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.
-
🧭 Strategic BDI cognitive reasoning engine for AI agents. Goal decomposition DAGs, multi-factor utility scoring, risk evaluation, and adaptive replanning over MCP.
npm MIT ★ 13 -
MCP-Based-Agentic-AI-System-for-Cleantech-Retrieval-Reasoninggithub.com/navikamaglani/MCP-Based-Agentic-AI-System-for-Cleantech-Retrieval-Reasoningupdated this year
End-to-end MCP agent that retrieves, ranks, summarizes, and explains answers from a 20k-document cleantech corpus. Built with ChromaDB, HuggingFace LLMs, cross-encoder reranking, and a custom reasoning tool. Includes a complete evaluation pipeline for retrieval and answer quality.
-
right-reasonsgithub.com/Right-Reasons/right-reasonsupdated this year
Structured business ontology that gives AI agents deterministic access to institutional reasoning.
NOASSERTION ★ 6 -
Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.
Apache-2.0 ★ 1,750 -
mcp-dual-cycle-reasonerstale
MCP server implementing dual-cycle metacognitive reasoning framework for autonomous agents
npm MIT -
reason-rdngithub.com/astrognosy/reason-ecosystemupdated this year
ReasonRDN — the shared memory substrate for the agentic era. Local-first with seamless auto-deposit to the warf Xchange (https://warf.astrognosy.com). reason:// handoffs, protected structural fingerprints (PCF), unified client, embedded node, first-class MCP, and CLI.
pypi Apache-2.0 -
mcp-dual-cycle-reasonergithub.com/cyqlelabs/mcp-dual-cycle-reasonerupdated this year
A MCP server implementing the Dual-Cycle Metacognitive Reasoning Framework for autonomous agents. A loop prevention and experience recall mechanism.
npm MIT ★ 9 -
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 -
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required
npm 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 -
reasontraceupdated this year
Local-first reasoning drift detection for AI agents, served as an MCP server
pypi MIT -
fusionpact-vectordbgithub.com/FusionpactTech/fusionpact-vectordbupdated this year
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
npm Apache-2.0 -
scitracegithub.com/mobai-read/scitraceupdated this year
MCP server for AI agents to record and query their reasoning steps. SQLite-backed, zero-dependency beyond mcp SDK.
pypi MIT -
A Structured Reasoning Framework for AI Agents featuring cascade thinking and structured problem solving
npm MIT -
autoai-agentwatchgithub.com/autoailabadmin/agentwatchupdated this year
AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior
npm Apache-2.0 -
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 -
Self-recalling long-term memory & reasoning traces for AI agents, via MCP + local SQLite.
npm MIT -
reasonblocks-mcpupdated this year
MCP server for ReasonBlocks — inject reasoning patterns into any AI coding agent
npm MIT -
Pick the right reasoning effort for every coding-agent prompt. Works with Claude Code, Codex, OpenCode and MCP. Local, transparent, free.
MIT -
prova-mcpgithub.com/insinuateai/prova-mcpupdated this year
MCP server for Prova — let any AI agent verify its own reasoning before answering.
pypi MIT -
fusion-centergithub.com/Draichi/fusion-centerupdated this year
MCP-based OSINT intelligence platform with LangGraph AI agent. Implements multi-step reasoning (task decomposition, hypothesis testing, self-reflection, verification) for autonomous geopolitical research. Supports Gemini, Grok, Ollama, and Docker Model Runner
★ 4 -
viveka-mcp-serverupdated this year
MCP server for structured iterative reasoning with 13 critical thinking lenses — a disciplined thinking scaffold for AI agents. Features structured reasoning state, cognitive moves (branch/revise/supersede/falsify/verify/retract/stop), Escalation Ladder,
npm MIT -
lensgithub.com/frescodicredito/lensupdated this year
Cognitive infrastructure for LLM reasoning — an MCP server that wraps problems in structural cognitive constraints and runs multi-agent analysis. Navigate the tails of the distribution.
MIT -
ask-fableactive
An MCP (Model Context Protocol) server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils (Gemini, Codex, DeepSeek) in Claude Code and coding agents.
pypi MIT -
chaos2alphagithub.com/superiron888/chaos2alphaupdated this year
AI agent that traces everyday events to US stock signals via butterfly-effect causal reasoning. MCP server.Predict the direction of stocks through daily life events
-
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 -
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 -
dead-letter-oraclegithub.com/tvprasad/dead-letter-oracleupdated this year
Governed MCP agent for DLQ incident resolution with closed-loop reasoning, multi-factor governance, and BlackBox reasoning trace
Apache-2.0 -
reasonforge-publicgithub.com/euuuuuuan/reasonforge-publicupdated this year
A deterministic, read-only reasoning harness that a coding agent can call over 8 MCP tools: it forces a scope lock, a plan whose first move is the cheapest way to be proven wrong, a blind-spot sweep with line-level evidence, and a verdict gate that refuses a verified-fact claim without proof of execution. Read-only is enforced by a test.
