{
"mcpServers": {
"agenthub-mcp-server-runtime": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
AgentHub MCP Server Runtime (Go)
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 5 days ago.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Agenthub Mcp Server Runtime and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Servidor MCP que expõe as capacidades do AgentHub (Skills, Knowledge Bases, Prompts) via protocolo Model Context Protocol, permitindo que sistemas externos como Claude Desktop, IDEs e outros agentes consumam as capacidades da plataforma.
Claude Desktop / IDE / Agente externo
│ (stdio ou HTTP)
▼
agenthub-mcp-server-runtime
│
├── GET /api/skills?status=ACTIVE ───► agenthub-backend:8080
├── GET /api/knowledge-bases ─────────► agenthub-backend:8080
└── POST /api/v1/skills/invoke ───────► agenthub-skill-runtime:8082
| Tipo MCP | Origem AgentHub | Descrição |
|----------|----------------|-----------|
| Tools | Skills ativas | Cada skill vira uma MCP Tool com seu inputSchema |
| Resources | Knowledge Bases | URI: agenthub://kb/{id} |
| Prompts | Curados (hardcoded) | Templates para operações comuns |
pesquisar-conhecimento — busca semântica em knowledge basesexecutar-skill — executa uma skill com parâmetros JSONTodas as configurações são via variáveis de ambiente:
| Variável | Descrição | Padrão |
|----------|-----------|--------|
| AGENTHUB_TENANT_ID | Obrigatório. UUID do tenant | — |
| AGENTHUB_BACKEND_URL | URL do agenthub-backend | http://agenthub-backend:8080 |
| AGENTHUB_SKILL_RUNTIME_URL | URL do agenthub-skill-runtime | http://agenthub-skill-runtime:8082 |
| AGENTHUB_API_TOKEN | Bearer token para autenticação | — |
| STDIO_MODE | Iniciar em modo stdio | true |
| HTTP_PORT | Porta do servidor HTTP (0 = desabilitado) | — |
O servidor lê requisições JSON-RPC do stdin e escreve respostas no stdout. Ideal para integração com Claude Desktop, que lança o servidor como subprocesso.
// ~/.config/claude/claude_desktop_config.json
{
"mcpServers": {
"agenthub": {
"command": "/caminho/para/mcp-server-runtime",
"env": {
"AGENTHUB_TENANT_ID": "seu-tenant-uuid",
"AGENTHUB_BACKEND_URL": "http://localhost:8080",
"AGENTHUB_SKILL_RUNTIME_URL": "http://localhost:8082",
"AGENTHUB_API_TOKEN": "seu-token",
"STDIO_MODE": "true"
}
}
}
}
Quando HTTP_PORT está definido, o servidor também expõe endpoints HTTP:
# Iniciar em modo HTTP puro
AGENTHUB_TENANT_ID=uuid STDIO_MODE=false HTTP_PORT=8080 ./mcp-server-runtime
# Health check
curl http://localhost:8080/health
# Enviar requisição JSON-RPC
curl -X POST http://localhost:8080/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
// Requisição
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"claude","version":"1.0"}}}
// Resposta
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2024-11-05","capabilities":{"tools":{},"resources":{},"prompts":{}},"serverInfo":{"name":"agenthub-mcp-server-runtime","version":"1.0.0","protocolVersion":"2024-11-05"}}}
// Requisição
{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}
// Resposta
{"jsonrpc":"2.0","id":2,"result":{"tools":[{"name":"document-search","description":"Busca semântica em documentos","inputSchema":{"type":"object","properties":{"query":{"type":"string"},"limit":{"type":"integer"}},"required":["query"]}}]}}
// Requisição
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"document-search","arguments":{"query":"arquitetura do AgentHub","limit":5}}}
// Resposta
{"jsonrpc":"2.0","id":3,"result":{"content":[{"type":"text","text":"{\"documents\":[...]}"}],"isError":false}}