tggroupMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API key for embeddings (alternative to TELEGRAM_EMBEDDINGS_API_KEY). | |
| TELEGRAM_SESSION | Yes | The Telegram session string generated by the setup script. | |
| TELEGRAM_SEND_ENABLED | No | Set to 'false' to disable sending messages (dry run mode). | true |
| TELEGRAM_EMBEDDINGS_API_KEY | No | API key for embeddings (alternative to OPENAI_API_KEY). |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_configB | Return redacted Telegram Parilka MCP configuration and safety state. |
| resolve_chatC | Resolve the configured or provided Telegram chat and cache its input peer. |
| get_chat_infoC | Resolve chat info plus local cache statistics. |
| sync_historyB | Sync Telegram history into local SQLite cache. Use this manually; normally run sync-daemon in the background. |
| read_historyC | Read messages from the local SQLite cache. |
| search_messagesB | Search cached Telegram messages with keyword FTS, vector cosine search, and hybrid candidates. |
| semantic_search_messagesB | Vector/cosine search over indexed cached Telegram message chunks. |
| index_embeddingsB | Index cached Telegram messages into vector chunks for semantic search. |
| get_thread_contextC | Return cached messages around a message ID. |
| preview_messageA | Validate a Telegram send without sending anything. |
| send_messageB | Send or dry-run a Telegram message with allowlist, dedupe, and throttling. |
| reply_to_messageC | Convenience wrapper around send_message with required reply_to_message_id. |
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 12 tools
Tools are largely distinct, but 'search_messages' and 'semantic_search_messages' could cause confusion if descriptions are not read carefully. Otherwise, each tool targets a different operation like resolving, reading, syncing, sending, or searching.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_chat_info, sync_history, send_message). No mixed conventions or vague verbs.
12 tools cover the main needs of a Telegram chat assistant: chat resolution, history management, search, indexing, messaging, and configuration. The number feels well-scoped for the domain.
Core operations like reading, searching, sending, and previewing messages are present. Missing are message editing/deletion or real-time updates, but these are reasonable omissions for a read-heavy chat assistant.