aigate MCP server
2026년 11월 5일 커밋추론, 브라우저 자동화, 코드 실행 및 미디어 처리를 위한 OpenAI 호환 엔드포인트를 제공하는 셀프 호스팅 AI 플랫폼입니다.
다른 이름 psyb0t/aigate
- 스타
- 18
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 11월 5일
- 라이선스
- WTFPL
aigate MCP란?
추론, 브라우저 자동화, 코드 실행 및 미디어 처리를 위한 OpenAI 호환 엔드포인트를 제공하는 셀프 호스팅 AI 플랫폼입니다.
프로젝트 README에서 생성된 요약
aigate MCP server 정보
aigate는 올인원 인프라가 필요한 개발자를 위해 단 한 번의 명령으로 셀프 호스팅 AI 생태계를 구축할 수 있게 해줍니다. localhost:4000에서 OpenAI 호환 엔드포인트를 제공하며, Ollama 또는 vllm-wrap을 통한 로컬 하드웨어부터 Groq 또는 OpenRouter와 같은 클라우드 서비스까지 다양한 모델 프로바이더에 연결됩니다. 이 플랫폼은 function-calling 모델이 통합된 다양한 도구를 사용하여 복잡한 워크플로우를 자율적으로 조율할 수 있는 중앙 허브 역할을 합니다.
사용자는 봇 탐지를 우회하기 위한 스텔스 브라우저 클러스터, Piston을 통한 샌드박스 코드 실행, 고급 미디어 처리와 같이 선택적으로 컨테이너를 배포하여 특정 기능을 사용할 수 있습니다. 시스템에는 audiolla를 이용한 오디오 제작, flickies를 이용한 비디오 편집, predictalot을 이용한 시계열 예측을 위한 전문 도구가 포함되어 있습니다. 또한 Telegram 클라이언트와 이메일 게이트웨이를 통해 통신을 관리합니다. 이 설정은 로컬 프라이버시와 웹 검색, 이미지 생성, 유형화된 의사 결정과 같은 고수준의 에이전트 기능을 결합하고자 하는 사용자를 위해 설계되었습니다.
활용 사례
- 1자동 웹 리서치모델이 브라우저를 열고 페이지를 읽은 뒤 조사 내용을 요약하도록 하여 특정 주제를 조사하게 합니다.
- 2결정론적 코드 연산execute_code 도구를 사용하여 보안 샌드박스 내에서 복잡한 계산이나 데이터 변환을 수행합니다.
- 3고급 오디오 및 비디오 편집에이전트에게 미디어 파일의 stem separation, face restoration 또는 lip-syncing을 수행하도록 지시합니다.
- 4예측 데이터 분석시계열 데이터를 플랫폼에 전달하여 파운데이션 모델을 사용한 예측치를 생성합니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능psyb0t/aigate is public and reachablegithub.com/psyb0t/aigate ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)WTFPL is not OSI-approvedspdx.org/licenses/WTFPL.html ↗결함 발견
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-05github.com/psyb0t/aigate ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음0 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기aigate
A self-hosted AI platform. One docker-compose up.
Everything an AI-powered workflow needs, inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, web search, an email gateway, a Telegram client, time-series forecasting, typed decisions, an async job queue, and a web UI, behind a single OpenAI-compatible endpoint at http://localhost:4000. Point any existing client at it and it works.
Models and routing
Models across multiple providers. Five providers offer free tiers (Groq, OpenRouter, HuggingFace, Mistral, Cohere). Free means rate-limited and capped, not unlimited. Cerebras needs a paid plan as of the last audit. See free-tier reality check for exact RPM/RPD/monthly caps before relying on a tier. Local providers run on your own hardware, CPU or NVIDIA GPU, with no network calls, rate limits, or usage costs. They include Ollama, talkies for ASR and TTS, vllm-wrap for text LLMs and embeddings, llama.cpp for Surya OCR 2 and Qwen3-8B embeddings, stable-diffusion.cpp, audiolla, predictalot, and decidealot. The gateway tries providers in priority order and falls back when one rate-limits or fails.
Tools and capabilities
MCP tools across multiple servers. Any model with function calling can invoke them autonomously — the model orchestrates, you just prompt.
