second-brain
This MCP server implements a second brain system, managing unvalidated investigation cases as JSON and validated knowledge as markdown files and skills. It provides tools for creating, updating, promoting cases, managing knowledge files, and performing semantic search.
README
second-brain
MCP server + skill pour un second cerveau : la connaissance validée vit dans des fiches MD et des skills, tout ce qui n'est pas encore validé vit dans des cases (dossiers d'investigation JSON). Un case résolu se promeut en fiche ou en skill via le MCP.
source de vérité (fichiers) index dérivé (regénérable)
──────────────────────────────────── ────────────────────────────
<data_dir>/
cases/<case-id>/case.json ──→ vector/ (chromadb, gitignoré)
cases/<case-id>/evidence/*.log + recherche lexicale (fallback)
fiches/*.md
skills/<slug>/SKILL.md
Stack
- Python 3.12+,
uv - FastMCP (stdio)
- ChromaDB + fastembed (index vectoriel, optionnel :
[vector]) - jsonschema (validation des cases)
Installation (dans un projet)
uv init
uv add "second-brain[vector]" # ou sans [vector] pour le fallback lexical
Ou depuis le repo :
cd second-brain
uv sync --extra vector
Configuration
| Variable | Rôle | Défaut |
|---|---|---|
SECOND_BRAIN_DATA_DIR |
Dossier racine des données (cases + kb + vector) | ~/second-brain-data |
Câbler le serveur MCP dans opencode
Ajouter à ~/.config/opencode/opencode.json :
{
"mcp": {
"second-brain": {
"type": "local",
"command": ["/opt/second-brain/.venv/bin/python", "-m", "second_brain.server"],
"enabled": true,
"environment": {
"SECOND_BRAIN_DATA_DIR": "/opt/infra/kb"
}
}
}
}
Installer le skill globalement
Le skill est versionné dans ce repo (skill/second-brain/SKILL.md). Pour le rendre
disponible à tous les agents opencode :
ln -s /opt/second-brain/skill/second-brain ~/.agents/skills/second-brain
Sur une autre machine, cloner le repo puis créer le même lien pointant vers le checkout.
Outils MCP
Cases
| Outil | Rôle |
|---|---|
case_create |
Créer une investigation (sujet non validé) |
case_get / case_list |
Lire / lister (filtres status, tag) |
case_search |
Recherche sémantique (cases + KB) |
case_update |
Ajouter findings / steps / hypothèses / conclusion |
case_add_evidence |
Attacher une preuve (log, sortie, note) |
case_set_status |
open / in_progress / resolved / abandoned |
case_promote |
Promouvoir un case résolu → fiche ou skill |
KB
| Outil | Rôle |
|---|---|
fiche_list / fiche_read / fiche_write |
CRUD des fiches validées |
skill_list / skill_read |
CRUD des skills validés |
index_rebuild |
Reconstruire l'index vectoriel depuis les fichiers |
Schéma des cases
Défini dans schema/case.schema.json — source de vérité.
Tout case écrit via le MCP est validé contre ce schéma.
Tests
uv run pytest tests/ -v
uv run ruff check src/ tests/
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.