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.
-
Decision-Graphgithub.com/tanyasinghp/Decision-Graphupdated this year
Engineering decision memory for your organization. Extract the why behind your code from PRs, issues, and commits, then ask natural-language questions - dg ask "Why was this built this way?" and get answers with evidence chains, not just what changed.
★ 1 -
Decision memory layer for AI-assisted codebases — trả lời 'logic nghiệp vụ này có từ bao giờ, ai quyết, vì sao'. Markdown là nguồn sự thật, SQLite FTS5 để search, MCP server cho AI agent.
MIT ★ 1 -
The project's decision graph for AI coding agents: decisions, rejected alternatives and gotchas, anchored to your code.
pypi Apache-2.0 -
Temporal Knowledge Graph System for Architectural Memory - Track decisions, patterns, and failures with MCP integration for Claude Code/Desktop
npm MIT ★ 4 -
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 -
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 -
@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 -
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 -
Log, evaluate, and ground every consequential AI-assisted decision against your organization's authority graph. Traceable decision audit trail. Developer tier free.
MIT ★ 1 -
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 -
personal-kg-mcpgithub.com/tomschell/personal-kg-mcpupdated this year
Personal Knowledge Graph MCP Server - Decision intelligence for multi-agent workflows
npm MIT ★ 6 -
Organizational memory for AI agents captures decisions into a knowledge graph and serves them over MCP.
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 -
VisualizeBettergithub.com/chldbwnstm/VisualizeBetterupdated this year
The AI draws. You see. The next session remembers. — an MCP-native live graph workspace where AI pushes structure, findings, and the reasoning behind decisions into a GPU-rendered graph that outlives the session.
MIT -
cairngithub.com/andrewjsauer/cairnupdated this year
A self-compacting, code-indexed decision graph for AI coding agents, built on git + Lore-compatible records and served over MCP.
Apache-2.0 -
miegithub.com/kraklabs/mieupdated this year
Persistent memory graph for AI agents. Facts, decisions, entities, and relationships that survive across sessions, tools, and providers. MCP server — works with Claude, Cursor, ChatGPT, and any MCP client.
go AGPL-3.0 ★ 44 -
DreamGraph is a graph-governed conceptual development environment (CDE) that turns plans, architecture decisions, and project knowledge into auditable execution through a persistent cognitive graph.
npm NOASSERTION ★ 128 -
The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.
npm Apache-2.0 ★ 23 -
Architectural Memory Engine, The Fast AST Indexer, The Constraint & Guardrail Engine, The Architecture Decision Record (ADR) Graph, Agent Execution Memory & Session Drift Recovery
MIT -
Self-hosted, local-first AI Memory Vault, Epistemic Knowledge Graph (FACT / CLAIM / DECISION), Hybrid Search, and Native MCP Server for AI Agents.
MIT -
SENGRA is an autonomous fraud investigation agent that uncovers organized fraud rings through multi-hop graph analysis. It leverages WCC, PageRank, Louvain communities, and betweenness centrality, retains entity intelligence across sessions, and visualizes evidence paths behind every decision in a real-time dark ops console.
-
Agentic Manufacturing Orchestration — a small public dataset of the S&OE decisions where good planners disagree, plus the graph, MCP server, skills, and first agent.
MIT -
Graph-grounded experience for AI agents: know WHEN to reuse it, see WHY, and keep decisions accountable through trusted feedback. Powered by FalkorDB.
MIT -
@simple-lang/obsidian-lsp-mcp-servergithub.com/ormastes/simpleupdated this year
Obsidian vault LSP-MCP server — 11 tools for full-text search, graph traversal, authority ranking, tags, tasks, and decisions. Native binary, no Node.js runtime needed.
npm 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 -
A knowledge graph and document editor over source and documentation: where something is defined, what a change reaches, which decisions govern an area. Console, REST and MCP.
MIT -
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 -
Self-hosted shared memory for AI agents: vaults of people, facts and decisions your agents recall over MCP or REST, with semantic, keyword and graph search.