Apache-2.0 -
ejentum-mcpno update data
Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.
smithery -
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 -
MemoryLayerno update data
Local-first persistent memory for AI agents, with reasoning and formal verification.
npm -
Graph of Thoughts (GoT) MCP Server — bounded, auditable reasoning for AI agents
npm MIT ★ 1 -
pageindex-light-mcpgithub.com/BukeLy/pageindex-light-mcpupdated this year
Lightweight Agentic PDF Search via MCP — Vectorless, reasoning-based document retrieval
★ 4 -
Goose configuration for Foundation Agent: A physics-inspired, multi-specialist AI system with adaptive reasoning and validated knowledge integration.
MIT -
brier-agentgithub.com/jdshfhds/brierupdated this year
Buyer-run shopping agent MCP server with neutral ranking, reasons, approval, and local audit
npm MIT -
blender-orchestratorgithub.com/mlolson/blender-orchestratorupdated this year
MCP toolset allows agents to control blender. Includes spatial reasoning toolkit for better results.
★ 26 -
Warrantgithub.com/s0fractal/warrantno update data
Record an agent's decisions with reasons anyone can re-execute offline — verify recomputes them.
pypi -
Implementation based on the paper "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory"
go MIT ★ 11 -
ORAM.AI: A Multi-Agent Chatbot with RAG-Based Reasoning and MCP Integration for Adaptive Fitness Recommendation
GPL-2.0 ★ 2 -
A project that integrates mcp servers for Prover9/Mace4 for a logical reasoning agent
★ 1 -
netbox-agent-mcpgithub.com/magicboxlab-ai/netbox-agent-mcpupdated this year
Agentic Model Context Protocol server for NetBox — read-only, tool-rich, built for LLM reasoning workflows
pypi MIT -
agentic-veritasgithub.com/agentralabs/agentic-veritasupdated this year
Intent compilation and uncertainty detection for AI agents — truth verification, ambiguity resolution, causal reasoning. Rust core + MCP server.
cargo MIT ★ 1 -
z39github.com/alejandroqh/z39updated this year
Z3-powered reasoning for AI agents. MCP server + CLI for scheduling, logic, config, and safety.
cargo ★ 3 -
elingupdated this year
Unified second brain for AI agents — 5-tier memory, HRR reasoning, 14 MCP tools, Zettelkasten linking, memory evolution
pypi MIT -
Agent-native, user-owned Harness asset factory with a portable Digital Expert, local MCP operations, deterministic reasoning, lifecycle, and Catalog.
npm Apache-2.0 -
io.github.mifactory-bot/mifactory-logic-verifiergithub.com/mifactory-bot/mifactory-logic-verifierno update data
Verify AI agent reasoning and logic for errors and contradictions. Pay-per-use.
npm -
topolift-mcpupdated this year
MCP server exposing TopoLift's atom-grounded negotiation reasoning to any MCP-compatible agent (Claude Code, Cursor, OpenAI Agents SDK, etc).
pypi MIT -
Persistent reasoning memory for AI coding agents over MCP: decisions, evidence, corrections and experience history.
NOASSERTION -
MCP server for AI agent research — captures LLM reasoning, model identity, and feedback via schema injection
MIT -
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 -
Healthcare Claims Query Agent built with MCP + Groq LLM — answers eligibility, claim status, and denial reason queries in plain English.
MIT -
Multi-agent LLM system for clinical diagnostic reasoning, with structured agent debate and clinical risk-score checks.
-
A stateless, Graph-powered Outlook MCP that enables AI agents to search, retrieve, and reason over email data intelligently.
MIT ★ 1 -
MCP server providing probabilistic reasoning and stochastic thinking tools for AI agents.
MIT ★ 6 -
Agent Deck MCP server — the CWI agent departments shared reasoning layer (stdio). 25-SKU product registry + verified 24-track catalog as read-only MCP tools.
MIT -
pokt-agent-mcpgithub.com/jayanng/pocketagentupdated this year
AI agents that reason about and interact with 52 blockchains — via Model Context Protocol
pypi MIT -
progressive-reveal-mcpgithub.com/colinhale1/progressive-reveal-mcpupdated this year
Working Python MCP server demonstrating progressive reveal, how the protocol guides agent reasoning through layered capability discovery and validation gates.
★ 1 -
asiflow-mcpgithub.com/asiflow/mcp-server-sdkupdated this year
Connect Cursor, Claude Code, and VS Code to ASIFlow's AI reasoning, memory, and multi-agent capabilities
pypi MIT -
AI household safety agent — MCP server for Alexa+ that reasons about events and context before acting, not just forwarding alerts
MIT