telegram-messaging
Guide for using Telegram MCP tools across both servers — telegram-all (personal account, full access) and telegram-bot (Bot API). Covers reading chats, sending messages, search, history, group management, and how to pick the right server. Use when the user asks about Telegram messages, chats, contacts, or bot operations.
What this skill does
# Telegram Messaging
This plugin ships **two MCP servers** — pick the right one before invoking any tool.
## Server selection — always do this first
| User's intent | Server | Why |
|---------------|--------|-----|
| "Read my chat with Alice" / "what did Bob say" / "search my messages" / "send a message as me" | **`telegram-all`** | Operates as the user's personal Telegram account. Sees all private chats, full history, can act as the user. |
| "Send a notification from the bot" / "respond to bot updates" / "moderate the group with the bot" | **`telegram-bot`** | Operates as a Telegram bot. Only sees chats the bot is in; no access to user's private chats. |
| User says "Telegram" without context | Default to **`telegram-all`** | Personal-account use is the more common path; bot use is usually explicit. |
**If both servers are configured and the request is ambiguous, ask the user which one.** Don't silently pick.
If a tool call fails with "server not connected" or similar, the corresponding server is likely disabled via the user's `disabledMcpjsonServers` setting — explain this and offer to fall back to the other server if it makes sense.
---
## Path A: `telegram-all` (Personal Account, TDLib)
Tool names: `mcp__plugin_che-telegram-mcp_telegram-all__<tool>`
### Auth — one-time setup
Auth state persists in `~/Library/Application Support/che-telegram-all-mcp/tdlib/`.
**Always check `auth_status` before doing real work.** It returns `{state, next_step, last_error}`.
- If `state == "ready"`, skip auth.
- Otherwise, prefer `auth_run` (v0.5.0+) which drives the state machine in one tool:
```
auth_run → fires auto-set params (if env present)
auth_run → fires auto-send phone (if env present)
auth_run(code: "12345") → caller MUST supply SMS code (never auto-fired)
auth_run → fires auto-send 2FA password (if env present)
auth_run → state == "ready"
```
- Legacy per-step tools (`auth_set_parameters`, `auth_send_phone`, `auth_send_code`, `auth_send_password`) are still available as escape hatches.
`auth_status.next_step` tells you exactly which arg the next call needs (e.g., `{tool: "auth_run", required_args: ["code"], hint: "..."}`); follow it.
### Tool categories
#### Discovery (start here)
| Tool | Purpose |
|------|---------|
| `get_chats` | List recent conversations (`limit` param) |
| `search_chats` | Find chat by name |
| `get_chat` | Get details of a specific chat |
| `get_contacts` | List saved contacts |
| `get_me` | Your own profile |
| `get_user` | Look up another user by ID |
#### Reading messages
| Tool | Purpose |
|------|---------|
| `get_chat_history` | Read history (`chat_id`, `limit`, `from_message_id`, optional `since_date` / `until_date` / `max_messages`) |
| `search_messages` | Search within a chat by keyword |
| `dump_chat_to_markdown` | One-shot export with date range / cap |
#### Sending / modifying messages
| Tool | Purpose |
|------|---------|
| `send_message` | Send text to a chat |
| `edit_message` | Edit your own sent message |
| `forward_messages` | Forward between chats |
| `delete_messages` | Delete messages |
| `mark_as_read` | Mark messages read |
> ⚠️ **CRITICAL**: Always confirm with the user before `send_message`, `edit_message`, `delete_messages`, or `forward_messages`. These actions show up in real conversations and cannot always be undone.
#### Group management
| Tool | Purpose |
|------|---------|
| `get_chat_members` | List group members |
| `create_group` | Create a new group |
| `add_chat_member` | Add member to group |
| `pin_message` / `unpin_message` | Pin/unpin |
| `set_chat_title` / `set_chat_description` | Edit group info |
### Common workflows (`telegram-all`)
```
Read recent messages:
1. get_chats(limit: 10) → find the chat
2. get_chat_history(chat_id, limit: 20) → read messages
Search:
1. search_chats(query: "name") → find the chat
2. search_messages(chat_id, query: "keyword") → find messages
Send a message:
1. search_chats(query: "recipient") → find chat_id
2. CONFIRM with user → show recipient + message preview
3. send_message(chat_id, text) → send
```
---
## Path B: `telegram-bot` (Bot API)
Tool names: `mcp__plugin_che-telegram-mcp_telegram-bot__<tool>`
### What the bot can / cannot do
- ✅ Send/receive messages in chats the bot has been added to
- ✅ Manage chats it's an admin of (pin, ban, restrict, set title)
- ✅ Send media (photo, video, document, audio, sticker, location, poll)
- ❌ Read the user's private chats (Bot API has no access)
- ❌ Search across history (Bot API only fetches via 24h `get_updates` window or webhooks)
### Tool categories
#### Identity & updates
| Tool | Purpose |
|------|---------|
| `get_me` | Bot's profile |
| `get_updates` | Poll for new messages / events (24h window) |
#### Send messages & media
| Tool | Purpose |
|------|---------|
| `send_message` | Send text |
| `send_photo` / `send_video` / `send_audio` / `send_document` / `send_sticker` / `send_location` / `send_poll` | Send specific media types |
| `forward_message` / `copy_message` | Forward / copy between chats |
| `edit_message_text` | Edit a sent message |
| `delete_message` | Delete a message |
#### Chat info
| Tool | Purpose |
|------|---------|
| `get_chat` | Chat details |
| `get_chat_administrators` | List admins |
| `get_chat_member_count` | Member count |
| `get_chat_member` | One member's role |
#### Admin actions (bot must be admin)
| Tool | Purpose |
|------|---------|
| `pin_chat_message` / `unpin_chat_message` / `unpin_all_chat_messages` | Pin/unpin |
| `ban_chat_member` / `unban_chat_member` | Ban control |
| `restrict_chat_member` / `promote_chat_member` | Permissions |
| `set_chat_title` / `set_chat_description` | Edit chat info |
| `leave_chat` | Bot leaves the chat |
#### Bot commands
| Tool | Purpose |
|------|---------|
| `set_my_commands` / `get_my_commands` / `delete_my_commands` | Manage `/command` list shown in Telegram clients |
> ⚠️ Same confirmation rule as Path A — always confirm with the user before any send / delete / ban / restrict / promote action.
---
## Security notes
- `telegram-all` operates as the user's **personal account**. It can read all private chats — handle content with care; never log or store message content beyond the current conversation.
- `telegram-bot` operates as a public bot — its actions are visible to everyone in the chat. Treat bot tokens as secrets (they're stored in macOS Keychain).
- Always get explicit user confirmation before any send / delete / forward / ban action. Don't infer consent from earlier turns of the conversation.
## When tools fail
| Error pattern | Likely cause | Fix |
|---------------|--------------|-----|
| `Not authenticated` (telegram-all) | Auth not completed | Walk through `auth_run` flow above |
| `FLOOD_WAIT_X` | Rate limited by Telegram | Surface the wait time to the user; retry after X seconds |
| `Server not connected` | Server disabled in settings, or binary missing | Check `disabledMcpjsonServers` and the SessionStart hook output |
| Bot 401 / `Unauthorized` | Bot token wrong or revoked | Re-issue token via @BotFather and update Keychain |
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.