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.
-
MCP server for structured decision-making - weighted decision matrices, criteria scoring, sensitivity analysis and a defensible recommendation
MIT ★ 2 -
Decision MCP by BuildWorks.AI — sequential thinking, decision-making, and analysis server for MCP-compatible IDEs.
npm MIT -
mcp-choice-enginegithub.com/cskwork/mcp-choice-engineupdated this year
MCP server for structured decision-making with weighted criteria
-
MCP server for stochastic algorithms and probabilistic decision making
npm MIT -
Model Context Protocol (MCP) Server for Pros-Cons (Decision Making App)
npm MIT -
@iflow-mcp/yodakeisuke-mcp-desicivegithub.com/yodakeisuke/mcp-decisiveupdated this year
MCP server for WRAP decision-making framework with structured output
npm MIT -
free MCP server with 7 decision-making mental models for Claude. By SigmaMax AI Solutions.
MIT ★ 1 -
AskAway Model: hooks and MCP that make Claude Code, Claude Desktop and Codex delegate decisions to TypeSafe JEV through a local gateway.
Apache-2.0 -
The decision-making apps platform. Multidimensional models, role-based workflows, connectors, automation triggers, MCP server and AI builder. Unlimited users. Free to self-host for internal company use.
NOASSERTION -
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.
-
SEEK4INFOgithub.com/AyacodeYa/SEEK4INFOupdated this year
Offer Matcher is an intelligent job-seeking decision-making assistant based on the MCP protocol and local Ollama large model. It helps job seekers quickly analyze position fit and provides professional decision-making recommendations.
MIT -
A shared planning board where humans and agents make decisions together, over MCP
npm Apache-2.0 -
Deliberation and Decision Making MCP Server
MIT -
useminditgithub.com/dragoon0x/useminditupdated this year
mindit — AI skills that find the design decisions you didn't make. Eight forces, eleven skills, scored output. v2 adds a CLI, MCP server, and decision-graph linter.
npm MIT -
Thoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.
npm MIT ★ 66 -
An MCP server that delivers crypto ETF flow data to power AI agents' decision-making.
MIT ★ 9 -
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 -
TruthTrailno update data
Record the decisions your AI coding agent makes, in the repo and on the Jira or GitHub ticket.
npm -
taste-mcpgithub.com/JVPVO/taste-mcpupdated this year
a mcp that enables agents to make decisions based on your bookmarks
★ 1 -
将你的jev变成mcp插件,接入任意agent(Claude,codex,Cherry Studio)。辅助llm决策层。Turns your jev into an MCP plugin, helping LLM make decisions.
MIT -
vote-mcp-serverupdated this year
MCP server for Vote-MCP: Democratic decision-making for AI agent collectives
npm MIT -
MCPgithub.com/JorgeDelAngel03/MCPupdated this year
Model Context Protocol (MCP) server for the Claude agent, designed to make randomized (weighted) decisions and maintain a persistent history.
-
@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 -
Model Context Protocol (MCP) Server providing sophisticated financial calculation functions for business intelligence and strategic decision-making. ONLY FOR EDUCATIONAL PURPOSES.
MIT -
An MCP (Model Context Protocol) server designed to automate SRE tasks, runbooks, and interactive playbooks with AWS Bedrock integration for intelligent decision making.
-
hive-mind-mcp-servergithub.com/AiAgentKarl/hive-mind-mcp-serverupdated this year
Swarm intelligence for AI agents — collective decision-making through weighted consensus voting
pypi MIT -
QuantiaBayes Financial MCP. A Research-Grade Financial MCP implementing Hierarchical Bayesian Inference (HMC) and Reinforcement Learning (PPO) for risk assessment and autonomous decision making.
-
Multi-agent thinking methodology MCP tools for strategic analysis and decision-making
npm MIT -
rise-local-lead-creationgithub.com/JSXSTEWART/rise-local-lead-creationupdated this year
Complete Agent Orchestration System: - Zapier AI agents for workflow orchestration - Claude agents for intelligent decision-making - MCP server as unified tool gateway - Hybrid data architecture (Supabase + Zapier Tables)
MIT -
mcp-rizz-gamemakergithub.com/taborgreat/mcp-rizz-gamemakerupdated this year
A React-wrapped HTML GameMaker game controlled by an authoritative Node.js WebSocket server (acting as the MCP client) that communicates with a custom MCP server for in-game intelligence/decision making.
-
Local-first, definition-driven research-to-code harness. Keeps intent, research, decisions, and code connected across Claude Desktop and Antigravity, and makes drift visible.
npm MIT -
MCP server for Pokémon Champions competitive play: official Regulation Sets, usage-derived meta, and battle math for team building and decision making
npm MIT -
Clear Thought Serverno update data
Provide systematic thinking, mental models, and debugging approaches to enhance problem-solving capabilities. Enable structured reasoning and decision-making support for complex problems. Facilitate integration with MCP-compatible clients for advanced cognitive workflows.
smithery -
🔌 Exposes GDPR compliance over MCP — DPIA automation, Article 30 records, Article 22 automated decision-making audit, data subject request workflow.
pypi MIT ★ 1 -
Provide enhanced problem-solving capabilities by leveraging systematic thinking, mental models, and debugging approaches. Enable structured reasoning and decision-making support for complex challenges. Facilitate integration with MCP-compatible clients for advanced cognitive workflows.
smithery -
Agentic AI trading system that uses MCP servers for portfolio control, market data, and push alerts. Trader agents make buy/sell decisions, while Researcher agents gather and analyze market signals.
