telegram vs Pushary: human-in-the-loop for AI agents
telegram is a plugin bundle for AI coding tools published by mjavadalavi. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Pushary: human-in-the-loop for AI agents is an MCP server published by Pushary. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-29. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  telegram |  Pushary: human-in-the-loop for AI agents |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: not stated Forks (GitHub): 0 Stars (GitHub): 0 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.5.2 Forks (GitHub): 1 Stars (GitHub): 1 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | telegram | Pushary: human-in-the-loop for AI agents |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 0 (worse) | 1 (better) |
| Forks (GitHub) (differs) | 0 (worse) | 1 (better) |
| Last release (differs) | Not published | 2026-10-25 |
| Where it runs (differs) | Installs as a plugin bundle | Remote server (pushary.com/api/mcp/mcp) |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Licence (differs) | Not stated | MIT |
| Repository (differs) | github.com/mjavadalavi/claude-plugins-official | github.com/pushary/pushary-skill |
| Changes in the last 7 days (differs) | 0 | 5 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 6 days ago |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
telegram
Connect a Telegram bot to your Claude Code session over MCP. The server logs in as a bot, forwards inbound messages into the session as <channel> notifications, and exposes tools to reply (with attachments up to 50MB), react with emoji, edit prior messages, and download inbound files. Built-in access control supports DM pairing flows and group/supergroup allowlists managed through the /telegram:access skill. Forum-topic routing via TELEGRAM_TOPIC_IDS lets a single bot fan out to multiple parallel Claude Code sessions, each bound to its own supergroup topic, so four sessions can work on four projects without racing for inbound messages. Proxy-aware transport (TELEGRAM_PROXY / HTTPS_PROXY) routes both text and multipart uploads through an HTTP proxy for use in regions where api.telegram.org is blocked or rate-limited.
Pushary: human-in-the-loop for AI agents
Human-in-the-loop for AI agents: ask a person and get approvals or answers by push notification.
How to run each
telegram As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install telegram@claude-communityPushary: human-in-the-loop for AI agents As a remote MCP server
claude mcp add --transport http pushary https://pushary.com/api/mcp/mcp --header "Authorization: Bearer <YOUR_TOKEN>"Requires: Authorization header
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only Pushary: human-in-the-loop for AI agents has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: telegram · What it can do: Pushary: human-in-the-loop for AI agents · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.