, a council of rival AI models for big plans, and local search over your Claude Code, Codex and ChatGPT history. CLI, MCP server and skills.
MIT -
loregithub.com/yimwoo/loreupdated this year
Persistent cross-project memory for Codex — rules, decisions, and context that follow you.
npm ★ 1 -
ssot-registrygithub.com/groupsum/ssot-registryupdated this year
A single source of truth for software delivery. Use the Python CLI to link features, specs, and ADRs to claims, tests, and evidence, certify releases, and export lineage graphs.
pypi Apache-2.0 ★ 5 -
An autonomous LLM fund that scores its own stock predictions — Brier score, calibration curves, eval + ablation harness — and serves its full decision history over MCP. LangGraph pipeline with deterministic risk guardrails.
★ 1 -
memory-mcp-servergithub.com/yossifibrahem/memory-mcp-serverupdated this year
A persistent memory MCP server for LLMs. Models can save facts, preferences, context, and decisions — and recall them across sessions.
-
Local search for coding agents: Claude Code, GitHub Copilot and Codex get the passages that answer, with file and line, from your notes, decisions, PDFs and code. A replaced decision ranks below the one that replaced it. Words and meaning, over MCP, on your own machine.
MIT ★ 1 -
IP Vault with Citations — extract decisions, frameworks, and insights from AI conversations with full provenance.
npm MIT -
pmorun-mcpupdated this year
pmo.run MCP server — classic PMO decision tools (PERT, Monte Carlo, TCO, EVM) over the Model Context Protocol.
pypi MIT -
Ranks Tenable VM findings into cases and engineer-ready fix packages, with Claude-written cited narratives and a human-recorded decision.
MIT