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.
-
@iflow-mcp/haasonsaas-deliberate-reasoning-enginegithub.com/haasonsaas/deliberate-reasoning-engineupdated this year
MCP server that transforms linear AI reasoning into structured, auditable thought graphs
npm MIT -
iflow-mcp_saptadey-adaptive-graph-of-thoughtsgithub.com/saptadey/adaptive-graph-of-thoughts-mcpupdated this year
Adaptive Graph of Thoughts: Intelligent Scientific Reasoning through Graph-of-Thoughts MCP Server
pypi Apache-2.0 -
Persistent Graph-of-Thoughts with Graph-RAG retrieval. Eager MCP server where the corpus is chain-of-thought reasoning. Retrieve from HOW you thought, not just WHAT you know.
npm MIT -
predicate-skillgithub.com/nordicagents/predicateupdated this year
Local reasoning knowledge graph (RDF/OWL) for AI agents — Claude Code plugin + MCP server + predicate CLI.
npm SEE LICENSE IN LICENSE -
Assumption-first reasoning graph: negate an assumption, see what falls, branch and diff. Open source, local-first, MCP-first.
cargo 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 -
Browser-based RDF/ontology knowledge graph editor — load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorithm layout and clustering. AI-native via MCP tool surface and relay bridge. Fully client-side, no backend required.
NOASSERTION ★ 265 -
Chreiagithub.com/sstanley-yelnatss/Chreiaupdated this year
Local-first reasoning graph for investigations. Tauri desktop app + optional MCP
AGPL-3.0 ★ 2 -
code-reasongithub.com/ph0smet/code-reasonupdated this year
MCP server that gives AI agents program-analysis primitives like data flow, call graphs, taint analysis so they reason from deterministic data instead of grep-and-guess."
Apache-2.0 ★ 6 -
deep-thinkergithub.com/nachosystems/deep-thinkerupdated this year
Advanced cognitive reasoning MCP server — DAG thought graph, 10 strategies, metacognition, self-critique, knowledge integration, and pruning
MIT ★ 15 -
The Advanced Scientific Research (ASR) Graph of Thoughts (GoT) MCP server is a highly efficient implementation of the Model Context Protocol (MCP) that allows for sophisticated reasoning workflows using graph-based representations.
pypi Apache-2.0 ★ 12 -
A Model Context Protocol server providing structured reasoning and thinking tools with memory graph
npm MIT -
MCP server with multi-modal reasoning, dynamic knowledge graphs, and collaborative AI personas that thinks like a human brain.
★ 3 -
mcp-engramgithub.com/shuruheel/mcp-engramupdated this year
MCP server for cognitive knowledge graphs — models thought, emotion, reasoning, and episodic memory
npm MIT -
@iflow-mcp/shuruheel-mcp-engramgithub.com/shuruheel-mcp-engramupdated this year
MCP server for cognitive knowledge graphs — models thought, emotion, reasoning, and episodic memory
npm MIT -
AI Intelligence Platform -- knowledge graph + semantic search + reasoning + multi-agent debate in a single binary
NOASSERTION ★ 20 -
Serve versioned, pre-reasoned RDF knowledge-graph bundles read-only over the Model Context Protocol
MIT -
Make AI research agents accountable — give every conclusion a traceable argument graph. MCP server + Claude Code plugin for paper reproduction, hypothesis verification, and auditable scientific reasoning.
MIT ★ 3 -
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 -
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 for structured AI reasoning — decompose problems into atomic thoughts with dependency graphs, confidence tracking, and interactive D3.js visualization
npm MIT ★ 96 -
NexusMindgithub.com/SaptaDey/NexusMindupdated this year
NexusMind: Intelligent Scientific Reasoning through Graph-of-Thoughts MCP Server
★ 3 -
Compiler-precise code property graph for C, Python, and TypeScript, navigable over MCP — data- and taint-flow with source→sink witnesses, points-to, and guard/sink structure for security reasoning over source.
