OnMind-RAG
This lightweight knowledge base (RAG) MCP server enables agents to query, search, and retrieve content from one or more static sites, complementing a static site generator. Key capabilities:
List configured sites (
list_sites): View loaded sites, body-cache statistics, and Orama search engine status (mode, embeddings, snapshot).Summarize the knowledge base (
catalog_summary): Get document counts by site, category, language, and top tags, filterable by visibility (public,protected,all).Full-text search (
search_content): Perform BM25 searches (optional hybrid/vector if embeddings enabled) across titles, descriptions, tags, and full markdown body. Filter by site, category, language, tags, and visibility. Paginate withlimitandoffset.Retrieve document metadata (
get_entry): Fetch full metadata for a document by its stable ID (e.g.,know:devops/es/Keycloak).Read full document (
read_document): Get the complete markdown body (without frontmatter) from cache/disk, with configurable truncation up to 100,000 characters.List series (
list_series): List documents in a category ordered by filename for sequential reading (e.g., chapters, dream logs).Reload catalog (
reload_catalog): Re-read index and markdown files from disk and rebuild the Orama index, respecting snapshot settings.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OnMind-RAG Search for 'markdown indexing' in the knowledge base"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
On startup, the server loads
docs/public/_index.jsonfrom each configured site.Normalizes in memory (stable IDs, clean tags,
visibility, path to.md).Body cache: reads each
.mdonce, storesbodyText(no frontmatter) and logs time/size to stderr.Search engine: Orama BM25 full-text by default;
hybrid/vectormodes opt-in with embeddings.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/knowfrom OnMind-PUB)
Setup
cd rag
cp .env.example .env # optional; you can also export vars
bun install # or: npm installVariables (see .env.example):
Variable | Meaning |
| Paths to site roots, comma-separated (required) |
| Optional labels (same order) |
|
|
| Max chars returned by |
|
|
|
|
|
|
| Vector dimensions (default 384) |
|
|
| Snapshot path (default |
Example:
export RAG_SITES=../sites/know
# or multiple:
# export RAG_SITES=../sites/know,../sites/andreySmoke test (no MCP)
RAG_SITES=../sites/know bun run smokeWith embeddings + hybrid:
RAG_SITES=../sites/know RAG_EMBEDDINGS=1 RAG_SEARCH_MODE=hybrid bun run smokeWith 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: loadedStart MCP server (stdio)
RAG_SITES=../sites/know bun run mcpMCP 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
nodeinstead ofbun
{
"command": "node",
"args": ["/absolute/path/to/pub/rag/src/server.js"],
"env": { "RAG_SITES": "/absolute/path/to/pub/sites/know" }
}Tools
Tool | Purpose |
| Loaded sites, body-cache stats, search-engine status (Orama, embeddings, snapshot) |
| Stats by category / language / tags (orientation) |
| Full-text Orama (BM25) by default on title/description/tags/body. |
| One record by |
| Markdown body (preferably from cache; truncatable) |
| Series ordered by |
| Re-reads |
Typical agent flow:
catalog_summary → search_content → get_entry / list_series → read_documentRelation to OnMind-PUB
OnMind-PUB | onmind-rag |
Generates | Only consumes it |
Publish workflow | Outside that flow |
Lives in monorepo for convenience | Movable: just point |
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 · 450msWith 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 |
| BM25 with stemming, typo tolerance, field boosting. Fast, no external deps. |
| BM25 + vector (cosine) — needs |
| Vector similarity only — needs |
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 toolscatalog_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
Scored across 7 tools
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.
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.
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.
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
Related MCP Connectors
KnowMan MCP server: search, ask, save and read your Knowledge Base from any MCP client.
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
An MCP server for search and retrieval over a local LanceDB database
Related MCP Servers
- AlicenseBqualityDmaintenanceA 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.3MIT
- AlicenseAqualityBmaintenanceMCP server for local knowledge management with Markdown and PDF indexing using SQLite FTS5.515 npm2MIT
- FlicenseNot gradedqualityDmaintenanceA CLI tool and MCP server that turns markdown documentation into a searchable, queryable knowledge base.-
- AlicenseNot gradedqualityBmaintenanceA 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 PyPIMIT