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.
-
The LLM Council works together to answer your hardest questions
pypi MIT ★ 49 -
Convert your Obsidian markdown vault into a six-persona MCP team for local LLM tools to provide cited, accurate insights.
GPL-3.0 ★ 1 -
MCP Servers
MIT ★ 1 -
An MCP server that provides LLMs access to other LLMs
go MIT ★ 83 -
Practica con LLM para un gestor de tareas
-
llm-cost-mcpgithub.com/comparedge/llm-cost-mcpupdated this year
MCP server: token cost math for LLM API calls, 69 models across 17 providers, prices verified by ComparEdge
MIT ★ 2 -
See every hop of a request through your local LLM system: a tracing server, a live flow map, a waterfall per request, and an MCP server for Claude Code and Cursor. One static Go binary.
Apache-2.0 ★ 1 -
mcp-llms-txt-explorergithub.com/thedaviddias/mcp-llms-txt-explorerupdated this year
MCP to explore websites with llms.txt files
npm NOASSERTION ★ 78 -
MCP server for interacting with LLMs using LlamaIndexTS
npm MIT -
An MCP server for grabbing music
★ 8 -
gemini-llm-councilgithub.com/theerud/gemini-llm-councilupdated this year
Multi-LLM consensus extension for Gemini CLI. Inspired by Andrej Karpathy's llm-council.
MIT ★ 16 -
Allow any MCP-capable LLM agent to communicate with or delegate tasks to any other LLM available through the OpenRouter.ai API.
MIT -
llm-eval-searchgithub.com/fvahedian/llm-eval-searchupdated this year
—
-
@mseep/mcp-llm-responsesstale
Model Context Protocol server for sharing LLM responses
npm MIT -
llm-context-searchgithub.com/rorlikowski/llm-context-searchupdated this year
Fast LLM-free search-to-context engine for AI agents
pypi MIT -
llm-chess-evaluation-harnessgithub.com/PythonicVarun/llm-chess-evaluation-harnessupdated this year
LLM Chess Evaluation Harness ♟️
MIT -
llm-wiki-mcpgithub.com/sumitroajiprabowo/llm-wiki-mcpupdated this year
MCP server for building and maintaining LLM-powered knowledge wikis. Implements Andrej Karpathy's LLM Wiki pattern.
MIT ★ 6 -
MCP-сервер, который организует работу нескольких LLM на основе паттерна Planner-Executor-Reviewer.
MIT -
A Model Context Protocol server for exploring websites with llms.txt files
npm MIT -
llm-wiki-mcpgithub.com/sumitroajiprabowo/llm-wiki-mcpupdated this year
MCP server for building and maintaining LLM-powered knowledge wikis
npm MIT -
Large Language Model Tool: Greek Lexicon
CC0-1.0 ★ 4 -
Memory framework for LLM
MIT -
llm-wiki-kitgithub.com/iamsashank09/llm-wiki-kitupdated this year
Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your agent remembers forever. Based on Karpathy's LLM Wiki pattern.
MIT ★ 63 -
cucm-mcp-llmgithub.com/simranjit-uc/cucm-mcp-llmupdated this year
MCP-LLM Powered Webex CUCM Assistant
MIT ★ 2 -
让 LLM Agent 像调函数一样驱动一台 Windows 主机:跑 cmd / PowerShell、推拉文件、调用厂商工具,统一返回结构化结果。android-llm-bridge 的姊妹项目。
Apache-2.0 ★ 2 -
LLM Model Context Protocol (MCP) demo using Spring AI
-
Benchmark AI model inference speed — like speedtest.net but for LLMs. MCP server with zero telemetry.
MIT -
@iflow-mcp/aplaceforallmystuff-mcp-local-llmgithub.com/aplaceforallmystuff/mcp-local-llmupdated this year
MCP server for delegating mechanical tasks to local LLMs via Ollama
npm MIT -
—
AGPL-3.0 -
a local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via the Model Context Protocol
MIT ★ 6 -
Give your local LLM internet search — no API keys, no rate limits. Self-hosted SearXNG + FastAPI middleware for LM Studio & Ollama.