-
CognitiveBiasLabs-MCPgithub.com/double2dev/CognitiveBiasLabs-MCPupdated this year
Official MCP Server for Cognitive Bias Labs. An AI-powered diagnostic engine to detect cognitive biases in text and decision-making.
-
An agent-driven equity trading system for Robinhood, built on the Robinhood MCP server. Claude orchestrates; a deterministic Python core makes every decision.
★ 2 -
polymarket-agentsgithub.com/artvandelay/polymarket-agentsupdated this year
Polymarket research MCP server with 10 tools (odds, orderbook, spread, history) + autonomous trading bot framework. Claude Sonnet decision-making, pluggable strategies, SQLite persistence
MIT ★ 4 -
Standalone server designed to deliver market data insights to AI trading agents. It processes data from external brokers and computes structured information to help LLMs and other AI systems make more informed trading decisions using JSON RPC protocol
★ 4 -
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.
-
Chain of Draft Server is a powerful AI-driven tool that helps developers make better decisions through systematic, iterative refinement of thoughts and designs. It integrates seamlessly with popular AI agents and provides a structured approach to reasoning, API design, architecture decisions, code reviews, and implementation planning.
MIT ★ 24 -
A proactive, headless contextual intelligence layer for the hospitality sector. It predicts the impact of a property's environment on guests' experience, optimizing decision making and operations.
MIT ★ 3 -
Engineering-first design system for complex apps. Makes UI and UX decisions explicit for engineers and AI agents. Components, agent rules, CLI and MCP server.
NOASSERTION ★ 1 -
An AI trading agent that is never allowed to make a trading decision. Deterministic Python core. Every rule is in tested code, not prompt text.
MIT ★ 2 -
Bring your toughest question to a team of AI advisers. They examine the evidence, challenge the plan and keep their objections on the record. You make the final decision.
Apache-2.0 -
An explainable AI healthcare system that predicts diabetes risk using ML, MCP, and SHAP-based insights. It delivers transparent, clinically meaningful assessments through a modern microservices architecture, enabling healthcare professionals to make clear, data-driven decisions.
MIT -
scheduleroraclegithub.com/ToolOracle/scheduleroracleupdated this year
SchedulerOracle — Persistent Autonomous Task Scheduler MCP for AI Agents. 9 tools: cron/interval/one-time scheduling, auto-store results in MemoryOracle, optional Decision Preflight gate, execution history. The motor that makes agents work 24/7.
NOASSERTION -
Pattern checks a coding agent's UI decisions against your own design system before it builds, whether that lives in code or in Figma. It helps the agent reuse what the product already has and build only what is actually missing. An opt-in enforcement boundary can make that check required, and every decision is recorded in an auditable ledger.
npm MIT ★ 9 -
mcp-rerankergithub.com/globalpocket/mcp-rerankerupdated this year
A generic Model Context Protocol (MCP) server for high-accuracy document reranking using sentence-transformers (Cross-Encoder). Ideal for enhancing RAG and AI agent decision-making. sentence-transformers (Cross-Encoder) を使用して文書の関連度を再計算・ソートする汎用 MCP (Model Context Protocol) サーバー。
Apache-2.0 ★ 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 -
Session memory for AI coding agents. Records decisions, dead ends and assumptions as they happen, makes them greppable, and tells you when what you wrote stops being true. MCP server for Claude Code.
pypi Apache-2.0 ★ 1 -
Interpleadergithub.com/Shanks-btc/Interpleaderupdated this year
A real-time financial and on-chain intelligence agent for AI systems that need live market data to make decisions. Interpleader exposes 10 tools across 3 independently-sourced data providers: Bitcoin market cycle analysis (MVRV ratio, entry risk classification, long-term holder behavior, and 2021-cycle-top comparison), short squeeze risk detection
-
Venom AI by Venom Labs: make the coding agents your team already uses multiplayer. The Venom MCP plugin connects Claude Code, Codex, Cursor and Gemini CLI so they share tasks, decisions, skills and tools.
MIT -
Multi-tenant agent for telecom billing disputes: classifies disputes, retrieves tariff and contract clauses alongside invoice and call records, and makes cited credit decisions, with deterministic credit calculation, fraud escalation and CI-gated evals. LangGraph, MCP, fine-tuned classifier vs LLM baseline
MIT -
mcp-marionettegithub.com/overbit/mcp-marionetteupdated this year
The MCP Marionette server provides a bridge for AI agents to interact with humans for decision-making, clarification, and session steering. It implements the Model Context Protocol (MCP) to allow agents to pause their execution and wait for human input th
npm MIT -
Multi-AI consensus MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel and synthesizes responses to reduce bias and improve accuracy. A Python implementation of the wisdom-of-crowds approach for AI decision making.
pypi MIT ★ 33 -
AgentCall is an open-source platform that lets AI agents call you when they need help. When an AI gets stuck — needs approval, clarification, or urgent input — it rings your phone via a real voice call. Chat, make decisions, and send the AI back to work. Self-hosted, private, no records. Works with Claude, Cursor, OpenCode, and any MCP-compatible.
MIT ★ 3 -
pbxgithub.com/zamfono/pbxactive
Self-hosted cloud PBX for small businesses (5–20 users). Asterisk 22 carries calls; a Node.js control plane makes every routing decision over ARI. Run it with Docker or Podman Compose on one SQLite database, and administer it through a REST API or an MCP client like Claude Code. Ringotel softphones, voicemail, recordings, backups. AGPL.
AGPL-3.0 ★ 2 -
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