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.
-
Team-aware memory for AI coding assistants — intent tracking, decision history, real-time team conflict detection.
NOASSERTION -
Agent coordination MCP server — shared blackboard, decision tracking, and context assembly
npm MIT ★ 7 -
cccmemorygithub.com/xiaolai/cccmemoryupdated this year
MCP server for indexing and searching Claude Code conversation history with decision tracking, git integration, and project migration/merge
npm MIT -
pvc-mcp-servergithub.com/aliyun7869160768/pvc-mcpupdated this year
Plan Version Control (PVC) MCP Server — Git-like version control for AI agent decision tracking
pypi Apache-2.0 -
MCP server for indexing and searching Claude Code conversation history with decision tracking, git integration, and project migration/merge
npm MIT -
decision-os-mcpupdated this year
MCP server for Decision OS - LLM-native decision tracking and learning system
npm MIT -
decision-os-mcpgithub.com/marianstefi20/decision-os-mcpupdated this year
MCP server for Decision OS — LLM-native decision tracking and learning system that captures novel pressure and compresses it into reusable foundations
-
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 -
bicameral-mcpgithub.com/bicameralai/bicameral-mcpupdated this year
Decision ledger MCP server — ingests meeting transcripts, maps decisions to code, tracks drift
pypi MIT -
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 -
Obsidian MCP Note System for knowledge management, planning, and decision tracking.
★ 3 -
@rubiconsoftware/anchor-mcpgithub.com/rubiconsoftware/anchorupdated this year
MCP server for Anchor Decision Intelligence — bias detection, decision analysis, and history tracking for Claude Code, Cursor, and MCP-compatible AI tools
npm MIT -
mcp-meeting-intelligenceupdated this year
MCP server for cross-meeting intelligence — tracking promises, decisions, and action items across meetings
npm MIT -
decreegithub.com/doruksahin/decreeupdated this year
Decision governance for code and the agents editing it — track PRD→ADR→SPEC decisions, map them to files, and gate changes against them. Deterministic, honest CLI + MCP.
MIT ★ 2 -
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 -
LLM-native architecture decision record (ADR) tracking. Prevents Agents from repeating mistakes. SQLite + Qdrant + MCP.
pypi Apache-2.0 ★ 4 -
Temporal Knowledge Graph System for Architectural Memory - Track decisions, patterns, and failures with MCP integration for Claude Code/Desktop
npm MIT ★ 4 -
AI coding harness to plan, track and search decisions. Skills, rules, CLI and MCP that mandate a structured workflow for Claude Code and Codex.
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 -
Persistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.
npm -
pt-edgegithub.com/grahamrowe82/pt-edgeupdated this year
Precomputed reasoning cache for AI infrastructure decisions — 220K+ pages tracking the open-source AI ecosystem
pypi MIT ★ 8 -
thinking-toolsgithub.com/mordiaky/thinking-toolsupdated this year
63 MCP tools for structured AI reasoning — ideation, hypothesis tracking, decision matrices, mental models, and more
MIT -
A lightweight task framework — persistent task tracking, memory injection, and structured decision logging via MCP tools.
★ 1 -
agent-reflexion-mcpgithub.com/mdfifty50-boop/agent-reflexion-mcpupdated this year
Agent self-improvement and reflection MCP server — decision logging, pattern analysis, performance tracking
-
Voice-first benefits companion covering 12 months of decisions, not a one-shot enrollment wizard. Vercel WDK track with a custom Benefits-Knowledge MCP server.
-
Intentgithub.com/SixByFive/Intentupdated this year
Git-native reasoning layer for software projects. Track the why behind code with plans, decisions, constraints, and AI-readable project context.
npm MIT ★ 4 -
Prospective Memory MCP server — tracks the agent's intentions, suspended tasks, deferred decisions, and context markers across context windows and sessions.
Apache-2.0 -
Perplexity MCP server and CLI in Python: Agent, Search, Embeddings and Decisions APIs, model routing, local chat history, usage and cost tracking
npm MIT ★ 3 -
Track your ideas, tasks and decisions, and the work your agents hand in. Local-first Windows app with an MCP server.
