freemcplab / Directorio / Playground / OpenRouter Deep Research MCP

● Comunidad wheattoast11 ⚡ Instantáneo

OpenRouter Deep Research MCP

Name: OpenRouter Deep Research MCP MCP Server
Author: wheattoast11

por wheattoast11 · wheattoast11/openrouter-deep-research-mcp

Multi-agent research MCP server with consensus-backed ensemble swarm and on-the-fly pglite indexes.

OpenRouter Deep Research MCP is a MCP server that multi-agent research mcp server with consensus-backed ensemble swarm and on-the-fly pglite indexes Use it from Claude Code, Cursor, Codex, or any MCP-compatible / skills-compatible agent.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por qué usarlo

Características clave

Single-purpose integration
Compatible with Claude Code and other agents
Open-source on GitHub
Maintained by the publisher
Easy install via standard tooling

Demo en vivo

Cómo se ve en la práctica

openrouter-deep-research-mcp.replay ▶ listo

0/0

Instalar

Elige tu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "openrouter-deep-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "openrouter-deep-research-mcp"
      ],
      "_inferred": true
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "openrouter-deep-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "openrouter-deep-research-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "openrouter-deep-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "openrouter-deep-research-mcp"
      ],
      "_inferred": true
    }
  }
}

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "openrouter-deep-research-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "openrouter-deep-research-mcp"
      ],
      "_inferred": true
    }
  }
}

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "openrouter-deep-research-mcp",
      "command": "npx",
      "args": [
        "-y",
        "openrouter-deep-research-mcp"
      ]
    }
  ]
}

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

{
  "context_servers": {
    "openrouter-deep-research-mcp": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "openrouter-deep-research-mcp"
        ]
      }
    }
  }
}

Añádelo a context_servers. Zed recarga en caliente al guardar.

claude mcp add openrouter-deep-research-mcp -- npx -y openrouter-deep-research-mcp

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: OpenRouter Deep Research MCP

Use OpenRouter Deep Research MCP for its core workflow

👤 Engineers and power users ⏱ ~15 min intermediate

Cuándo usarlo: You want MCP server integration for ai work without writing glue code.

Requisitos previos

Repo installed / cloned — See repo README

Flujo

Install

Set up the OpenRouter Deep Research MCP MCP server.✓ Copiado

→ MCP server listed in your agent config
Invoke

Use OpenRouter Deep Research MCP to run a representative task in ai.✓ Copiado

→ Tool call succeeds; result returned

Resultado: Real ai work completed via OpenRouter Deep Research MCP with one chat.

Errores comunes

Auth/credential setup is the most common blocker. — Follow the repo README for env vars and tokens.

Combinar con: filesystem

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

openrouter-deep-research-mcp + filesystem

Pair with filesystem for ai workflows that need local file IO.

Use OpenRouter Deep Research MCP together with filesystem.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
primary_call	task-specific	For the main use case	Varies

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: Provider rate limits apply
Tokens por llamada: Varies
Monetario: Free / pay provider directly
Consejo: Cache results; batch calls.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: Use environment variables or your OS keychain.

Salida de datos: Depends on integration

Resolución de problemas

Errores comunes y soluciones

Confirm install and restart your agent.

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills