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.
-
pro-bridgegithub.com/alubato0127/pro-bridgeupdated this year
Expose web-only GPT Pro (and any ChatGPT model) to MCP clients via your real, logged-in browser
MIT ★ 3 -
image-gen-pro-mcpgithub.com/fledgeling-co/image-gen-pro-mcpupdated this year
Image generation as an MCP tool. GPT Image 2, Gemini 3 Pro Image, or Seedream 4.5 behind one call; reference images and context supported; returns file paths, not megabytes of base64.
npm MIT -
comfyui_LLM_partyygithub.com/heshengta0/comfyui_LLM_partyyupdated this year
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
AGPL-3.0 ★ 2 -
comfyui_LLM_partygithub.com/heshengta0/comfyui_LLM_partyupdated this year
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
AGPL-3.0 ★ 2 -
comfyui_LLM_partygithub.com/heshengtao/comfyui_LLM_partyupdated this year
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
AGPL-3.0 ★ 2,390 -
openrouter-image-mcpgithub.com/tem11134v2-cmd/openrouter-image-mcpupdated this year
Minimal MCP server for image generation via OpenRouter — Nano Banana 2/Pro, GPT-5 Image. One key, six models.
MIT -
Zero-dependency MCP server: image generation (Nano Banana Pro/2, GPT Image 2/2.5) and Suno 5.5 music via VELIN
MIT -
Open-source MCP server giving AI assistants (Claude, GPT, Gemini) complete access to the ArcGIS Pro ecosystem via ArcPy
Apache-2.0 ★ 1 -
Universal MCP server enabling AI clients (Claude Desktop, etc.) to access third-party models (GPT-5, Claude Opus 4, Gemini 2.5 Pro) with intelligent model selection and custom endpoints
npm MIT -
@tenpo/image-mcpgithub.com/tenpo-ai/tenpoupdated this year
Portable image-prompt + image-generation MCP. Faithful to the gpt-image-2 structuring skill (object/scene/vibe/quality/aspect/avoid). Multi-backend: OpenAI (gpt-image-1, dall-e-3), Replicate (Flux 1.1 Pro), fal.ai (Flux dev). Auto-detects which API key yo
npm MIT -
Multi-LLM research MCP server — fan queries to Claude, GPT-4.1, and Gemini 2.5 Pro via OpenRouter, with structured synthesis
MIT -
@micka33/ask-scientistgithub.com/micka33/ask_scientistupdated this year
MCP server for rate-limited consultations with a specialized scientist powered by OpenAI GPT-5.5 Pro.
npm MIT -
claude-code-generate-images-mcpgithub.com/TamerinTECH/claude-code-generate-images-mcpupdated this year
Auto generate and insert image assets during UI coding in Claude Code, using an MCP server for Azure OpenAI gpt-image-1 and Flux-1.1 Pro
MIT ★ 13 -
Ask ChatGPT (GPT-6 Pro, Deep research) from Claude Code and Codex with local files — a plugin + MCP server that uses your own ChatGPT subscription.
MIT -
ckg-mcpgithub.com/yarmoluk/ckg-mcpupdated this year
Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.
pypi MIT -
antigravity-claude-mcpgithub.com/arjunthilak05/antigravity-claude-mcpupdated this year
Give Claude Code a second brain: ask Google Antigravity (Gemini 3 Pro, Claude, GPT-OSS) for an independent code review / second opinion via MCP. One command, zero deps.
npm MIT ★ 3 -
antigravity-claude-mcpgithub.com/arjunthilakeros/antigravity-claude-mcpupdated this year
Give Claude Code a second brain: ask Google Antigravity (Gemini 3 Pro, Claude, GPT-OSS) for an independent code review / second opinion via MCP. One command, zero deps.
MIT -
image-proxy-mcpgithub.com/lproux/mcp-orchestrationupdated this year
MCP server that proxies image generation to Azure (GPT-Image, DALL-E 3, FLUX Kontext Pro), saves to local disk, and returns file paths instead of base64 to keep context windows clean.
npm MIT -
oraclegithub.com/mazdak/oracleupdated this year
Oracle is a coding-focused MCP server that uses OpenAI's gpt-5-pro model with high reasoning to answer questions about your code. Use the `solve_coding_problem` tool with a coding problem and optional file paths; it will analyze the problem and files and propose concrete fixes.
-
repo-bridgegithub.com/zcrossoverz/repo-bridgeupdated this year
Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.
npm MIT ★ 4 -
Image and video generation as an MCP tool. GPT Image 2, Gemini, Recraft, Seedream, Grok, Arrow SVG, plus MiniMax and Seedance video; reference images and context supported; returns file paths, not megabytes of base64.
npm MIT -
Model Context Protocol server for the expanded Kie.ai image and video generation APIs
npm MIT -
ChatGPT <-> Codex bridge: local coding agents ask ChatGPT for advice, and ChatGPT can inspect or steer your running Codex sessions. No API key.
MIT ★ 14 -
An open-source bridge between AI assistants and Adobe Premiere Pro, for supported editing workflows. Go, Rust, Python, and TypeScript.
go MIT ★ 148 -
An LLM-powered, autonomous coding assistant. Also offers an MCP and ACP mode.
go MIT ★ 190 -
10 Chinese AIGC, ecommerce, image and video MCP Spaces powered by AI-HIVE
MIT