- Stealth browser cluster — 5 Camoufox replicas behind HAProxy, real OS-level mouse and keyboard input, zero CDP exposure. Passes Cloudflare, CreepJS, BrowserScan, and every other bot detector we've thrown at it.
- Two agentic coding agents — full shell access, persistent workspaces, file I/O, tool use. Claude Code (your subscription or API key) and pi-coding-agent pointed at z.ai for GLM models. Both expose REST API, OpenAI-compatible endpoint, and MCP server.
- Sandboxed code execution — piston at
/piston/. Multi-language code execution in nsjail-isolated sandboxes (own user namespace, chroot, seccomp, cgroups, no network). Default install: Python + Node. Add Bash / Deno / Go / Rust / TypeScript / 40+ other languages viaPISTON_LANGUAGES+ rebuild. REST API +execute_codeMCP tool any function-calling LLM can call to compute deterministic results (hashes, parses, transforms) instead of guessing. - Object storage — S3-compatible, public-read uploads, presigned URLs, auto-expiry. Plain HTTP and boto3.
- Image generation — FLUX, DALL-E, Stable Diffusion (cloud + local CPU/CUDA via stable-diffusion.cpp) via MCP tools that return persistent URLs, not base64 blobs. Local CPU: sd-turbo, sdxl-turbo. Local CUDA adds: sdxl-lightning, flux-schnell, juggernaut-xi.
- Text-to-speech — Kokoro (CPU + CUDA-ONNX, English+Chinese, voice presets), Qwen3-TTS (CUDA, voice cloning + voice-design + emotion control via the
instructionsfield), OpenAI TTS. - Transcription — Whisper (cloud + local CPU/CUDA), Parakeet (~3400× real-time on CPU).
- Web search — SearXNG self-hosted meta-search (Google, Bing, DuckDuckGo, Wikipedia) via MCP
search_webtool. - Telegram client — Telethon at
/telethon/. Send/read/edit/delete messages, list dialogs, forward, send files from URL, manage group membership. REST API + MCP tools. - Email gateway, mailbox at
/mailbox/. IMAP+SMTP across N accounts from one YAML config, unified inbox, per-account list/search/CRUD, SMTP send. REST API + flat MCP tool set (mailboxparameter selects account). - Time-series forecasting + tabular ML — predictalot at
/predictalot/. Five foundation forecasters (chronos-2, timesfm-2.5, moirai-2, toto-1, sundial-base-128m) across six forecast types (univariate, multivariate, past/future covariates, samples) with per-type weighted ensembles at/v1/timeseries/<type>/…+ a sibling/v1/tabular/*family in v1.0.0 — 9 supervised backends (lightgbm, xgboost, hist-gbt, random-forest, logistic, mlp, svm-rbf, knn, naive-bayes) and 3 meta-learners (calibrated / stacking / diversified). REST API for both families + 27 MCP tools (foundation-model forecasting plusunload_models, tabular is REST-only). CPU or CUDA. - Typed decisions: decidealot at
/decidealot/. Local Laya, Von, and CLM are enabled by default. Hosted TypeSafe Jev enables when its key is configured. Send astateplus namedchoice,score, ornoulquestions and get typed answers with model probabilities, so the caller sets its own threshold. Laya routes between English and multilingual checkpoints and has a checkpoint tuned for policy, routing, and triage decisions. Von is English-only, for short questions with clear criteria. CLM calls AIGate's internal Qwen3-8B embeddings route;make run-bgstarts its CUDA encoder automatically. SetDECIDEALOT_CLM_ENABLED=falseto remove that GPU dependency. REST API, batch decisions, and 4 MCP tools. CPU or CUDA. - Audio production — audiolla at
/audiolla/. Stem separation (Demucs / UVR), restoration (UVR de-reverb / de-echo / de-noise), mastering (matchering / pedalboard chains + curated presets likemaster-for-spotify,podcast-cleanup,vocal-cleanup), MIR analysis (BPM / key / LUFS / beats / onsets / melody / chords / segments), DSP transforms (sox + ffmpeg), loudness normalization, speech enhancement (DeepFilterNet), VAD (silero), diarization (pyannote), CLAP embeddings + zero-shot classification, AudioSet tagging (AST), audio→MIDI (basic-pitch), MIDI compose / inspect / transform / render via fluidsynth, text-to-audio generation (stable-audio-open / musicgen / riffusion / audioldm2 — CUDA only), ad-hoc op-chain pipelines, async jobs + webhooks. REST API + MCP tools. v1.0+ contract: JSON body on every audio endpoint, raw bytes only atPUT /v1/files/{path},output_pathxoroutput_urlmandatory for any audio-producing call. - Video toolkit — flickies at
/flickies/. Lipsync via LatentSync 1.5 (ByteDance, Apache-2.0, ~8 GB VRAM, default on CUDA) and Wav2Lip / Wav2Lip-GAN (LRS2 non-commercial, gated). Face restore via GFPGAN v1.4. ffmpeg ops — trim, concat, transcode (incl. gif + fps + codec change), scale, mux audio, extract audio, thumbnail grid. ffprobe info. Async jobs + webhooks. REST API + 11 MCP tools. Same JSON-body +output_pathxoroutput_urlcontract as audiolla. GFPGAN + LatentSync 1.5 are CUDA-only; CPU image runs ffmpeg ops + slow Wav2Lip-CPU.
