mcp-memoria
Shared project memory MCP server for storing and retrieving technical decisions, lessons learned, ADRs, and cross-links between projects.
README
mcp-memoria
Memoria de proyectos compartida. MCP server gemelo de mop-mcp pero para conocimiento: decisiones, lecciones, ADRs, links entre proyectos/ideas.
Quick reference
- Endpoint target:
http://secops:9092/mcp(HTTP, JSON-RPC sobre Streamable HTTP) - Stack: Python 3.12 + FastAPI + uvicorn (replica mop-mcp v3.4.2)
- Privacidad: allowlist de paths (NO MEMORY/USER/SOUL/IDENTITY/AGENTS/briefing)
- HA: backup diario a geo + tars vps (2 destinos, sin OCI por ahora)
- Embeddings + vector store (decisión 2026-07-01 corregida: sistema de memoria de la organización, requiere calidad)
- Lifecycle: 1 año (compromiso de Rodrigo)
- Status: PLAN — discovery completo, listo para implementación
Docs en este directorio
PLAN.md— plan completo: decisiones, stack, arquitectura, tools, tasks, riesgos, criterios de éxitoSECURITY.md— privacy boundaries (qué lee y qué NO lee, test de no-leak)OPEN_QUESTIONS.md— 4 puntos pendientes antes de implementar
Tools que va a exponer (9)
decision_list/decision_get— decisiones técnicaslesson_list/lesson_get— lecciones aprendidasadr_get— ADRs (Architecture Decision Records)project_brief— resumen por proyectocross_links— entidades que mencionan un topiclink_add/link_list— vincular entidades (append-only log)
Sources permitidos
~/.openclaw/workspace/kb/{decisions,lessons,jobs,concepts,wiki}/~/.openclaw/workspace/04-decisions/~/.openclaw/workspace/clientes/*/decisions.md
NO lee (denylist explícito): MEMORY.md, USER.md, SOUL.md, IDENTITY.md, AGENTS.md, briefing/, memory/sessions/, clientes//contactos
Cómo deployar (cuando se implemente)
cd /opt/mcps/memoria
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e .
sudo systemctl mcp-memoria
curl http://secops:9092/health
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.