mnemonexus-mcp-server
MCP server pro mnemonexus — memória pra agentes de IA, open source, em português.
Plug em Claude Desktop, Cursor, Hermes ou qualquer cliente MCP. Em <2min seu agente lembra de conversas, decisões, lições e fatos entre sessões — sem mais "alzheimer digital".
Instalação
pip install mnemonexus-mcp-server
ou direto do repo:
pip install git+https://github.com/lrdeoliveira/mnemonexus-mcp-server
Configuração
Variáveis de ambiente:
| Var | Default | Descrição |
|---|---|---|
MNEMONEXUS_URL |
http://localhost:8080 |
Base URL da API mnemonexus |
MNEMONEXUS_TOKEN |
(vazio) | Token Sanctum (Bearer) — obrigatório pra writes |
MNEMONEXUS_TIMEOUT |
30 |
Timeout HTTP em segundos |
Gere o token via:
curl -X POST http://localhost:8080/api/v1/auth/login \
-H "Content-Type: application/json" \
-d '{"email":"you@example.com","password":"..."}'
Claude Desktop
Adicione ao ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) ou %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"mnemonexus": {
"command": "mnemonexus-mcp-server",
"env": {
"MNEMONEXUS_URL": "http://localhost:8080",
"MNEMONEXUS_TOKEN": "seu-token-sanctum"
}
}
}
}
Reinicia o Claude Desktop. Você verá as tools nexus_recall, nexus_remember, etc. disponíveis.
Tools
| Tool | O que faz |
|---|---|
nexus_recall |
Busca híbrida (FTS + vetor) — pergunte qualquer coisa |
nexus_remember |
Adiciona memória nova (texto, decisão, lição) |
nexus_extract |
Extrai facts/entidades/relações via FactExtractor |
nexus_lesson |
Registra lição (twice-rule automático) |
nexus_decision |
Loga decisão com rationale e alternativas |
nexus_compact_session |
Fecha + compacta uma sessão |
nexus_history |
Cadeia de versões de uma página |
nexus_search_entity |
Busca no grafo de entidades |
nexus_card |
Card compacto de uma entidade |
Dev local
git clone https://github.com/lrdeoliveira/mnemonexus-mcp-server
cd mnemonexus-mcp-server
pip install -e .
mnemonexus-mcp-server # roda como stdio MCP server
Pra inspecionar interativamente:
npx @modelcontextprotocol/inspector mnemonexus-mcp-server
Licença
MIT.
Metadata
Release files for mnemonexus-mcp-server 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mnemonexus_mcp_server-0.1.0.tar.gz | 5.9 kB | Without provenance | Details for mnemonexus_mcp_server-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mnemonexus_mcp_server-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for mnemonexus_mcp_server-0.1.0-py3-none-any.whl |
Total release size: 13.1 kB
Release files / mnemonexus_mcp_server-0.1.0.tar.gz
| Download URL | mnemonexus_mcp_server-0.1.0.tar.gz |
|---|---|
| Size | 5.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fc9eea8927954a1283e928a3d1154e62fb45938c512052959ab5dbb7d69f1a5f
|
|
BLAKE2b-256 checksum How to use checksums |
8feea0fe144f3c2acf4f16db2dcb8a1f00ff869ec10d5e5947351081d3f4a394
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Release files / mnemonexus_mcp_server-0.1.0-py3-none-any.whl
| Download URL | mnemonexus_mcp_server-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
30d8fd375998b8ad24552b485c8379201c7df0fcf03cc03ab636a2e8bdb11e5c
|
|
BLAKE2b-256 checksum How to use checksums |
8674d284538d0524d9747ebc4e0613994266168a1f8ded9dd9d49ae81fb9b2ca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Security for mnemonexus-mcp-server 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.