dual-plane telegram mcp: read-only analytics + guarded actions with anti-spam and block-risk controls
This repository also configures its own agents. See what tg-mcp-guarded tells them →
Skill Claude CodeCodex
use this skill for assistant-authored messages to other people from an owner's telegram account. it does not itself authorize delivery or apply the owner's voice to unrelated agent work.
Skill Claude CodeCodex
execute an authorized telegram send or other write through tg-mcp actions with identity checks, exact scope, approval gates and read-back verification.
Skill Claude CodeCodex
use the private operator profile in your workspace for the expected account username and numeric user id, read/actions server aliases, repository path and recipient scope. use the installed tool schemas; names below are tg-mcp tool names, not client aliases. when implementation details matter, resolve documentation…
Skill Claude CodeCodex
read the private operator profile in your workspace for the expected account, read server alias, private artifact location and existing local transcription backend. tg-mcp retrieves media; transcription is a separate local capability. do not assume a particular wrapper, speech model, cloud service or text-to-speech…
Skill Claude CodeCodex
Read and analyze GCONF personal sales conversations through Dima's tg-mcp in gconf-core; perform sales actions only when explicitly requested. Does not apply to unrelated Telegram conversations, other accounts, support or other projects.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: