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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
An mcp server to inject raw chain of thought tokens from a reasoning model.
★ 12 -
@iflow-mcp/liorfranko-mcp-chain-of-thoughtgithub.com/liorfranko/mcp-chain-of-thoughtupdated this year
Chain of Thought is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavi
npm MIT -
Chain of Thoughts (zoth-cot): zero-dependency working memory and reasoning log for AI agents, with an MCP server. Free and open source.
-
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 -
Servidor MCP com CoConuT (Continuous Chain of Thought) para uso com Cursor IDE - Pacote Global NPM
npm MIT -
thinker-contextgithub.com/yourusername/thinker-contextupdated this year
Thinker Context - MCP server for AI-powered context management and chain-of-thought planning with DeepSeek-V3.1
npm MIT -
Enterprise AI Meeting Agent: Contextual ASR speech repair, multi-turn Chain-of-Thought commitment disambiguation, and gated MCP tool execution.
MIT -
Enhanced MCP Shrimp Task Manager with comprehensive LLM integration. A task management tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. Features real GPT-4 ↔ MCP tools communication, comprehensive testing pipeline
npm MIT -
branch-thinkinggithub.com/m-siles/branch-thinkingupdated this year
MCP tool to allow multiple chains of thought
MIT ★ 43 -
This is a Chain-of-Recursive-Thoughts (CORT) MCP server.
MIT ★ 5 -
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 -
cotforce-mcpgithub.com/islobodan/cotforce-mcpupdated this year
Give brains to your small models. MCP server that enforces step-by-step Chain-of-Thought — turns 4B models into methodical reasoners
MIT -
deepseek-mcp-servergithub.com/deepzhun/deepseek-mcp-serverupdated this year
A small, clean MCP server for the DeepSeek API — V3 generation, chat, and R1 reasoning with visible chain-of-thought.
MIT ★ 1 -
Taskerson MCP is a tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior
npm MIT -
Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
MIT -
Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like develope
npm MIT -
Answer your AI coding agent from Home Assistant or your terminal — GitHub Copilot CLI, Claude Code, Codex CLI, or any MCP client. Per-session dashboard cards, live activity, chain-of-thought, and answers typed straight back into the terminal.
MIT -
Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
go MIT ★ 2,150 -
Clear Thought MCP server with modular architecture - 38 reasoning operations for systematic thinking
npm MIT -
codex-thinking-blockgithub.com/sibylsea-hub/codex-thinking-blockupdated this year
在自建前端展示 codex 的思考链:关闭原生推理,用一个 MCP 工具承接该轮思考。含两版实现、档位验证、调用率实测与可运行前端。
MIT ★ 1 -
thinker-mcpupdated this year
MCP server that clarifies prompts, loads context, and chain-thinks before coding — giving AI assistants persistent project memory
npm MIT -
tool to get the best results out of an LLM!
npm ISC -
claude-orator-mcpgithub.com/Vvkmnn/claude-orator-mcpupdated this year
🪶 An MCP server for prompt optimization in Claude Code
npm MIT ★ 2 -
forced-reasoning-mcpactive
MCP server exposing the Forced-Reasoning scratchpad tool from arXiv 2609.26637v1 Appendix B, for extracting model reasoning through a tool channel.
npm MIT -
Enhanced sequential thinking MCP server for advanced reasoning and problem-solving with Cursor AI
npm MIT -
SequentialThinkinggithub.com/LseKit/SequentialThinkingupdated this year
Multi-step sequential thinking MCP server powered by large language models — structured reasoning with self-MoA and iterative thinking modes
pypi MIT ★ 1 -
Reasoning orchestration MCP server — Tree of Thoughts with deep planning, branching, and revision. Drop-in replacement for sequential-thinking with critical Claude Code string coercion fix. Works with Claude Code, Claude Desktop, and any MCP client.
npm MIT ★ 3 -
steelmind-mcpgithub.com/stabgan/steelmind-mcpupdated this year
Research-grounded structured thinking + steel-manning verification for AI agents via MCP. Sequential step tracking with cognitive mode separation. Backed by 43+ papers.
npm MIT ★ 1 -
Find the RAG retrieval setup that works on your data, then use it automatically. HyDE, Step-Back, Fan-Out, hybrid BM25 search and reranking, benchmarked on your documents (Markdown, HTML, PDF, DOCX) and routed per query, with citations and streaming, for
npm MIT -
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks
npm MIT ★ 506