xerj

Level AMCP ecosystemNot an MCP ServerLocal

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

Overview

XERJ is a local-first search engine and MCP server for AI agents, shipped as a single Rust binary. It auto-indexes code, docs, logs, JSONL/CSV, PDFs and SQLite, and offers BM25 full-text, vector and hybrid search, so agents pull the exact code passages they need instead of reading files one by one. Uses include code search, agent memory and RAG. It exposes an Elasticsearch-compatible API, and Corpus Hub serves hundreds of reference memory corpora. Works with Claude Code, Cursor and any MCP clien…

⭐ 18.8kDatabaseRustRepo ↗Updated 2026-11-02

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "xerj": {
      "command": "npx",
      "args": [
        "https://github.com/xerj-org/xerj/releases/download/mcpb-v1.0.0-rc.99/xerj-mcp-1.0.0-rc.99.mcpb"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/xerj-org/xerj

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "xerj": {
      "command": "npx",
      "args": [
        "https://github.com/xerj-org/xerj/releases/download/mcpb-v1.0.0-rc.99/xerj-mcp-1.0.0-rc.99.mcpb"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers