Skip to main content
Glama
Telegram Bot API Docs MCP

Telegram Bot API Docs MCP

by yoxcito

Telegram Bot API Docs MCP

It gives AI clients access to the current Telegram Bot API documentation. The server scrapes the official docs on startup, validates the method/type graph, and serves the result through MCP tools and JSON resources.

Run

Run the published package over stdio, which is the usual transport for local AI client bindings:

uvx telegram-bot-api-docs-mcp

Or run as an HTTP MCP server:

uvx telegram-bot-api-docs-mcp --transport http --host 127.0.0.1 --port 8080

Startup requires internet access because the server fetches https://core.telegram.org/bots/api every time it starts.

For local development from a checkout, use uv run python main.py with the same arguments.

Related MCP server: Gemini Docs MCP Server

Codex

This repo includes a project-scoped Codex config at .codex/config.toml:

[mcp_servers.telegram-bot-api-docs]
command = "uvx"
args = ["telegram-bot-api-docs-mcp"]

Start a new Codex session from this trusted repo and run /mcp to confirm that telegram-bot-api-docs is connected.

Tools

  • get_bot_api_overview: version, release date, changelog URL, and counts.

  • list_methods / list_types: paginated method/type discovery with optional search.

  • get_method / get_type: full docs for a method or type.

  • get_field: docs for a specific method parameter or type field.

  • search_bot_api: search names, descriptions, fields, return types, and relationships.

  • get_related_types: subtype and usage graph for a type.

  • dump_bot_api_spec: raw full spec or a single section.

Resources

  • telegram-bot-api://overview

  • telegram-bot-api://methods

  • telegram-bot-api://types

  • telegram-bot-api://spec

Scraper

scrape.py contains the parser and schema validation used by the MCP server.

Thanks to PaulSonOfLars for such wonderful project

Example

Here is an example bot created completely using codex

Made by Mukund

Available Tools

9 tools
dump_bot_api_specA

Return the raw scraped Bot API documentation spec, optionally restricted to one section.

Inputs: section. Returns: object

get_bot_api_overviewA

Return Bot API version metadata and counts for the loaded documentation.

Inputs: no named parameters. Returns: object

get_fieldC

Return documentation for a method parameter or type field.

Inputs: field_name (required), owner_name (required), section. Returns: object

get_methodC

Return full documentation for a Telegram Bot API method.

Inputs: name (required), include_return_types. Returns: object

get_typeB

Return full documentation for a Telegram Bot API type.

Inputs: name (required), include_related_methods. Returns: object

list_methodsB

List Telegram Bot API methods, optionally filtered by a search query.

Inputs: limit, query, offset. Returns: object

list_typesC

List Telegram Bot API types, optionally filtered by a search query.

Inputs: limit, query, offset. Returns: object

search_bot_apiC

Search method/type names, descriptions, fields, return types, and relationships.

Inputs: query (required), limit, section. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool addresses a distinct aspect of the Telegram Bot API documentation: raw spec retrieval, overview metadata, individual methods/types, fields, relationships, listings, and search. There is no functional overlap.

    Naming Consistency5/5

    All tool names follow a clear verb_noun pattern in snake_case (e.g., get_method, list_types, search_bot_api). The verbs (dump, get, list, search) and nouns are consistent and predictable.

    Tool Count5/5

    With 9 tools, the server covers the core operations needed to explore Telegram Bot API documentation without being sparse or overwhelming. Each tool serves a clear purpose.

    Completeness5/5

    The tool set fully covers the API documentation domain: listing, fetching, searching, relationship navigation, raw spec access, and metadata. There are no obvious gaps for the intended use case.

    Related MCP Connectors

    Related MCP Servers