Claude — web & desktop
Settings → Connectors → Add custom connector → paste the URL → Connect. Sign in with Telegram and confirm the team.
Model Context Protocol
Plan, publish and measure the channels you own — from inside your assistant's chat window. One hosted connector, OAuth or a token, 25 tools, works on the free plan.
Connector URL — the same for every client
https://awraiter.ai/mcp
Streamable HTTP. OAuth 2.0 with a consent screen, or a personal access token you mint yourself in the panel. 120 requests per 60 seconds per token.
01 — Connect
In your client, add a custom MCP server and paste https://awraiter.ai/mcp. Transport is Streamable HTTP.
OAuth opens an AwrAiter page: sign in and confirm which team the assistant may act for. Clients without OAuth take a token from awraiter.ai/mcp-connect as Authorization: Bearer ….
The tools appear in the client's tool list. “Show last week's statistics for my channel.”
02 — Clients
Settings → Connectors → Add custom connector → paste the URL → Connect. Sign in with Telegram and confirm the team.
claude mcp add --transport http awraiter https://awraiter.ai/mcp — it walks you through OAuth on first use.
In the browser, Settings → Connectors offers OAuth. The desktop/Codex form has no OAuth: set type Streamable HTTP and add the header Authorization: Bearer pat_…. Leave the “token environment variable” fields empty — a token typed there leaves the connector with no tools.
Any MCP-capable client works against the same URL with a Bearer token in the headers.
03 — Tools
Read tools work with any scope. ✍️ marks tools that change something: they need OAuth or a full-scope token. Only deep_analyze spends AI credits — everything else is free on every plan.
list_teams | Your teams, with the active one marked. |
switch_team | Switch the active team. |
list_channels | Channels of the active team. |
get_channel | One channel's profile — name, language, description. |
get_channel_stats | The dashboard: subscribers, reach, ER, dynamics over 1–90 days. |
get_channel_insights | What works for this audience: top and flop posts scored against the 30-day median, plus statistically-backed patterns — best day, posting window, length, question at the end — once the channel has 20+ scored posts. |
deep_analyze | Deep AI analysis of one channel, or a comparison of several. Runs on our servers and spends AI credits. |
get_recent_posts | The channel's latest published posts. |
search_channel_content | Semantic search across the channel's own past posts and sources. |
draft_from_sources | The freshest scraped sources not yet used in a post — raw material to draft from. |
search_sources | Search the sources bound to the channel. |
create_post_from_text | Save a finished post — your assistant's text, plus images and video by URL — as a draft. ✍️ |
preview_post | Exactly what will be sent: title, body, media. |
score_post | Score a draft against the channel's own history before it goes out. |
check_uniqueness | Near-duplicate check against the team's posts and sources. |
schedule_post | Publish a draft now or at a chosen time. ✍️ |
cancel_scheduled_post | Roll a scheduled post back. ✍️ |
get_content_plan | The channel's plan and its slots. |
find_free_slot | The earliest free slot in the plan. |
create_content_plan | Create a plan for a channel. ✍️ |
get_playbook | A step-by-step operator playbook: analyze, create_plan, fill, improve, rewrite. |
get_channel_memory | The channel's brand brief and banlist. |
set_brand_brief | Set free-form brand and tone guidance the AI follows. ✍️ |
add_banlist_entry | Add a forbidden word to the channel's list. ✍️ |
remove_banlist_entry | Remove a word from the channel's list. ✍️ |
04 — Example prompts
Paste one into your assistant once the connector is on.
Compare my three channels over the last 30 days and tell me which content works best where.
Take the freshest unused source for @mychannel, write a post in the channel's tone, score it, and if the score is good — schedule it for the next free slot.
What are the statistically best day and time to post on my channel?
Build a content plan for next week: 5 posts, alternating news and evergreen topics.
Check this draft against my last 100 posts for near-duplicates, then preview exactly what would be sent.
05 — How it differs
Most Telegram MCP servers hand the assistant your personal account over MTProto so it can read your chats. This one never touches your account or your correspondence. It works on the channels where you are an administrator, and on what happens to them: the plan, the publishing, the numbers.
| What differs | Userbot MCP servers | AwrAiter |
|---|---|---|
| What it connects | Your personal Telegram account | The channels you administer |
| What it sees | Your chats and correspondence | Your channels' posts, plans and statistics |
| Credentials | Your phone number and a session file | OAuth sign-in or a revocable token |
| Publishing | Messages from you, as you | Scheduled posts into the channel, with preview and scoring |
| Analytics | None | Growth, ER, ERR, per-post stats, channel comparison |
| Hosting | Usually self-hosted | Hosted — nothing to run |
06 — FAQ
No. You sign in with Telegram on our page, or paste a token you minted in the panel. There is no phone number, no code, no session file — and nothing that would let an assistant read your personal chats.
Only if you let it. A read-only token can read analytics and content and cannot publish, edit or cancel anything; publishing needs OAuth or a full-scope token. Every write goes through the same permission checks as the panel, including per-channel access for team members.
Yes. The connector is included on every plan, including the free one — one channel, free forever. Only deep_analyze spends AI credits.
Those give the assistant your personal account over MTProto. AwrAiter gives it the channels you administer: content plans, scheduled publishing, ER/ERR analytics and post-level insights. Different job, different data, different risk.
Anything that speaks MCP over Streamable HTTP: Claude web and desktop, Claude Code, ChatGPT and Codex, Cursor, Gemini CLI, Qwen Code and others. OAuth where the client offers it, a Bearer token where it does not.
120 requests per 60 seconds per token. Agents running in a tight loop should back off.
One channel is free forever, no card. The connector is included.