Nexus Leads AI — MCP Bridge
Remote MCP server that connects Nexus Leads AI to MCP-compatible clients, enabling read-only operations on leads, tasks, proposals, and more, plus controlled test scenarios, secured via GitHub OAuth.
README
Nexus Leads AI — MCP Bridge V1
Servidor MCP remoto e privado para conectar o Nexus Leads AI a clientes compatíveis com Model Context Protocol.
Arquitetura
ChatGPT / MCP Inspector
↓ OAuth 2.1
GitHub OAuth + lista de usuários permitidos
↓
Cloudflare Worker: nexus-leads-mcp
↓
D1 nexus-leads-db + API do Nexus principal
O MCP fica em um Worker separado para evitar que uma falha no conector derrube o site principal.
Ferramentas incluídas
Somente leitura
nexus_system_healthnexus_command_centernexus_list_leadsnexus_get_leadnexus_list_tasksnexus_list_proposalsnexus_list_paymentsnexus_list_projectsnexus_run_full_auditnexus_test_api_endpoints
Testes controlados
nexus_seed_test_scenario: cria um cenário identificado com prefixomcp_test_.nexus_cleanup_test_data: remove somente os registros de teste MCP e exige confirmação literal.
Todas as chamadas tentam registrar auditoria em mcp_audit_log.
Segurança
- OAuth 2.1 intermediado pelo Worker.
- Login pelo GitHub.
- Lista permitida em
ALLOWED_GITHUB_USERS. - Nenhuma chave do Nexus é enviada ao modelo.
- O token GitHub é usado somente para confirmar identidade e não é salvo como dado de negócio.
- Ferramentas de escrita e exclusão são marcadas corretamente no MCP.
- O servidor MCP usa um Durable Object próprio e o mesmo D1 do Nexus.
Instalação resumida
Siga GUIA_INSTALACAO_PASSO_A_PASSO.md.
- Execute
migrations/0017_mcp_bridge.sqlno D1. - Crie um KV chamado
OAUTH_KV. - Cole o ID do KV em
wrangler.jsonc. - Crie um GitHub OAuth App.
- Cadastre os quatro secrets.
- Publique este Worker separado.
- Teste no MCP Inspector.
- Em um plano do ChatGPT com Developer Mode, adicione a URL HTTPS terminada em
/mcp.
Endpoint esperado
https://nexus-leads-mcp.luizfelipeehsilva.workers.dev/mcp
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.