tg-recall-mcp
Related Servers
Alternatives to tg-recall-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceRead-only MCP server that exposes retrieval tools over a Telegram chat archive, including archive overview, full-text search with Russian morphology, aggregates, message retrieval, and local context. It lets LLM agents answer questions from chat history without syncing Telegram, downloading files, or modifying the index.-
- AlicenseAqualityDmaintenanceA local MCP server that enables full-text and semantic search over your own Telegram chats using your personal MTProto login, with everything running locally.7MIT
- AlicenseNot gradedqualityDmaintenancePrivacy-first Telegram MCP server enabling maintainers to triage chats, inspect context, search messages, draft replies, and send authorized messages locally without a cloud relay.193 npm1MIT
- AlicenseAqualityAmaintenanceMCP server that exposes any Telegram-Archive instance to LLMs, enabling message search, chat browsing, and access to archived Telegram history.9247 npm5GPL 3.0
- AlicenseNot gradedqualityCmaintenanceLocal-first MCP server for indexing and searching research materials (papers, notes, logs, READMEs) using SQLite FTS, with tools for memory management and evidence retrieval.MIT
- FlicenseNot gradedqualityBmaintenanceAn MCP server that connects to a Telegram group chat, persists messages to a local SQLite database, and exposes tools to search, retrieve, and send messages via SSE.-
TDQS
Scored across 5 tools
Each tool has a largely distinct purpose: search queries messages, read retrieves messages in order, stats aggregates counts, export writes to a file, and chats lists available chats. The only mild overlap is that search and read both return message content, and export can cover similar bulk-retrieval ground as read, but the descriptions make the intended use cases clear.
All five names are single lowercase words with no separators, which is a consistent and predictable style. However, they mix verbs (search, read, export) and nouns (stats, chats) rather than following a single verb_noun or uniform category convention, which is a minor deviation.
Five tools is well within the appropriate 3-15 range for a Telegram message-recall server. Each tool maps to a distinct capability (query, ordered read, aggregation, bulk export, chat listing) and none feels redundant.
The read-only recall domain is well covered: search for targeted retrieval, read for chronological access, stats for aggregation, export for bulk analysis, and chats for scope discovery. A minor gap is the lack of an explicit sync/refresh or per-message lookup tool, though chats' sync age and read's since/until partially mitigate this.