Mnē-MCP
Allows indexing Obsidian vaults and querying them using RAG, providing answers with citations to specific note paths and headings.
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., "@Mnē-MCP qué escribí sobre embeddings en mis notas del proyecto"
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.
Mnē-MCP — MCP RAG Server for opencode
Mnē-MCP (from the Greek Mnēmosynē, Titaness of memory; the macron in ē, U+0113, marks the long vowel in the transliteration) is an MCP server that implements a complete RAG (Retrieval-Augmented Generation) pipeline for opencode: it indexes an Obsidian vault or document folders and answers assistant questions using your own notes as a source, citing the exact path of each fragment used.
Stack: #RAG #MCP #mcp-server #opencode #Obsidian #Qdrant #Ollama #DeepSeek #bge-m3 #Python
Features
Incremental indexing — scans directories (
.md,.txt) from disk with change detection viamtime+md5, stale cleanup, and support for large volumes (~19 GB).Local embeddings —
bge-m3model via local Ollama (/api/embed), 1024 dimensions, multilingual (including Spanish), L2-normalized to scale correctly with cosine similarity.Semantic retrieval — Qdrant (Docker), single collection with payload filters (
source,path,mtime,md5,heading_path) and configurable relevance threshold.Grounded generation — answers with
deepseek-v4-flash(Ollama Cloud) only when evidence exceeds the threshold; otherwise returns explicit rejection ("no relevant documents found"). Without evidence, it does not generate.
Related MCP server: Obsidian MCP Assistant
Architecture
MCP tools (stdio) ──┐
├── RagService (core) ────▶ Qdrant (vectorial, Docker)
Admin page (:8310) ─┘ │
├── OllamaEmbedder (bge-m3 local)
└── LLMProvider (deepseek-v4-flash, Ollama Cloud)Python 3.14 · official MCP SDK (
mcp==1.12.4) ·qdrant-client·httpx7 tools:
index·query·search·delete·list·stats·configLocal admin page (
http://127.0.0.1:8310): dashboard, indexed documents, asynchronous indexing with progress, and search playground. Shares the same core as the MCP tools (zero duplicated logic).Suite of 70 offline tests (Qdrant
:memory:+ mocks) + end-to-end smoke test.
Developer Usage
docker compose up -d qdrant # Qdrant
ollama pull bge-m3 # embeddings locales
cp .env.example .env # OLLAMA_API_KEY + VAULT_ROOT
make install # instala el paquete (venv)
make admin # panel: http://127.0.0.1:8310Register in opencode.json (mcp section, local type, command python3 mcp_rag/server.py or the mcp-rag-opencode entry point).
Request | Behavior |
| Incremental scan, skips unchanged files, uploads vectors in batches |
| Retrieval → reranker/LLM → answer with citations ( |
| Raw hits with |
| Qdrant/Ollama health, LLM status, counts by source |
Roadmap
Hybrid dense+sparse search (BM25 + RRF) · cross-encoder reranking · semantic cache · evaluation harness (recall@k, MRR, nDCG) — planned in openspec/specs/mnemos-differentiators/.
Academic
Integrated Project · Prof. Christian Pérez · Student: Gat · 2026
Available Tools
7 toolsconfigC
Get the full config, or set one persisted field.
Inputs: key, value, action.
deleteA
Delete indexed docs by exact path or by source.
Inputs: path, source.
indexB
Index the vault (source root or sub-path) into Qdrant.
Inputs: path, source, max_files, force_rescan.
listA
List indexed documents (paginated, filter by source/path prefix).
Inputs: limit, offset, source, path_prefix.
queryC
Retrieve context and answer the question with the LLM.
Inputs: question (required), top_k, source, path_prefix, +1 more.
searchB
Raw vector retrieval without the LLM.
Inputs: text (required), top_k, source, path_prefix, +1 more.
statsB
Return collection stats and provider health.
Inputs: no named parameters.
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 distinct role: indexing, LLM-based querying, raw vector search, deletion, listing, stats, and config. Query and search are clearly separated by whether the LLM is involved.
All tool names are lowercase, single-word commands that follow a consistent imperative/noun style. The set is uniform and predictable despite not using a verb_noun pattern.
Seven tools is well-scoped for a focused memory/RAG server. Each tool covers a necessary operation without redundancy or bloat.
The toolset covers the full indexed-document lifecycle: add via index, retrieve via search/query, remove via delete, inspect via list and stats, and configure via config. No critical missing operation is apparent.
Maintenance
Related MCP Connectors
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Search your Obsidian vault to quickly find notes by title or keyword, summarize related content, a…
Open-source Obsidian for MDX - edit local docs with agent assistance
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables indexing local documents (PDF, Markdown, text, code) into a knowledge base and querying them via semantic search using local embeddings, all running privately on your machine.4-
- FlicenseNot gradedqualityCmaintenanceEnables AI-powered chat and file operations on Obsidian vaults with local indexing, hybrid search, and MCP access.-
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to search, read, create, update, and delete notes in a local Obsidian vault through hybrid semantic and lexical retrieval, with all embedding and vector storage running locally.1MIT
- AlicenseAqualityBmaintenanceEnables natural-language and keyword search across Obsidian notes, returning reranked passages with provenance, and supports reading notes and incremental indexing.31MIT