offload-mcp-server

Let your main coding agent delegate heavy reading to a second agent, and read back only the answer

A new way for AI to search for data
View on GitHub
23GitHub stars

TypeScript, JavaScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 8aaacce8d5 (2026-11-08).

Selected work

Lục Anh Tài
@tailucanh

“stream mode, follow-ups, coverage and report hygiene (v0.3.0)”. 15 files, 945 lines in src, scripts, the project root.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-11-08. 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

ai-agentsantigravityclaude-codedeveloper-toolsgeminimcpmcp-servermodel-context-protocol

Example questions

The prompt

Paste it into your AI agent. It clones tailucanh/offload-mcp-server at the pinned commit and indexes it on your machine.

Search the GitHub repository tailucanh/offload-mcp-server with XERJ (https://hub.xerj.org/corpus/tailucanh--offload-mcp-server).
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/tailucanh/offload-mcp-server offload-mcp-server && git -C offload-mcp-server checkout 8aaacce8d51336f8071bac3d1ca61b897b48d010
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./offload-mcp-server --url http://127.0.0.1:9200 --prefix offload-mcp-server --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

Selected work and consent: the XERJ registry.