Ask a Groq model to research something and it opens a browser, reads pages, screenshots them, uploads to storage, and comes back with a summary and links. The model decides what tools to use and in what order.
Web UI
LibreChat at /librechat/ — pre-configured with all models and MCP tools, conversation history, file uploads, WebSocket streaming. Email/password auth, first user becomes admin.
Infrastructure
Multiple containers. Nginx reverse proxy. PostgreSQL + MongoDB for persistence. Two Redis instances (cache + browser session sync). Async job queue for long-running inference. Cloudflare Tunnel for public exposure with zero open ports.
Security
Network-isolated by default — internal services have no host ports. Every endpoint requires auth. Application containers carry no-new-privileges:true (genuine carve-outs: piston needs privileged:true for nsjail; tailscale needs NET_ADMIN for the userspace tun device). File path pre-flight validation on startup.
Everything is opt-in
Enable what you want in .env, ignore what you don't. The core stack (nginx, LiteLLM, PostgreSQL, Redis, proxq) is always on. Every provider, local model, MCP server, and extra service is a flag flip away.
make run-bg. That's the whole install.
Architecture
client
▼
cloudflared (CLOUDFLARED=1) │ tailscale (TAILSCALE=1, tailnet-only)
▼
nginx :4000 ┌──────────── always on ────────────┐
├─► /claudebox/ → claudebox │ nginx, LiteLLM, PostgreSQL, Redis │
├─► /pibox-zai/ → pibox-zai │ proxq — everything else is opt-in │
├─► /pibox/ → pibox │ │
├─► /stealthy-auto-browse/ → HAProxy → [browser ×5]└───────────────────────────────────┘
├─► /storage/ → hybrids3
├─► /q/ → proxq → LiteLLM (async, returns job ID)
├─► /librechat/ → LibreChat (web UI, LIBRECHAT=1)
├─► /searxng/ → SearXNG (meta-search, SEARXNG=1)
├─► /telethon/ → Telethon (Telegram client, TELETHON=1)
├─► /predictalot/ → predictalot (time-series forecasting, CPU, PREDICTALOT=1)
├─► /predictalot-cuda/ → predictalot (time-series forecasting, NVIDIA GPU, PREDICTALOT_CUDA=1)
├─► /decidealot/ → decidealot (typed decisions REST + MCP, CPU, DECIDEALOT=1)
├─► /decidealot-cuda/ → decidealot (typed decisions REST + MCP, NVIDIA GPU, DECIDEALOT_CUDA=1)
├─► /audiolla/ → audiolla (audio-production REST + MCP, CPU, AUDIOLLA=1)
├─► /audiolla-cuda/ → audiolla (audio-production REST + MCP, NVIDIA GPU, AUDIOLLA_CUDA=1)
├─► /flickies/ → flickies (video toolkit REST + MCP, CPU, FLICKIES=1)
├─► /flickies-cuda/ → flickies (video toolkit REST + MCP, NVIDIA GPU, FLICKIES_CUDA=1)
├─► /mailbox/ → mailbox (IMAP+SMTP gateway, MAILBOX=1)
├─► /piston/ → piston (sandboxed multi-language code execution, PISTON=1)
└─► / → LiteLLM (sync)
├─ Groq (free: 30 RPM, 1K-14.4K RPD per model, GROQ=1)
├─ Cerebras (paid plan required, CEREBRAS=1)
├─ OpenRouter (free: 50 RPD $0 / 1K RPD with $10+, OPENROUTER=1)
├─ HuggingFace (free: $0.10/mo credits — eval only, HUGGINGFACE=1)
├─ Mistral (free "Experiment" tier — exact limits not published, MISTRAL=1)
