Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
Nothing to run from here
Telegram Dev is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
10
tools declared
local
runs on your machine
—
downloads a day
What it does
Current official Telegram and TON docs: Bot API, Mini Apps, MTProto, TDLib, TON Connect, Tolk
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user telegram-dev-mcp '--' uvx telegram-dev serve
# 2 — ask your agent for something these tools do
# search_telegram_docs, get_telegram_document, get_telegram_corpus_status and 7 more
Telegram Dev costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
KAAll 1 server
kay0k11 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Telegram Dev as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user telegram-dev-mcp '--' uvx telegram-dev serveReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take TELEGRAM_KNOWLEDGE_DB (Path to the SQLite documentation cache (default: the user cache directory)), TELEGRAM_DOC_AUTO_SYNC (Set to 0 to disable the background refresh cycle) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Find the official documentation sections that answer a Telegram or TON development question.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Exact API names or short English keywords work best, e.g. 'InlineKeyboardButton style', 'sendVideoNote', 'ton_proof', 'jetton transfer', 'aiogram Router callback_query'. Common Russian feature words ( |
| area | no | Limit results to one documentation area; empty searches all areas. Core Telegram docs rank above library docs unless the query names a library. | |
| limit | integer | no | Maximum number of matching sections to return. |
Read the text of an official Telegram, TON or bot-library documentation page, one window at a time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Official page URL from search results or list_telegram_sources, e.g. https://core.telegram.org/bots/api or https://docs.ton.org/applications/ton-connect/overview. Pages outside the official sources ar |
| offset | integer | no | Character offset to start from; use a search result's document_offset or the previous next_offset. |
| length | integer | no | Number of characters to return. |
| refresh | boolean | no | Force a live check of the source even if the cached copy is fresh. |
Report how complete and how current the local documentation cache is, as totals.
Takes no parameters.
List the revisions of one documentation page that this installation has observed, newest first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Official page URL, the same form accepted by get_telegram_document. |
List the official entry points this server crawls, each with its documentation area.
Takes no parameters.
List the documentation pages already stored in the local cache, sorted by URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| area | no | Only pages from this documentation area; empty lists all areas. | |
| offset | integer | no | Number of pages to skip, for paging through long lists; use the previous next_offset. |
| limit | integer | no | Maximum number of pages to return. |
Return the current definition of one Bot API method or type as structured data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Exact Bot API method or type name, e.g. 'sendMessage', 'InlineKeyboardButton', 'ReplyParameters'. Case-insensitive; close matches are suggested. |
Check a Bot API request against the current official schema before running or shipping code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| method | string | yes | Bot API method name, e.g. 'sendMessage'. |
| params | object | yes | The request parameters exactly as your code sends them, as a JSON object. Nested objects such as reply_markup may be objects or JSON strings. |
List official Bot API changelog entries as structured releases: version, date, link and the individual changes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since_version | string | no | Only releases newer than this Bot API version, e.g. '9.0'. Empty returns the latest releases. |
| name | string | no | Only changes that mention this method, type, field or parameter, e.g. 'InlineKeyboardButton' or 'reply_parameters'. |
| limit | integer | no | Maximum number of releases when since_version is empty. |
Check every Bot API call in a Python bot project (aiogram, python-telegram-bot, pyTelegramBotAPI, raw HTTP requests) against the current official schema in one run.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path to the bot project directory or a single Python file on this machine. |
| exclude | array | no | Glob patterns relative to path to skip, e.g. ['tests/*', 'migrations/*']. |
| max_findings | integer | no | Maximum number of findings to return; totals always count everything. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Telegram Dev or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.9.0 · scanned 11 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings4 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest8a40b59afa9468bb5e12cb96e6e42bee89ff214302741978d424ade423e54cb9
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (10 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 10 recovered tools are registered only when transport == "stdio" holds (telegram_knowledge.py:998) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 9.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
9 tools are registered unconditionally · 1 more only when transport == "stdio" holds (telegram_knowledge.py:998) — typically when a key or option is configured. All 10 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_telegram_docs | untrusted-input | untrusted-input: keyword "fetch" |
| get_telegram_document | no tags | |
| get_bot_api_definition | no tags | |
| check_bot_api_call | no tags | |
| list_bot_api_changes | no tags | |
| get_telegram_corpus_status | untrusted-input | untrusted-input: keyword "crawl" |
| list_telegram_document_revisions | no tags | |
| list_telegram_sources | no tags | |
| list_telegram_cached_pages | no tags | |
| check_telegram_project conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest8a40b59afa9468bb
Scanned2026-11-11
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.9.0. Pin a release below and the command asks for exactly that one.
0.9.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Telegram Dev can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.