OpenClaw Tools Collection MCP
A set of MCP servers and skills for the OpenClaw assistant: YandexGPT, OCR, speech synthesis and image generation
- 2 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Five Node.js MCP servers call YandexGPT, Vision, SpeechKit and Yandex Cloud search
- Calls are billed, keys sit in the mcporter config
Install
- Works in
- Services
Manual install
mcporter config add yandexgpt --command "node /path/to/yandexgpt-server.js" --env YANDEX_FOLDER_ID=your_folder_id --env YANDEX_API_KEY=your_api_keyThe README's command for registering the YandexGPT server via mcporter; the same pattern applies to vision and speechkit.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Five Node.js MCP servers call YandexGPT, Vision, SpeechKit and Yandex Cloud search
- Calls are billed, keys sit in the mcporter config
This is third-party code. Review the repository files before installing.
What it does
A collection of five separate single-file Node.js MCP servers and three skills, built specifically for the OpenClaw assistant. yandexgpt-server gives access to the YandexGPT API, yandex-vision-server to image text recognition, yandex-speechkit-server to SpeechKit speech synthesis and recognition, while yandex-search-server and fusionbrain-image-server are marked less stable in the README. The skills duplicate part of this as declarative yandexgpt and yandex-tools skills, plus a separate heygen-video skill for avatar video.
Who it is for. For OpenClaw assistant users who want quick access to several Yandex Cloud services from one collection.
Good fit when
- You use OpenClaw specifically and want a ready Yandex tool set for it
- You need text generation, OCR and speech synthesis from one source without assembling each server yourself
Not a fit when
- You use a different MCP client: the servers are not published to npm and need a manual node <file>.js launch
- You need Yandex search or image generation: they're marked unstable in the README
Example request
Recognize the text on this image via yandex_vision_ocrMCP
- Transport
- stdio
- Authentication
- API key
Environment variables
YANDEX_FOLDER_IDrequired- Yandex Cloud folder ID.
YANDEX_API_KEYrequired, secret- Yandex Cloud service account API key.
Limitations
Needs mcporter or manual command setup pointing node at the server file's path; there is no published npm package. The yandex-search-server and fusionbrain-image-server servers are flagged by the author as less reliable than the other three. No tests or CI in the repository.
How to disable. Remove the corresponding entry from your mcporter or OpenClaw client config.
FAQ
Does it work without OpenClaw?
The servers are ordinary Node.js MCP servers and connect to any MCP client, but the collection is explicitly built and documented for OpenClaw.
Which servers are stable?
YandexGPT, Vision OCR and SpeechKit are marked ready; search and image generation carry a stability warning.
How is OpenClaw Tools Collection different from general MCP servers for Yandex services?
A collection of five single-file Node.js MCP servers and three skills built for the OpenClaw assistant: yandexgpt-server for the YandexGPT API, yandex-vision-server for text recognition, plus speech synthesis and image generation.
Does the collection work without OpenClaw and which servers are stable?
The servers are single-file and can connect to other MCP clients, but they were built for OpenClaw. Install through mcporter: mcporter config add yandexgpt --command node /path/to/yandexgpt-server.js. See the README for each server's stability status.
Discussion
No questions or reviews yet.
Related
All YandexGPT toolsFour single-file MCP servers for YandexGPT, text recognition, SpeechKit speech synthesis and Yandex search
MCP Gateway for GigaChat and YandexGPT
MCP Gateway
An MCP gateway to GigaChat and YandexGPT with automatic failover between them and 152-FZ personal-data anonymization
A skill and scripts for transcribing audio through Yandex SpeechKit: audio preparation, Object Storage upload and asynchronous v3 recognition
A Home Assistant integration that puts GigaChat, YandexGPT or another LLM behind your smart-home voice assistant
Yandex AI Studio skill for Laravel
yandex-ai-laravel skill
A Claude Code skill for the yandex-ai-laravel SDK: Responses API, Vision OCR across 12 models, embeddings and known differences from OpenAI
Monorepo of Yandex MCP servers: Direct, Metrica, Webmaster, Wordstat, Tracker, 360, Maps, SpeechKit, YandexGPT and AppMetrica
README in short
The Russian README gives a table of MCP servers with readiness status, a table of skills and guides, mcporter install commands with example environment variables, and a section on getting Yandex Cloud and FusionBrain keys.