Intel MCP
Intel MCP
Servicio remoto de Model Context Protocol para TrialAgents Intel Agent.
La primera herramienta implementada es start_analysis. Recibe únicamente un report_run_id creado por la aplicación, llama al endpoint privado del plano de control de la aplicación Intel Agent y devuelve la concesión de análisis de 60 minutos existente o recién reservada. La identidad del usuario, la aprobación del plan, el paquete, las herramientas habilitadas y las asignaciones se resuelven en el servidor mediante la aplicación.
Configuración local
python -m venv .venv
. .venv/bin/activate
pip install -e '.[dev]'
export INTEL_APP_CONTROL_URL=http://localhost:3000
export INTEL_APP_SERVICE_TOKEN=replace-me
export MCP_INBOUND_SERVICE_TOKEN=replace-me-too
intel-mcpEl endpoint HTTP Streamable es /mcp; el endpoint de comprobación de actividad sin autenticación es /health.
Ajustes de producción requeridos:
INTEL_APP_CONTROL_URL: URL base privada de la aplicación Intel Agent.INTEL_APP_SERVICE_TOKEN: credencial de servicio compartida almacenada únicamente en los secretos de Render.MCP_INBOUND_SERVICE_TOKEN: credencial de portador requerida en cada solicitud a/mcp.MCP_ALLOWED_HOSTS: entradas exactas de la lista de permitidos de Host, públicas/privadas, separadas por comas.PORT: puerto HTTP asignado por la plataforma.
El despliegue inicial gratuito de Render es público en la capa de red, pero /mcp está cerrado a quienes no tengan la credencial de portador del servicio interno. OAuth público es un perfil posterior y no debe reutilizar la credencial de servicio interna como autenticación de usuario final.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Manage hosted agentguard proxies: caps, dry-run, loop breaker, run reports, audit export.
Run and manage H Company's Computer-Use Agents from any MCP client.
Accountless pay-per-use code execution for agents. Read-only search and pricing; pay via x402.
Remote MCP for Antigravity agent run receipt MCP, structured receipts, audit logs, and reviewer-read
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceProvides SSH access to a remote machine with manual session approval, automatic termination, and inactivity timeouts, enabling secure command execution via Claude.-
- FlicenseNot gradedqualityDmaintenanceLease governed AI agent instances without hand-built runner queues.-
- AlicenseNot gradedqualityCmaintenanceEnables permission-preserving access to DefectDojo OSS via MCP, using the caller's own API token, with read tools, deterministic analytics and reporting, plus optional gated write and history tools.2AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to asynchronously submit tasks to a persistent coding agent already running on a development machine, disconnect, and retrieve results later through a secure, policy-controlled gateway.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tarous89/intel_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server