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.
Rust agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-search
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.xerj-org/xerj",
"title": "XERJ",
"description": "The search engine for AI agents: cited answers from your local code, docs, specs and logs.",
"version": "1.0.0-rc.100",
"websiteUrl": "https://xerj.org",
"repository": {
"url": "https://github.com/xerj-org/xerj",
"source": "github"
},
"packages": [
{
"registryType": "mcpb",
"identifier": "https://github.com/xerj-org/xerj/releases/download/mcpb-v1.0.0-rc.100/xerj-mcp-1.0.0-rc.100.mcpb",
"fileSha256": "753024ab77027fd807667e442555c88749d20d5a9ae49ff9ca9da623f20a7156",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"name": "XERJ_URL",
"description": "ES-compatible listener of a running XERJ node (start one with `xerj --insecure --data-dir ~/xerj-data`).",
"default": "http://localhost:9200",
"isRequired": false
},
{
"name": "XERJ_AUTH",
"description": "Authorization header for a node with auth on, e.g. 'ApiKey <key>'. Optional for a loopback node: the key is read from <data-dir>/admin.key.",
"isRequired": false,
"isSecret": true
}
],
"version": "1.0.0-rc.100"
}
]
}