NOASSERTION ★ 15 -
coregithub.com/Smeldr/coreactive
Keeps decisions coherent when people and AI agents move fast. A searchable graph of your decisions: who decided, what is in force, what builds on what. Rights set per domain and area, MCP-native, optional merge gates. Self-hosted and open source, with nothing to install beside it.
go AGPL-3.0 ★ 10 -
Open Swiss legal corpus + MCP server: 1M+ court decisions (1875–today), 21k laws, 10M-edge citation graph, 42 MCP tools. CC0 data, MIT code. Live at mcp.opencaselaw.ch
MIT ★ 80 -
Agentic Version Control System — an AI-native VCS where intent, session, operation, evidence and decision are first-class objects and code is a materialized projection of an operation graph.
npm Apache-2.0 -
subcoggithub.com/zircote/subcogupdated this year
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Features hybrid search (semantic + BM25), MCP server integration, SQLite persistence with knowledge graph, and proactive memory surfacing. Written in Rust.
npm MIT ★ 30 -
sverklogithub.com/sverklo/sverkloupdated this year
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.
npm MIT ★ 82 -
Local code intelligence for AI coding agents and developers. Builds a knowledge graph of your codebase from 26 languages and frameworks, searches it by keyword and meaning, navigates it through 21 language servers, and keeps a Context Graph of decisions and standards linked to the code. One MCP server of 75 tools. Fully local and private.
GPL-3.0 -
Archivist-MCPgithub.com/i3T4AN/Archivist-MCPupdated this year
Archivist MCP is a local-first memory server for coding agents. It persists decisions, incidents, rules, entities, and graph relationships in SQLite, then exposes them over MCP (stdio/HTTP), SSE team mode, and WebUI. Built for cross-session context continuity, conflict-safe updates, searchable recall, and auditable change history.
MIT ★ 4 -
Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.
MIT ★ 35 -
Audit any agent decision across its past, present, and future, on one typed graph.
go Apache-2.0 ★ 31 -
Project memory and skill routing for coding agents. Share decisions, search a local knowledge graph, and run code reviews through the CLI or MCP.
npm Apache-2.0 ★ 19 -
cerberus-mcpgithub.com/proxikal/cerberus-mcpupdated this year
MCP server for AI agents: intelligent code exploration (AST-based symbol search, architectural blueprints, call graphs, 90%+ token reduction) + persistent session memory (global preferences, project decisions)
-
Safety-first context & orchestration engine for AI coding agents. MCP server with mandatory research pipeline, knowledge graph, impact analysis, decision memory, and safety guard — works with any MCP client.
npm MIT -
MCP-Server-And-LangGraph-Agentgithub.com/AmirHashmi017/MCP-Server-And-LangGraph-Agentupdated this year
MCP Server & Agentic Workflows is a multi-system AI platform built under Scrum of Scrums (SPM) that integrates RAG, agentic workflows, and autonomous decision graphs using MCP Server and LangGraph to deliver end-to-end research and business intelligence automation.
★ 1 -
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
Apache-2.0 ★ 289 -
ArcRiftgithub.com/Eshaan-Nair/ArcRiftupdated this year
Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
MIT ★ 249 -
Open-source context layer for LLM agents — a single Rust binary served over MCP that feeds Claude, ChatGPT, Codex or any MCP client the facts, decisions & history they need. Local-first, on-device embeddings, hybrid BM25 + vector + graph retrieval. Apache-2.0.
Apache-2.0 ★ 4 -
Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a knowledge graph so Claude Code, Cursor and Copilot reason over architecture, dependencies and prior lessons — with confidence scores and evidence. 13 LLM backends + custom, fully offline capable.
pypi Apache-2.0 -
MCP server that lets coding agents (Claude Code or any MCP client) work autonomously within a session budget — with a dependency graph, human decision queue, required validation and exact handoff. OUTSIDE_MODE for bounded autonomy, DESK_MODE for human-in-the-loop.
MIT -
Gives AI coding agents the why behind your code, and makes them keep it: file cards, rules and decisions kept in git and delivered before every edit, for Claude Code and Codex
npm MIT -
open-indexgithub.com/DrDroidLab/open-indexupdated this year
Deterministic memory layer for your agents
MIT ★ 114 -
cortexgithub.com/rlaksana/cortexupdated this year
Cortex Memory MCP Server - Knowledge management with autonomous decision support
★ 2 -
Local-first engineering lineage: capture why your codebase looks the way it does. CLI, MCP server, and web UI.
npm MIT -
Agent coordination MCP server — shared blackboard, decision tracking, and context assembly
npm MIT ★ 7 -
It just remembers.
npm MIT -
LLM-native architecture decision record (ADR) tracking. Prevents Agents from repeating mistakes. SQLite + Qdrant + MCP.
pypi Apache-2.0 ★ 4 -
kioku-aiupdated this year
Local-first, source-backed decision memory for AI agents — Context Packs with provenance and reversal detection. MCP server + REST API + Python SDK.
pypi Proprietary -
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 -
Typed catalog of cognitive primitives, cross-referenced and lineage-grounded, with a surfacing function on top.
MIT -
codebase-intelgithub.com/mutharasu/codebase-intelupdated this year
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents.
pypi MIT -
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 -
Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.
MIT ★ 5