├─ Cohere (trial: 1K calls/MONTH — runs out fast, COHERE=1)
├─ Ollama CPU (local, OLLAMA=1)
├─ Ollama CUDA (local, NVIDIA, OLLAMA_CUDA=1)
├─ Talkies CPU (local, unified ASR + Kokoro TTS, TALKIES=1)
├─ Talkies CUDA (local, NVIDIA, full ASR + Kokoro + Qwen3-TTS voice cloning, TALKIES_CUDA=1)
├─ sd.cpp CPU (local, image gen, SDCPP=1)
├─ sd.cpp CUDA (local, image gen, SDCPP_CUDA=1)
├─ vLLM CPU (local, text LLM + embeddings, VLLM=1)
├─ vLLM CUDA (local, NVIDIA, text LLM + embeddings, VLLM_CUDA=1)
├─ llama.cpp CPU (local, GGUF + vision-VLM incl. Surya OCR 2, LLAMACPP=1)
├─ llama.cpp CUDA (local, NVIDIA, Surya OCR 2 + Qwen3-8B embeddings, LLAMACPP_CUDA=1)
├─ claudebox (subscription, CLAUDEBOX=1)
├─ pibox-zai (subscription, PIBOX_ZAI=1)
├─ pibox (this stack's own models, PIBOX=1)
├─ Anthropic (pay-per-token, ANTHROPIC=1)
└─ OpenAI (pay-per-token, OPENAI=1)
MCP servers (all optional):
├─ stealthy_auto_browse — run_script: multi-step browser automation (BROWSER=1)
├─ hybrids3 — file upload, download, list, delete, presign (HYBRIDS3=1)
├─ claudebox — agentic Claude Code via OAuth or API key (CLAUDEBOX=1)
├─ pibox_zai — agentic pi-coding-agent via z.ai/GLM (PIBOX_ZAI=1)
├─ mcp_tools — generate_image + generate_tts + search_web + execute_code (auto-enabled when HuggingFace, OpenAI, talkies[-cuda], sd.cpp[-cuda], or SearXNG is active — PISTON=1 alone does NOT enable it; execute_code only appears once mcp_tools is already active for one of those other reasons)
├─ telethon — Telegram send/read/edit messages, dialogs, files, group management (TELETHON=1)
├─ predictalot — time-series forecasting via 5 foundation models × 6 type-routed endpoints + per-type ensemble (PREDICTALOT=1 and/or PREDICTALOT_CUDA=1)
├─ decidealot typed decisions with Laya, Von, CLM, and hosted Jev via system_one, system_one_batch, list_models, unload_models (DECIDEALOT=1 and/or DECIDEALOT_CUDA=1)
├─ audiolla — audio-production: stem separation, restoration, mastering, MIR, DSP, loudness, speech enhancement, diarization, MIDI compose + render, workflow presets + ad-hoc pipelines (AUDIOLLA=1 / AUDIOLLA_CUDA=1)
├─ flickies — video toolkit: lipsync (LatentSync 1.5 + Wav2Lip), face restore (GFPGAN), ffmpeg ops — trim/concat/transcode/scale/mux_audio/extract_audio/thumbnail_grid (FLICKIES=1 / FLICKIES_CUDA=1)
├─ mailbox — IMAP+SMTP gateway: inbox, list/search/send across N accounts (MAILBOX=1)
└─ piston (via mcp_tools) — execute_code: sandboxed multi-language code execution via nsjail (requires PISTON=1 AND mcp_tools already active per above — hosted by the mcp_tools aggregator, not a standalone MCP server)
Most persistent data lives under .data/ by default (bind mounts). Override the base with DATA_DIR or per-service with DATA_DIR_* env vars (e.g. DATA_DIR_OLLAMA=/mnt/nas/ollama), see .env.example for the full list. The default directory structure is tracked in git via .gitkeep files so the right directories exist on a fresh clone, contents are gitignored.
