Nimbus Copiloto MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Nimbus Copiloto MCP ServerWhat's the SLA status of ticket #1234?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Nimbus Copiloto — Helpdesk MCP Server
MCP server for Helpdesk Nimbus, the support ticketing platform of Nimbus S.A.S. It lets an AI assistant operate the helpdesk: search cases, view history, escalate, respond, and measure SLA compliance.
This is a learning environment. Nimbus S.A.S. is a fictional company. The repository exists to learn FastMCP by building a project with the shape and demands of a real one.
Quick start
# 1. Dependencias
uv sync
# 2. Sembrar la base de datos
uv run python -m backend.seed
# 3. Levantar el backend de la empresa (terminal aparte, déjalo corriendo)
uv run uvicorn backend.main:app --reload --port 8000
# 4. Correr las pruebas
uv run pytest -vWith the backend running: http://127.0.0.1:8000/docs
Related MCP server: tickiti-mcp
The MCP server
# Correrlo
uv run python -m nimbus_mcp.server
# Inspeccionarlo en el navegador
uv run fastmcp dev src/nimbus_mcp/server.pyIt is also available inside Claude Code thanks to .mcp.json. Check with /mcp.
Structure
mcp-test/
├── backend/ # API interna de Nimbus — NO SE TOCA
│ ├── main.py # FastAPI: tickets, clientes, agentes, KB, métricas
│ ├── db.py # Esquema SQLite
│ └── seed.py # Generador de datos de prueba
├── src/nimbus_mcp/ # El servidor MCP — aquí trabajas
│ └── server.py
├── tests/ # Pruebas
├── data/nimbus.db # Base sembrada (regenerable)
└── docs/ # Documentación del proyectoDocumentation
Document | What it's for |
Start here. What MCP is, how to get everything running, learning path | |
The long plan: 8 phases to AI Engineer | |
The company, the team, why the project exists | |
The domain: tickets, statuses, SLA, glossary | |
API contract consumed by the MCP | |
Phase 1 — the MCP tickets | |
Phase 2 — the copilot tickets | |
Where the last session left off |
The plan
This repository is Phase 1 of eight. The system grows in layers: MCP → copilot → evals → RAG → guardrails → observability → own models → production. The complete map is in docs/RUTA_AI_ENGINEER.md.
Versions
Python 3.13 · FastMCP 3.4.7 · FastAPI 0.141 · pytest 9.1
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 Servers
- AlicenseAqualityFmaintenanceAn MCP-compliant server that enables AI assistants like Claude Desktop to access and analyze Intercom support tickets with full conversation history.48Apache 2.0

tickiti-mcpofficial
AlicenseBqualityBmaintenanceAn MCP server that exposes the Tickiti helpdesk API to AI assistants, enabling ticket management and helpdesk operations via natural language.11MIT- FlicenseNot gradedqualityBmaintenanceMCP server for Nimbus Operations Copilot that enables AI agents to search help docs, customer data, invoices, and tickets, and propose refunds/tickets with human approval for writes.
- FlicenseNot gradedqualityBmaintenanceMCP server that provides IT support tools to search known incidents, check ticket status, and create ticket drafts, enabling an AI assistant to help users with IT support queries.
Related MCP Connectors
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
MCP server for AI access to Swagger by SmartBear.
An AI concierge that turns static forms into adaptive AI conversations. From any MCP client.
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/ruben-salas20/nimbus-copiloto'
If you have feedback or need assistance with the MCP directory API, please join our Discord server