xerj

Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid sear…

Data & Analytics

xerj is a community MCP server that connects AI assistants like Claude to local-first search engine and mcp server for ai agents. one rust binary indexes code, docs, logs, jsonl/csv and pdfs for bm25 full-text, vector and hybrid sear…. It runs locally on your machine, keeping your data private and giving you full control over the connection. Adding it to your setup expands what Claude can do without any extra coding.

About xerj

Overview

Local-first search engine and MCP server for AI 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.

Topics

agent-memory, ai-agents, bm25, claude-code, cli, code-search, cursor, elasticsearch, elasticsearch-alternative, full-text-search, hybrid-search, jsonl, local-first, mcp, mcp-server, model-context-protocol, rag, rust, search-engine, vector-search

Who Should Use xerj?

1Search and retrieve information using natural language
2Extend Claude and other AI assistants with new capabilities
3Automate tasks that previously required manual steps
4Connect your existing tools to an AI workflow

How xerj Compares

✦It runs entirely on your local machine, so no data leaves your environment — important for teams with privacy or compliance requirements.

✦Compared to other Data & Analytics MCP servers, it focuses on a well-scoped set of capabilities, which keeps the integration lightweight and predictable.