Skip to main content
Glama

OnMind-RAG

A complementary and independent project from OnMind-PUB: a lightweight knowledge base (light RAG) that exposes an MCP server so an agent (MCP client) can query the content of one or more sites.

It is not part of the init → index → build → publish workflow. It only reads the _index.json already generated by a site and, on demand, the markdown.

Idea

  1. On startup, the server loads docs/public/_index.json from each configured site.

  2. Normalizes in memory (stable IDs, clean tags, visibility, path to .md).

  3. Body cache: reads each .md once, stores bodyText (no frontmatter) and logs time/size to stderr.

  4. Search engine: Orama BM25 full-text by default; hybrid/vector modes opt-in with embeddings.

  5. Exposes compact MCP tools: summary → search (meta + body) → document reading.

No _catalog.json is written. If the site re-indexes externally, use the reload_catalog tool.

Related MCP server: Lexomni MCP

Requirements

  • Node.js ≥ 18 (or Bun with Node compatibility)

  • At least one site with docs/public/_index.json (e.g. sites/know from OnMind-PUB)

Setup

cd rag
cp .env.example .env   # optional; you can also export vars
bun install            # or: npm install

Variables (see .env.example):

Variable

Meaning

RAG_SITES

Paths to site roots, comma-separated (required)

RAG_SITE_NAMES

Optional labels (same order)

RAG_VISIBILITY

public (default) | protected | all

RAG_MAX_BODY

Max chars returned by read_document (default 50000; increase for very long docs)

RAG_CACHE_BODY

1 (default) caches body at startup → Orama indexes body → full-text on markdown. 0 = metadata only (title/desc/tags) → no body search; read_document falls back to disk.

RAG_SEARCH_MODE

fulltext (default, BM25) | hybrid | vector (last two require RAG_EMBEDDINGS=1)

RAG_EMBEDDINGS

1 enables local hash embeddings for hybrid/vector; 0 (default)

RAG_EMBED_DIMS

Vector dimensions (default 384)

RAG_SNAPSHOT

1 saves/loads Orama snapshot to disk; 0 (default)

RAG_SNAPSHOT_PATH

Snapshot path (default ./data/orama-snapshot.json)

Example:

export RAG_SITES=../sites/know
# or multiple:
# export RAG_SITES=../sites/know,../sites/andrey

Smoke test (no MCP)

RAG_SITES=../sites/know bun run smoke

With embeddings + hybrid:

RAG_SITES=../sites/know RAG_EMBEDDINGS=1 RAG_SEARCH_MODE=hybrid bun run smoke

With snapshot (2nd load ~100 ms):

RAG_SITES=../sites/know RAG_SNAPSHOT=1 bun run smoke   # first: saved
RAG_SITES=../sites/know RAG_SNAPSHOT=1 bun run smoke   # second: loaded

Start MCP server (stdio)

RAG_SITES=../sites/know bun run mcp

MCP Client (Cursor / Claude Desktop / Grok / Jan)

{
  "mcpServers": {
    "onmind-rag": {
      "command": "bun",
      "args": ["/absolute/path/to/pub/rag/src/server.js"],
      "env": {
        "RAG_SITES": "/absolute/path/to/pub/sites/know",
        "RAG_VISIBILITY": "public",
        "RAG_SEARCH_MODE": "fulltext",
        "RAG_EMBEDDINGS": "0",
        "RAG_SNAPSHOT": "0"
      }
    }
  }
}

You can also use node instead of bun

{
  "command": "node",
  "args": ["/absolute/path/to/pub/rag/src/server.js"],
  "env": { "RAG_SITES": "/absolute/path/to/pub/sites/know" }
}

Tools

Tool

Purpose

list_sites

Loaded sites, body-cache stats, search-engine status (Orama, embeddings, snapshot)

catalog_summary

Stats by category / language / tags (orientation)

search_content

Full-text Orama (BM25) by default on title/description/tags/body. mode: fulltext|hybrid|vector optional. Returns cards with match.score and match.snippet.

get_entry

One record by id (site:url)

read_document

Markdown body (preferably from cache; truncatable)

list_series

Series ordered by filename within a category

reload_catalog

Re-reads _index.json + body cache + rebuilds index

Typical agent flow:

catalog_summary → search_content → get_entry / list_series → read_document

Relation to OnMind-PUB

OnMind-PUB

onmind-rag

Generates _index.json and the static site

Only consumes it

Publish workflow

Outside that flow

Lives in monorepo for convenience

Movable: just point RAG_SITES to any folder with docs/public/_index.json

Body cache (startup)

In stderr you'll see something like:

[onmind-rag] index: 289 entries from 1 site(s) in 3ms at ...
[onmind-rag] body cache: 289 docs, 3533.3 KiB in 59ms (missing path=0, read errors=0)
[onmind-rag] search engine: orama · mode=fulltext · embeddings=off · 289 docs · 450ms

With RAG_CACHE_BODY=1 (default): Orama indexes the body field → search_content performs full-text BM25 over the entire markdown. read_document answers from memory (fromCache: true).

With RAG_CACHE_BODY=0: Orama only indexes metadata (title, description, tags) → search_content does not find matches in the document body. read_document falls back to disk reads.

