Source · repo

XERJ: local search engine and MCP server for agents

Author
xerj-org
Published
16 November 2026
Added
16 November 2026
Original
https://github.com/xerj-org/xerj

Summary

XERJ is a single Rust binary that indexes code, docs, logs, CSV/JSONL, and PDFs on your machine and serves keyword (BM25), vector, and hybrid search through an Elasticsearch-compatible API and a stdio MCP server. It is Apache-2.0 for the engine, with about 19K stars and over 4,000 commits (read 2026-11-16; latest release candidate v1.0.0-rc.101). The date above is the read date; the repo is not new but was rising in the GitHub trends report.

Key points

  • Install: curl -fsSL https://xerj.org/get | sh (read the script first), a Nix flake, or cargo build --release -p xerj-server in engine/.
  • Run and index: xerj --insecure --data-dir ~/xerj-data & starts a local node (--insecure turns off TLS and API keys: single-user, localhost only), then xerj autoindex ~/my-project.
  • Use from Claude Code: claude mcp add xerj -- /absolute/path/to/xerj mcp (or an mcpServers entry in .mcp.json); set XERJ_URL if the node is not on http://localhost:9200, and pass the key from admin.key via XERJ_AUTH when auth is on. xerj mcp only proxies to a running node. Tools include xerj_search and xerj_def.
  • Good for: giving an agent fast search over a large repo plus its logs and docs without reading whole files into context.
  • Caveats: the token-saving and accuracy figures are the project's own and some benchmark scripts are unpublished; the optional XERJ Query-1 answer model shipped in release binaries since rc.101 is proprietary; the README is heavily promotional.

Why it matters

A self-hosted alternative to cloud doc and code search MCP servers: one binary, local data, and a familiar Elasticsearch API for other tools.