Default writable locations:
Mailbox also uses the mailbox-state named volume for its SQLite audit log, send limits, checkpoints and webhook delivery state. Back up that volume alongside the account config. Read the Mailbox migration notes and browser migration notes before upgrading older deployments.
| Path | Used by | Notes |
|---|---|---|
.data/claudebox/config/.always-skills/ |
claudebox | Drop <name>/SKILL.md files here — injected into every Claude session automatically |
.data/claudebox/workspace/ |
claudebox | Persistent task workspaces |
.data/pibox-zai/config/ |
pibox-zai | pi config dir (telegram.yml, cron history, etc.) |
.data/pibox-zai/workspace/ |
pibox-zai | Persistent workspace root (subdirs per task) |
.data/pibox/config/ |
pibox | pi config dir for the stack-backed agent |
.data/pibox/workspace/ |
pibox | Persistent workspace root (subdirs per task) |
.data/hybrids3/ |
hybrids3 | Object storage data |
.data/nginx/ |
nginx-auth-init | Generated htpasswd (from LITELLM_UI_BASIC_AUTH) |
.data/ollama/ |
ollama, ollama-cuda | Downloaded model weights (shared — CPU and CUDA instances read the same blobs) |
.data/talkies/ |
talkies, talkies-cuda | HuggingFace cache for all talkies models (Whisper × 3, Parakeet, Canary × 3, Kokoro). Shared between CPU and CUDA; CPU image loads a subset, CUDA loads the full set. |
.data/talkies-voices/ |
talkies-cuda | User-supplied Qwen3-TTS reference voices — drop <name>.wav (10-30s clean speech) and use as voice=<name> on /v1/audio/speech (nested paths supported) |
.data/sdcpp/models/ |
sdcpp, sdcpp-cuda | Downloaded stable-diffusion model weights (shared between CPU and CUDA) |
.data/librechat/ |
librechat, librechat-mongodb | Conversation data (MongoDB), file uploads |
.data/cloudflared/ |
cloudflared | Tunnel config and credentials (if using named tunnel) |
.data/tailscale/ |
tailscale | Tailscale node state (machine key, DERP info) — auto-created on first run |
.data/predictalot/models/ |
predictalot, predictalot-cuda | Downloaded HuggingFace snapshots for the 5 forecasters (~1.4GB total) |
.data/decidealot/models/ |
decidealot, decidealot-cuda | Enabled Laya, Von, and CLM model bundles, downloaded on first start. Must be owned by DECIDEALOT_UID/GID (default 1000) |
.data/audiolla/ |
audiolla, audiolla-cuda | Demucs weights (~6GB) + UVR models + torch hub + staged files (bind-mounted as /data; CPU and CUDA variants share the same cache) |
.data/flickies/ |
flickies, flickies-cuda | Model weights (~6GB total: S3FD + Wav2Lip ×2 + GFPGAN v1.4 + LatentSync 1.5) + staged file uploads (bind-mounted as /data; CPU and CUDA variants share the same cache) |
.data/vllm/models/<org>/<repo>/ |
vllm, vllm-cuda, vllm-pull | Flat HF-repo layout (no blobs/snapshots dedup) — vllm-pull populates via huggingface-cli download --local-dir. Shared by CPU and CUDA wrappers and by any other service that mounts the same dir. Default: Nomic embed v2 + Qwen3-0.6B. |
.data/mailbox/ |
mailbox | Recommended host path for the mailbox YAML config (config.yaml — gitignored, holds plaintext IMAP/SMTP creds) |
aigate MCP 질문
로컬 모델을 지원하나요?
네, 자체 CPU 또는 NVIDIA GPU에서 실행되는 Ollama, vLLM, llama.cpp와 같은 로컬 프로바이더를 지원합니다.
기존 AI 클라이언트와 함께 사용할 수 있나요?
네, OpenAI 호환 엔드포인트를 제공하므로 기존의 모든 클라이언트를 연결하여 사용할 수 있습니다.
브라우저 자동화가 탐지되나요?
아니요, 주요 봇 탐지기를 통과할 수 있도록 실제 OS 수준의 입력을 사용하는 스텔스 브라우저 클러스터를 사용합니다.