AGPL-3.0 -
Project management MCP server for Claude Code & Codex CLI — track tasks, visualize progress, manage decisions across AI coding hosts
pypi MIT ★ 1 -
Step-by-step guided AI development workflows, architectural decision tracking, and native MCP server for Cursor, Claude, and Copilot.
NOASSERTION ★ 6 -
The execution layer for Wispr Notetaker — an agentic AI that remembers every meeting decision, catches conflicts, tracks commitments, and turns talk into approved tasks in Notion, Slack & email.
★ 1 -
memguard-mcpgithub.com/liuhengyuan666/memguard-mcpupdated this year
Git-native MCP memory server for AI agents — persistent project memory with ADR-based decisions, error trap tracking, and thread-safe concurrent writes. Written in Rust.
npm MIT -
Local, single-user investment command center for PaytmMoney + INDmoney, with an AI panel for real portfolio Q&A and persistent thesis/decision tracking.
MIT -
Engramgithub.com/bitphonix/Engramupdated this year
🐘 Local-first causal knowledge graph for AI developer memory. Tracks decisions, rejected alternatives & reasoning — not just facts. MCP-native for Claude, Cursor & VS Code.
AGPL-3.0 ★ 2 -
MokeWenShu is an AI-powered analysis tool for China Judgments Online, leveraging NLP and legal knowledge graphs to enable conversational document analysis, similar-case pattern mapping, and visualized judgment trend tracking, delivering dynamic insights for legal decision-making.
-
The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy from track record, and every decision leaves a receipt. Your models, your machine, your policy. Includes an MCP bridge: 180 IDE tools for Claude Code.
npm MIT ★ 33 -
Position-trust layer for autonomous systems and decision platforms. Detects GNSS jamming and spoofing, scores track integrity across sources, and recommends fallback navigation. PX4/MAVLink-native, MCP-ready.
Apache-2.0 ★ 1 -
Project memory for Claude Code: every chat archived and searchable, decisions tracked with their reasons, MCP memory tools and hooks. Local, stdlib Python + SQLite FTS5, with pre-registered, held-out evaluations.
MIT -
Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.
npm MIT ★ 44 -
agentforge-graphgithub.com/Scaffoldic/agentforge-graphupdated this year
Turn any repo into a Code Knowledge Graph your coding agent can reason over — symbols, API routes, ORM models, architecture decisions & git history as a typed, provenance-tracked graph, served over MCP. Built on AgentForge.
pypi Apache-2.0 ★ 5 -
@gzoo/forge-mcpgithub.com/gzoonet/forgeupdated this year
MCP server for GZOO Forge — persistent project intelligence for Claude Code
npm MIT -
AI Coding Memory MCP 2026: 20 Tools for Persistent Sprint & Decision Management
-
Always-on companion for Claude that remembers your decisions and their evolution. Local-first memory using SQLite + transformers.js embeddings.
-
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 -
Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.
pypi MIT ★ 26 -
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 -
An MCP server for planning, execution and validation: Structured reasoning (think_*) + execution tracking (ship_*) + roadmap + signals for AI coding agents. Rust · stdio + Streamable HTTP · git-native, Agent-Trace-compatible traces.
cargo MIT ★ 2 -
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 -
cma-mcpgithub.com/clarethium/cmaupdated this year
Model Context Protocol server for the cma compound practice loop. Subprocess wrapper around the canonical bash cma binary; methodology-agnostic substrate; three-section payload (analysis + agent_guidance + provenance) on every response.
pypi Apache-2.0 -
@sunit24blr/brain-mcpgithub.com/sunitlabsorg/interceptor-brainupdated this year
MCP server that acts as a project brain with handoffs, tasks, decisions, and phase rules.
npm MIT -
MCP-powered healthcare AI agent that tracks unfulfilled clinical commitments from physician notes. Extracts promises, verifies against FHIR R4 records, and generates actionable Tasks. Built for Agents Assemble Hackathon 2026.
MIT -
Hosted Meta Ads MCP with an approval queue, decision receipts and independent arrival and conversion counts for AI agents.
MIT -
Multi-source clinical lab analysis pipeline: lab tests + PubMed evidence + MRI cross-validation, with DSPy dual-track LLM, quant gates and MCP server.
MIT ★ 1 -
Review your AI agent's edits like tracked changes: marked in VS Code and the Markdown preview until you accept them.
MIT