★ 2 -
llm-benchmark-mcp-servergithub.com/aiagentkarl/llm-benchmark-mcp-serverupdated this year
MCP Server for LLM comparison, benchmarks, and pricing — find the best model for any task
pypi MIT -
Model Context Protocol (MCP) server for AI & LLM crawler readiness via NPX. Audits robots.txt for AI bots, validates /llms.txt, and verifies markdown mirror content negotiation.
npm MIT -
llm-advisor-mcpgithub.com/Daichi-Kudo/llm-advisor-mcpupdated this year
—
npm MIT ★ 2 -
Веб-сервер позволяющий переделать изображение под стиль мультфилься "Губка Боб"
-
High-performance Go tools for LLM Agents (MCP/CLI). 100x faster than Python. Includes native MCP Server, token-optimized search, and persistent project memory.
MIT ★ 3 -
llm_mcpgithub.com/AuraFriday/llm_mcpupdated this year
MCP server that runs local LLMs (with full access to MCP tools included). Callable by Python to chain MCP tools with local intelligence.
Apache-2.0 ★ 3 -
llm-benchmark-mcp-servergithub.com/AiAgentKarl/llm-benchmark-mcp-serverupdated this year
MCP Server for LLM comparison, benchmarks, and pricing — find the best model for any task
MIT ★ 1 -
A Model Context Protocol (MCP) server providing unified access to multiple LLM providers with cost optimization
pypi MIT License Copyright (c) 2025 Jeffrey Emanuel -
Lightweight read-only multi-agent council for coding CLIs
MIT -
MCP server for local LLM inference on Ryzen AI Max+ 395 with queueing, deadlines and telemetry; benchmark findings
MIT -
llm-context-searchgithub.com/rorlikowski/llm-context-searchupdated this year
llm-context-search is a fast, LLM-free engine that turns web search results into clean, ranked, token-bounded context for AI agents.
MIT -
experimental MCP - encrypted thoughts for LLMs
MIT ★ 2 -
llm-radar-mcpgithub.com/ajentsor/llm-radarupdated this year
MCP server providing real-time AI model intelligence - pricing, capabilities, and recommendations
pypi MIT -
LLM plugins and MCP server for the Black Duck Software Composition Analysis (SCA) products
NOASSERTION -
—
AGPL-3.0 -
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
pypi MIT ★ 129 -
Advanced Knowledge Graph Engine with semantic search and temporal tracking
★ 1 -
An MCP (Model Context Protocol) server that exposes the `llms.txt` file from your project root as a resource for AI context enhancement.
MIT ★ 1 -
Any site's llms.txt: find the covering index, read its linked docs as markdown, search sections.
MIT -
Zero-dependency MCP server and CLI that puts Codex, Claude Code, Grok, Cursor, Antigravity, Pi, OpenAI and local LLMs behind one interface
Apache-2.0 -
Advanced Knowledge Graph Engine with Document Processing, Semantic Search and Multi-LLM Integration
pypi MIT License -
An interactive cyber pet system where AI Agents handle caretaking via MCP.
Unlicense ★ 1 -
llm-usage-mcpgithub.com/zhaoyue722/llm-usage-mcpupdated this year
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP
pypi MIT -
MCP server that gives AI agents a governed wiki — candidates proposed, human approves, wiki updates
MIT -
Model Context Protocol (MCP) server for LLM spend & latency intelligence. Ask Claude why our LLM bill jumped.
★ 3 -
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
npm MIT ★ 2,259 -
🧠 CLI-first knowledge base & second brain for LLMs (Obsidian-style Markdown, wikilinks, core/brain memory, and MCP server)
MIT ★ 1 -
MCP server for delegating mechanical tasks to local LLMs via Ollama. Claude does the thinking, your local model does the grunt work.
MIT ★ 15 -
LLM-Wikigithub.com/Oshayr/LLM-Wikiupdated this year
Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.
MIT ★ 51