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.
-
智谱 GLM Coding Plan 视觉理解 MCP Server,对标官方 @z_ai/mcp-server
npm MIT -
mcp-ocr-glmgithub.com/iwanro/mcp-ocr-glmupdated this year
Free OCR and vision for any MCP-capable AI coding client, powered by GLM-4.6V-Flash. Drop-in MCP server, no API key required.
MIT -
MCP server that turns Codex into a conductor for a multi-model coding pipeline: split plan → code with GLM → review with another model → auto-fix, all sandboxed with git commit/push blocked.
★ 1 -
OpenAI-compatible API for DeepSeek, Qwen, GLM, Kimi, MiMo, Hunyuan, Claude, GPT, Gemini and Grok. One key, payment in rubles. MCP server included.
MIT -
OpenAI-compatible Python SDK + MCP server for 110+ Chinese frontier AI models (DeepSeek, Qwen, GLM, Kimi, Seedance) via NovAI. Zero platform fee.
MIT -
rew-mcpgithub.com/koltyj/rew-mcpupdated this year
MCP server for Room EQ Wizard measurement analysis. Enables AI-assisted speaker placement decisions and validation of Genelec GLM calibration.
npm MIT -
mcp-local-visiongithub.com/jshsakura/mcp-local-visionupdated this year
Give text-only LLMs (GLM, DeepSeek, ...) eyes. MCP server that reads images and PDFs with a vision model on your own GPU — no API keys, nothing leaves the machine.
-
@iflow-mcp/jochenyang-luma-mcpgithub.com/jochenyang/luma-mcpupdated this year
Multi-model vision understanding MCP server. Supports GLM-4.6V (Zhipu), DeepSeek-OCR (SiliconFlow - Free), Qwen3-VL-Flash (Aliyun), and Doubao-Seed-1.6 (Volcengine)
npm MIT -
MCP server for delegating tasks to specialized AI assistants in Cursor, Claude Code, Codex, Command Code, Google Antigravity, Gemini, GLM, Kimi, Grok, OpenCode, MiniMax Code, and Pi
npm MIT -
Z.ai (GLM Coding Plan) plugin for DeepSeek Harness (dsh): web_search via the web_search_prime MCP server, mcp__zai__web_search_prime tool, and a live quota chip. International api.z.ai endpoint — for users outside mainland China.
MIT ★ 2 -
Official Model Context Protocol (MCP) server for WarungCyber AI Gateway — Connect Claude Desktop & Cursor to 19 AI models (Claude, Gemini, DeepSeek, Qwen, GLM, Kimi, GLM 5.3 Uncensored) with pay-as-you-go pricing. Top up Rp 18.000/$1 via QRIS.
MIT -
为claude code+glm 添加上眼睛
★ 62 -
zhipu-vision-mcpgithub.com/apsuadwf/zhipu-vision-mcpupdated this year
智谱视觉 MCP Server — 为 DeepSeek 等纯文本模型提供免费视觉能力(GLM-4V)
MIT -
Claude Code plugins: work tracking, statusline lab, token-usage panes, GLM quota, readability + local-LLM MCP servers
npm MIT -
本地优先的多模态视觉 MCP —— 为无视觉 LLM(DeepSeek、GLM 等)提供可自定义端点的看图 / OCR / 文档解析能力。
MIT -
z-ai-image-mcpgithub.com/georgh93/z_ai_image_gen_mcpupdated this year
MCP server for Z.AI image generation models (GLM-Image, CogView-4)
npm MIT -
让 Claude Code / Codex 等主导智能体通过 MCP 调度 DeepSeek、GLM 等模型和命令行智能体的轻量中枢 | A lightweight MCP hub for multi-agent delegation
MIT -
google-search-mcp-v2github.com/ye4wzp/google-search-mcp-v2updated this year
Google Search MCP Server - 优化版,支持双平台图片搜索(Google+Pinterest)、多模型AI分析(GLM/GPT/Claude)、S/A/B/C质量评分
MIT -
基于大语言模型的自然语言数据库查询与分析工作台(NL2SQL + 图谱 Schema Linking + AST 安全护栏 + 业务语义层 + MCP 服务中心 + RBAC 权限管理),内置 FastAPI + React 工作台,支持 DeepSeek / GLM / OpenAI / Qwen / Gemini / Ollama
MIT ★ 11 -
llm-vision-mcpgithub.com/me9rez/llm-vision-mcpupdated this year
给文本模型装上眼睛:MCP Server 借助 OpenAI 兼容视觉模型(默认 ModelScope 免费通义千问VL)把图片文件转为文字描述,让 DeepSeek/GLM 等文本模型也能看图说话。本地 stdio 运行,Claude Code / Opencode 即插即用。
MIT ★ 4 -
Let Claude (Code & Desktop) delegate tasks to any OpenCode model — Grok, Kimi, GLM, Qwen, DeepSeek… — while staying the orchestrator. MCP server + Claude Code plugin.
