---
slug: "xerj"
name: "XERJ"
effect: "Local search engine and MCP server that indexes code, docs, logs and CSV for agents to query"
category: "mcp-server"
tier: "rising"
url: "https://xerj.org"
github: "xerj-org/xerj"
pricing: "open-source"
license: "Apache-2.0"
tags: ["mcp", "code-search", "full-text-search", "vector-search", "agent-memory", "local-first", "rust"]
platforms: ["claude-code", "cursor", "any-mcp-client", "macos", "linux", "windows"]
install_kind: "cli"
date_added: "2026-10-20"
rank: 8
rising_score: 63
stars: 10872
star_velocity: 96.8
velocity_basis: "since creation"
created_at: "2026-06-30T04:32:45Z"
pushed_at: "2026-10-20T11:39:45Z"
signals_status: "ok"
signals_fetched_at: "2026-10-20T11:40:36.830Z"
page: "https://agenttooldrop.com/tools/xerj"
---

# XERJ

Local search engine and MCP server that indexes code, docs, logs and CSV for agents to query

Category: MCP servers. Tier: new and rising, rank 8 by new and rising score (63 of 100). Pricing: Open source. License: Apache-2.0.

Platforms: claude-code, cursor, any-mcp-client, macos, linux, windows.

## Why you would want it

XERJ is one Rust binary that indexes code, docs, logs, JSONL/CSV and PDFs and serves BM25, vector and hybrid search behind an Elasticsearch-compatible API. Running `xerj autoindex <folder>` sniffs each file and creates one index per dataset with no schema to write, and source files go through tree-sitter so code arrives with symbols and line numbers. `xerj mcp` is an MCP stdio server that proxies to the local node and exposes seventeen tools, including search, hybrid search, memory store and recall, and code search.

## Best for

- Letting an agent search a local codebase by passage
- Agent memory recalled across sessions
- Querying logs and JSONL/CSV with Elasticsearch syntax

## Use it when

You want a coding agent to query an index of your project, docs or logs through MCP instead of grepping and reading whole files, with the data indexed locally.

## Skip it if

The quick start runs the node with `--insecure`, which the README says turns off TLS and API-key auth so every caller that can reach the port can read and delete every index; it is meant for one user on a dev machine, and a shared host needs the auth-on start with an API key. The installer is a `curl | sh` script. The optional `rerank` search stage sends result text to TypeSafe AI's servers once you set a key. The default embedder is lexical, and the neural embedder is opt-in with a download of about 90 MB. The README says passage search for coding is neutral to harmful on popular public libraries the model already knows, and the latest release is a release candidate (v1.0.0-rc.97).

## Editor note

Windows install uses PowerShell: irm https://xerj.org/get.ps1 | iex. After install, `xerj mcp` needs a running node; the README MCP config block shows the client setup.

## Install

Install the xerj binary (Linux, macOS):

```sh
curl -fsSL https://xerj.org/get | sh
```

Source: https://github.com/xerj-org/xerj#install-by-hand

## Live signals

Fetched 2026-10-20T11:40:36.830Z (status: ok).

- Repository: xerj-org/xerj
- Repository created: 2026-06-30
- Stars: 10,872 (GitHub's count; it cannot be authenticated)
- Stars per day, since repo creation: 96.8 (an average over the repo's life, not a growth rate)
- Forks: 680
- Open issues and PRs: 106
- License (GitHub): Apache-2.0
- Last push: 2026-10-20
- Latest release: v1.0.0-rc.97 (2026-10-19)

## Links

- Website: https://xerj.org
- GitHub: https://github.com/xerj-org/xerj
- Install instructions verified at: https://github.com/xerj-org/xerj#install-by-hand
- Source for this entry: https://github.com/xerj-org/xerj#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/xerj
- Full catalog (JSON): https://agenttooldrop.com/tools.json