convez.ai
MCP ServerFinanceiroIntermediário
bevanding

Signal Daemon

bevanding/signaldaemon

Inteligência de narrativas e sinais para agentes de IA em crypto/macro

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP para inteligência de narrativas e sinais em crypto, IA e macro. Entrega narrativas curadas e sinais convergentes de múltiplas fontes, com falha segura (recusa alucinação). Integra-se nativamente a agentes Claude e outros via HTTP remoto ou stdio local.

Instalação

$npx convez-ai bevanding/signaldaemon

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 4 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Agentes de IA analisarem convergência narrativa em cripto e macro
  • Monitorar divergência entre capital e narrativa em tópicos específicos
  • Alimentar sistemas autônomos com sinais curados (não raw data)
  • Pesquisa de mercado token-agnostic para tomada de decisão

Veredito

Ferramenta especializada e bem arquitetada para agentes que precisam de inteligência narrativa em mercados de cripto e macro. Fortaleza clara no design "fail-safe" e integração MCP; limitação é escopo restrito (nicho financeiro/cripto).

README

A tradução para o português deste README ainda está na fila.

signaldaemon

Narrative & signal intelligence for AI agents — crypto, AI, and macro. A dumb-but-trustworthy pipe: it delivers curated narrative & signal, not raw data, and it fails safe — when it has no coverage it says so, rather than inventing. Built for machines, not human eyes.

This repo is the front door — quickstart, client configs, and the interface contract. The pipeline itself (sources, scoring, curation) is not open source.


What it is (and isn't)

It isIt is not
Cross-source narrative convergence + capital-vs-narrative divergenceA price/market-data API (use CoinGecko etc. for that)
Coverage across ~14 crypto/AI/macro domainsA raw news firehose
Fails safe — "no coverage" over hallucinationA database you query for facts
For agents (API/MCP), token-cost-agnostic, quality-firstA human-facing dashboard

Quickstart

# 1 · self-serve a demo key (no signup)
KEY=$(curl -s -X POST https://api.signaldaemon.com/v1/request-key | jq -r .key)

# 2 · the day's ranked narratives + derived signals (cached, instant)
curl -s https://api.signaldaemon.com/v1/narratives \
  -H "x-api-key: $KEY" -d '{"limit":8}'

# 3 · clean narrative feed for a topic
curl -s https://api.signaldaemon.com/v1/feed \
  -H "x-api-key: $KEY" -d '{"query":"restaking","limit":8}'

Connect from your agent (MCP)

Remote MCP over Streamable HTTP, authenticated with the x-api-key header.

# Claude Code
claude mcp add --transport http signaldaemon \
  https://api.signaldaemon.com/mcp --header "x-api-key: <KEY>"
# Hermes Agent — ~/.hermes/config.yaml
mcp_servers:
  signaldaemon:
    url: "https://api.signaldaemon.com/mcp"
    headers: { x-api-key: "<KEY>" }

More clients (Cursor, Cline) in examples/mcp-configs.md. Tools: get_market_narratives(limit) · get_clean_feed(query, category, limit) — both annotated readOnlyHint.

Local stdio bridge

For clients that don't support remote MCP, this repo ships a thin stdio bridge (mcp_server.py) exposing the same two tools over the hosted API. It holds no methodology — just a client.

pip install mcp
export SIGNALDAEMON_API_KEY=cns_...   # https://signaldaemon.com/console
python mcp_server.py

Or with Docker:

docker build -t signaldaemon-mcp . && \
docker run -i -e SIGNALDAEMON_API_KEY=cns_... signaldaemon-mcp

The bridge starts and answers introspection (tools/list) without a key; tool calls require one.

Interface

Endpoints and response-field contract (incl. the divergence schema) in API.md. Field names are stable.

License

Examples and docs in this repo: MIT (see LICENSE). The signaldaemon service and pipeline are proprietary.

Ver o original no GitHub

Bom para

Relacionados