pypi AGPL-3.0 ★ 6 -
deep-thinkergithub.com/hubinoretros/deep-thinkerupdated this year
Advanced cognitive thinking MCP with DAG-based thought graph, 10 reasoning strategies, node aliases, session persistence, structured responses, auto strategy selection, and 17 tools with help & conclude
npm MIT -
code-graph-rcagithub.com/sebdenes/code-graph-rcaupdated this year
Halo · structural facts about your code, exposed to any AI agent over MCP. Long-lived daemon parses your repo with tree-sitter, builds a call graph + git-aware index, and gives Cursor / Claude Code / Cody / Cline / Continue / Windsurf / Zed ten tools (callersOf, calleesOf, pathBetween, recentlyChangedNear, rca, …) for grounded code reasoning.
npm MIT ★ 1 -
VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.
pypi MIT ★ 327 -
Mikegithub.com/shiwani42/Mikeupdated this year
A Splunk-native agent that turns SOC analyst reasoning into a queryable institutional knowledge graph, accessible from SPL, a Python CLI, and a Model Context Protocol server.
MIT -
obsidian-open-ontologiesgithub.com/fabio-rovai/obsidian-open-ontologiesupdated this year
Full Open Ontologies engine in Obsidian: reason over, SHACL-check and SPARQL-query your vault as a knowledge graph, and expose it to Claude over MCP
MIT ★ 10 -
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 -
Graph of Thoughts (GoT) MCP Server — bounded, auditable reasoning for AI agents
npm MIT ★ 1 -
Tigergraph-agentic-fraud-investigationgithub.com/krapanshi/Tigergraph-agentic-fraud-investigationactive
TRACE: graph-backed agentic fraud investigation with TigerGraph, official MCP, Gemini reasoning, local embeddings, policy actions, SARs, and 20 verified cases.
-
The alert is never where the bug is. An incident agent that reasons over a FalkorDB graph: finds where a failure starts, fixes it, verifies, and remembers. MCP server + Claude Code plugin.
Apache-2.0 ★ 1 -
ThoughtMcpgithub.com/keyurgolani/ThoughtMcpupdated this year
🧠 AI cognitive architecture over MCP — human-like five-sector memory, parallel reasoning, metacognition (bias/emotion/confidence), a 3D memory graph, and a web UI. PostgreSQL + pgvector + Ollama embeddings. 20 MCP tools.
npm MIT ★ 1 -
engram-memgithub.com/docaohieu2808/engram-memupdated this year
Dual-memory system (episodic vector + semantic graph) with LLM reasoning for AI agents. CLI, MCP, HTTP API, WebSocket interfaces.
pypi MIT -
Unified cross-AI memory: one MCP hub for shared memory, code graph, handoffs, reasoning logs and safe secret references
oci MIT ★ 1 -
DecompGTIgithub.com/yuvraj-rathod-1202/DecompGTIupdated this year
DecompGTI is a graph-reasoning framework that fine-tunes small language models to parse natural-language graph queries into structured JSON plans executed by deterministic algorithms on a FastMCP server.
MIT -
A context layer for coding agents: notes, RFCs, tasks and tracked time as one graph of plain markdown. The running app hosts an MCP server, so Claude Code and other agents read what is ready, follow the reasoning behind it, and log their own work.
MIT ★ 6 -
A stateless, Graph-powered Outlook MCP that enables AI agents to search, retrieve, and reason over email data intelligently.
MIT ★ 1 -
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 -
Auditable deterministic reasoning MCP server (non-LLM). World-graph → A* auditable reasoning → execution → learning loop. Fail-closed: an unchecked claim is never returned as passed. Free for non-commercial agent use.
npm NOASSERTION -
68+ atomic MCP bricks for AI agents — files, code intel, shell, reasoning, search, graphs, workflows. Official FocusMCP catalog.
npm MIT -
domain-mcp-servergithub.com/waabox/domain-mcp-serverupdated this year
MCP server that clones and analyzes microservices to extract business rules, APIs, and data models—represented as an in-memory graph for fast reasoning.
