telegram-mcp
Local, read-only Telegram MCP server with public-channel discovery and folder-aware retrieval
What XERJ indexed
Snapshot
The whole repository at commit 2beac8bb73 (2026-10-22). main is 43 commits ahead.
Selected work
“improve retrieval reliability and compact MCP responses”. 52 files, 4,986 lines in tests, src/telegram_mcp, scripts.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-24. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
Example questions
- Where does telegram-mcp handle “improve retrieval reliability and compact MCP responses”?
- What does src/telegram_mcp do in telegram-mcp?
Inside the indexed corpus
- 119 files, 1013.4 KB in total, about 8.5 KB per file.
- The selected commit changed 52 of those files (43.7%).
- Languages by size: Python 100%, Makefile 0%.
- On GitHub since 2026-10-08, last push 2026-10-29, 53 commits on main.
- The pin is 43 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for egor-fedorov/telegram-mcp on 2026-10-31, and the LICENSE file at commit 2beac8bb73 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Egor Fyodorov (@egor-fedorov) has 1 selected repository on the hub.
Using XERJ with telegram-mcp
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Ask questions about a GitHub repo without cloning it
- Index a reference library for a coding agent
- ripgrep vs a code index for coding agents: 30 tasks
The prompt
Paste it into your AI agent. It clones egor-fedorov/telegram-mcp at the pinned commit and indexes it on your machine.
Search the GitHub repository egor-fedorov/telegram-mcp with XERJ (https://hub.xerj.org/corpus/egor-fedorov--telegram-mcp). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/egor-fedorov/telegram-mcp telegram-mcp && git -C telegram-mcp checkout 2beac8bb7336fbaf18df22382cf4bd1ed2b661ad 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./telegram-mcp --url http://127.0.0.1:9200 --prefix telegram-mcp --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: MIT. Keep the copyright notice and credit the authors.
Related
Egor FyodorovAI, prompts and agents corpora
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.