MIT ★ 6 -
MCP server: ask or compare other AI models (DeepSeek, GLM, Claude...), web search and balance via Ezkielyna API
MIT -
AarnXen-MultiAI-MCPgithub.com/Abhishek-Kraj/AarnXen-MultiAI-MCPupdated this year
Multi-model AI orchestration MCP server — 31 tools, 25+ models (Gemini, DeepSeek, Kimi, Qwen, GLM, MiniMax), memory flywheel, web grounding. Works with Claude Code.
MIT -
image-vision-mcpgithub.com/staticdeng/image-vision-mcpupdated this year
Multi-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.
npm MIT -
MCP server for onomeo: ask free LLMs (DeepSeek, GLM, Gemini, Mistral and more) for a second opinion from Claude Code, Cursor, Cline or any MCP client.
MIT -
A股多Agent量化交易决策框架 — LangGraph 15位AI分析师辩论式分析,反思闭环+Token优化,支持DeepSeek/Qwen/GLM,附零依赖MCP server | Multi-agent A-share trading framework with reflection loop & MCP server
MIT ★ 4 -
Self-hosted VLM image-recognition MCP server (stdio). Paste an image in Claude Code / Codex / OpenCode → get recognition. OpenAI-compatible backend (vLLM / Ollama / GLM-4V / Qwen-VL).
MIT ★ 1 -
LLM-bridge-mcp-servergithub.com/Magnexis/LLM-bridge-mcp-serverupdated this year
`LLM-bridge-mcp-server` is a local-first MCP server that lets Codex, Claude Desktop, and other MCP-compatible hosts use GLM-5 as a knowledge consultant, reasoning specialist, UI auditor, repository inspector, and approval-gated development assistant.
NOASSERTION -
MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.
npm MIT ★ 50 -
MCP server that lets Claude Code delegate heavy-token tasks to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Claude orchestrates; the delegate does the heavy lifting. Zero dependencies.
npm MIT -
Cut Claude Code costs: Claude stays the brain while its subagents run on cheaper models (OpenRouter, DeepSeek, Qwen, GLM, Kimi). Rust CLI, local proxy and MCP server with secret/PII redaction, budgets and savings reports.
MIT ★ 1 -
The MCP with the cats inside. One door for your AI into the whole Catzoid litter — Claude, Gemini, GPT, GLM, any assistant that speaks MCP can wake a DevCatz site, ask DBCatz a read-only question or send a DialCatz request. One connection, every cat. You hold the keys.
Apache-2.0 -
Delegate tasks from Claude Code to the AI accounts you already pay for. Claude plans the work, and omnitrix routes each task to Codex, Gemini, DeepSeek, Kimi, GLM, a local model or any OpenAI- or Anthropic-compatible API while tracking each account's usage.
Apache-2.0 ★ 2 -
AIXX MCP server — one API key to every AI model (Claude/GPT/Gemini/DeepSeek/Qwen/GLM) + image & video generation. Unified AI gateway, OpenAI-compatible. By AIXX (Wanan Exchange), the verification-first compute exchange. Works with any MCP client (CodeBudd
npm MIT -
freemodel-mcpgithub.com/yummy342/freemodel-mcpupdated this year
Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%
npm MIT -
Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%
npm MIT -
UnrealGenAISupportgithub.com/prajwalshettydev/UnrealGenAISupportupdated this year
Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agentic, chat, 3D gen, TTS, multimodal, image gen. UnrealMCP/UnrealClaude
MIT ★ 686 -
Context-Engine MCP - Agentic Context Compression Suite
MIT ★ 402 -
codex-vision-bridgegithub.com/raven-moonfade/codex-vision-bridgeupdated this year
为纯文本 Codex 模型补上看图能力的 MCP 工具:支持 describe(看图描述/OCR)、locate(界面元素定位)、photo(图片内容保真)、ui(界面读屏)四种模式。一条命令安装。
MIT ★ 1 -
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
npm MIT ★ 98 -
Full-featured MCP server for aaPanel management. 282 tools across 19 modules.
MIT ★ 5 -
Professional AI research tool for Zotero: chat with PDFs, whole-library search, Literature Radar, AutoPilot. 30+ LLMs or local models; built-in MCP server.
AGPL-3.0 ★ 2,708 -
Delegate work from Claude Code to workers on Codex, Z.ai and Command Code, with a record of every run
MIT -
PDFDashboardWithMCPgithub.com/dakshp26/PDFDashboardWithMCPupdated this year
Upload PDFs, extract text via OCR/PyMuPDF RAG Pipeline, and chat with your documents using a local LLM — fully offline via Ollama, with a Streamlit dashboard and MCP server for AI assistant integration.
AGPL-3.0 -
code-assistant-peersgithub.com/AnamKwon/code-assistant-peersupdated this year
MCP server for mandatory peer review between coding assistants like Claude Code, Codex, Gemini, and other CLI agents.
MIT ★ 11