MIT ★ 1 -
Transparent API security discovery: risk scores that cite their reasons, real-traffic cross-referencing, an agent/MCP security graph, behavioral baselining, and Cedar policy generation. Rust core, Python CLI/SDK.
Apache-2.0 -
mcp-netgraphgithub.com/ayushgoel24/mcp-netgraphupdated this year
Model Context Protocol (MCP) server for AWS Network Engineering. Uses NetworkX to build a directed graph of VPC infrastructure (SGs, NACLs, Route Tables), enabling deterministic reachability reasoning and 'shadow path' detection for AI agents.
pypi MIT -
codemindgithub.com/twly7ho2/codemindupdated this year
CodeMind is an AI agent memory system that maintains persistent, real-time context over complex codebases. By utilizing symbol graph storage, AST chunking, and intelligent file scanning, CodeMind enables LLMs to reason about relationships across large code structures without losing track of dependencies
★ 1 -
Persistent memory and reasoning layer for developers and AI coding agents. Automatically records what you tried, what failed and why you decided things, so you or any AI can resume exactly where you stopped. Local-first. VS Code extension, MCP server and interactive context graph.
MIT ★ 1 -
zaxygithub.com/syndicalt/zaxyupdated this year
Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge graph for reasoning (local-first, no sidecar; Neo4j/Postgres optional), cited Memory Checkout for compact context, and MCP tools for model-facing retrieval, capture, and feedback.
pypi MIT ★ 17 -
Cortivexgithub.com/AhmedRaoofuddin/Cortivexupdated this year
AI agent pipeline orchestration for Claude Code. Deploy specialized agents in coordinated pipelines with self-learning capabilities, mesh coordination, Raft consensus, CRDT knowledge graphs, and pipeline debugging. 15 production-grade skills with reasoning protocols, 20+ agent types, 15 ready-to-run templates. Zero infrastructure.
npm NOASSERTION ★ 12 -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
right-reasonsgithub.com/Right-Reasons/right-reasonsupdated this year
Structured business ontology that gives AI agents deterministic access to institutional reasoning.
NOASSERTION ★ 6 -
Persistent knowledge graphs with WikiLinks and vector search. MCP server that transforms ephemeral AI sessions into continuous collective intelligence.
npm MIT -
polyg-mcpgithub.com/captain-jay29/polyg-mcpupdated this year
Multi-Graph Agent Memory via MCP - The memory system that understands causality
npm MIT -
Adaptive-Graph-of-Thoughts-MCP-servergithub.com/SaptaDey/Adaptive-Graph-of-Thoughts-MCP-serverupdated this year
LLM Reasoning Framework for Scientific Research
MIT ★ 31 -
Clear Thought MCP server with modular architecture - 38 reasoning operations for systematic thinking
npm MIT -
jarvis-orbgithub.com/TheStack-ai/jarvis-orbupdated this year
See AI thinking in real time — 3D orb that visualizes Claude Code reasoning. Free, open-source MCP server
MIT ★ 25 -
snapgraph3dgithub.com/scifiss/snapgraph3dupdated this year
Constraint-guided 3D scene assembly agent with typed scene graphs, connector validation, repair/rollback safety, Unity export, and MCP tooling.
Apache-2.0 -
OWL 2 RL 推理引擎 + 领域适配器 + FastAPI/MCP + 本体图谱工作台:一个可快速应用本体的开源 Demo,配套《本体上手指南》
MIT ★ 4 -
Next-Generation AI Reasoning Framework for Scientific Research
Apache-2.0 ★ 4 -
Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neumann series, push, and hybrid random-walk algorithms with npm/npx CLI and Flow-Nexus HTTP streaming for swarm cost propagation and verification.
npm MIT ★ 94 -
overmindgithub.com/xuanlinAI/overmindupdated this year
玄霖超脑 · 无量网络 v4 重构版— 66 模块6通道 AI 认知神经系统 · 装一次,你所有的 AI 工具从此共享一个永远不失忆的大脑。跨会话记忆 · 多 Agent 互通 · 自动代码审查 · 零配置
MIT ★ 85