Disable only if RAM is very tight or corpus > 50 MB and you accept metadata-only search.

Search engine (Orama)

Mode

What it does

fulltext (default)

BM25 with stemming, typo tolerance, field boosting. Fast, no external deps.

hybrid

BM25 + vector (cosine) — needs RAG_EMBEDDINGS=1

vector

Vector similarity only — needs RAG_EMBEDDINGS=1

Embeddings (opt-in)

RAG_EMBEDDINGS=1 uses local feature-hashing (no TensorFlow, no API keys) — a portable baseline to exercise the vector/hybrid path. Not a SOTA semantic model. For real quality, replace embed.js with a provider (OpenAI, Xenova/transformers.js, etc.) keeping the embedText(text, { dims }) interface.

Snapshot (opt-in)

RAG_SNAPSHOT=1 serializes the Orama index to disk (data/orama-snapshot.json + .meta.json). On subsequent starts, if the corpus fingerprint (ids, titles, body length, hide, embeddings flag/dims) matches, it loads the snapshot in ~100 ms instead of re-indexing (~450 ms).

Limits (by design)

  • Lexical/BM25 retrieval + hash vectors (no SOTA embeddings unless you plug them in).

  • No knowledge graph / neighbors yet (next step: markdown links).

  • Designed as a useful, portable base — not a managed vector engine.

Why Spanish tokenizer?

The corpus is predominantly Spanish (~80%). Orama's default English tokenizer treats short technical codes like "XDB", "IAM", "UCDM" as stop-words/noise. Setting language: 'spanish' in the tokenizer indexes them correctly.


Based on onmind-rag v0.2.0 — MCP server for knowledge retrieval with Orama BM25 + opt-in hybrid/vector + snapshot

Available Tools

7 tools
catalog_summaryA

Resumen de la base de conocimiento OnMind. Úsalo ANTES de buscar para orientarte: cuenta docs por sitio, categoría, idioma y tags top. Te dice qué hay disponible sin hacer búsqueda.

Inputs: visibility.

get_entryA

Obtiene la ficha completa de un documento OnMind por ID estable (site:url). Úsalo tras search_content para ver metadatos antes de leer el cuerpo.

Inputs: id (required).

list_seriesB

Lista documentos de una serie/categoría OnMind ordenados por filename (libros, sueños, capítulos). Útil para leer en secuencia: abridgetothemiracles, thoseaccordsyoudontremember, dreams, etc.

Inputs: category (required), site, language, visibility.

list_sitesB

List configured knowledge sites, body-cache stats, and search-engine status (Orama, embeddings, snapshot).

Inputs: no named parameters.

read_documentA

Lee el cuerpo markdown COMPLETO de un documento OnMind (sin frontmatter). Úsalo tras search_content/get_entry cuando necesites el contenido técnico completo. El cuerpo puede truncarse (máx 12k chars por defecto).

Inputs: id (required), maxBody.

reload_catalogA

Recarga el índice OnMind desde disco (_index.json + markdown) y reconstruye el índice Orama. Úsalo tras cambios en la fuente (re-index externo). Respeta RAG_SNAPSHOT.

Inputs: no named parameters.

search_contentA

BÚSQUEDA PRIMARIA en la base de conocimiento OnMind. Úsala PRIMERA para cualquier pregunta sobre: OnMind-PUB, OnMind-XDB, OnMind-CMS, OnMind-WDB, OnMind-ARK, OnMind-EPI, OnMind-DAI, Método OnMind, ABCode, CloudOps, DevOps, código, arquitectura, productos OnMind. Busca en título, descripción, tags y cuerpo completo (BM25 Orama). Devuelve cards con score y snippet. NO uses búsqueda web hasta agotar esta herramienta.

Inputs: q, mode, site, tags, +7 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: listing sites, summarizing catalog, fetching entry details, reloading index, searching, reading full documents, and listing series. No two tools overlap in functionality, making selection unambiguous.

    Naming Consistency4/5

    Tool names mostly follow a verb_noun pattern (list_sites, get_entry, reload_catalog, search_content, read_document, list_series). The exception is catalog_summary, which is a noun phrase, but still descriptive and consistent in style.

    Tool Count5/5

    Seven tools is well-scoped for a RAG knowledge base system, covering all necessary operations: overview, search, retrieval of details, admin reload, and series browsing. No tool feels redundant or missing.

    Completeness5/5

    The tool set provides complete coverage for a knowledge retrieval workflow: overview (catalog_summary), search (search_content), entry details (get_entry), full content (read_document), and navigation (list_series, list_sites). No obvious gaps for the intended purpose.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      A local MCP server that allows AI systems to search and retrieve information from a custom knowledge base generated from markdown files. It provides tools for natural language text search, category browsing, and specific content chunk retrieval.
      3
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A CLI tool and MCP server that turns markdown documentation into a searchable, queryable knowledge base.
      -
    • A
      license
      Not graded
      quality
      B
      maintenance
      A lightweight MCP server for semantic search over markdown knowledge bases, enabling AI coding agents to index, search, and answer questions from local markdown documents.
      227 PyPI
      MIT