@theyahia/gigachat-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GIGACHAT_AUTH_KEY | Yes | Base64-encoded client_id:client_secret from Sber developers portal. Required for authentication. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chatB | Генерация текста через GigaChat. Поддерживает диалог с системным промптом. |
| list_modelsA | Список доступных моделей GigaChat. |
| embed_textB | Получение векторных представлений (эмбеддингов) текстов через GigaChat. |
| get_token_countC | Подсчёт токенов для массива текстов. |
| generate_imageB | Генерация изображения через GigaChat (описание в тексте сообщения). |
| get_balanceB | Проверка остатка токенов/квоты GigaChat. |
| list_assistantsB | Список доступных ассистентов GigaChat. |
| file_uploadB | Загрузка файла в GigaChat для мультимодальной обработки. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct GigaChat capability: file upload, token counting, image generation, balance check, assistant listing, embedding, chat, and model listing. The purposes are clearly separated with no overlapping operations, making it easy for an agent to select the right tool.
All tool names follow a consistent verb_noun pattern, such as 'get_token_count', 'generate_image', 'list_assistants', and 'embed_text'. Even the single-word 'chat' fits the pattern as a clear action. There are no style inconsistencies or mixed conventions.
With 8 tools, the set is well-scoped for a comprehensive GigaChat client. Each tool covers a core API operation without redundancy or bloat, staying well within the ideal range for clarity and maintainability.
The toolset covers all major GigaChat features: text generation, embeddings, image generation, token counting, balance, model and assistant listing, and file upload. Minor gaps exist, such as missing assistant creation or management operations, but agents can still accomplish most workflows without dead ends.