nvidia-cumulus-mcp
Allows querying network configuration and state from NVIDIA Cumulus Linux switches via the NVUE API, providing read-only tools for platform, system, interfaces, VRFs, BGP, and more.
Click on "Deploy 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., "@nvidia-cumulus-mcp show me the list of interfaces"
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.
NVIDIA Cumulus MCP Server
MCP server that integrates with the Cumulus Linux OS. This application was implemented using FastMCP and NVIDIA's NVUE API.
This application was developed forCumulus VX (Virtual Experience) 5.4.0. It has not been tested on actual hardware or the latest version since the simulator has since migrated to the NVIDIA AIR cloud sandbox.
flowchart LR
user["User / MCP client"]
server["nvidia-cumulus-nvue<br/>FastMCP server"]
tools["Read-only MCP tools<br/>platform, system, interfaces, VRFs, BGP"]
client["NVUEClient<br/>HTTP GET + basic auth"]
cumulus["Cumulus VX or switch<br/>NVUE API /nvue_v1"]
user -- "MCP over stdio" --> server
server --> tools
tools --> client
client -- "HTTPS GET :8765" --> cumulus
cumulus -- "JSON response" --> client
client --> tools
tools --> server
server -- "tool result" --> userQuick Start
Configuring a simulator (optional)
You can find a copy of Cumulus VX by downloading the qcow2 file from GNS3. Run the simulator and be sure to forward ports for SSH and the NVUE API
qemu-system-x86_64 \
-enable-kvm \
-m 2048M \
-smp 2 \
-hda cumulus-linux-5.4.0-vx-amd64-qemu.qcow2 \
-netdev user,id=mgmt,hostfwd=tcp:0.0.0.0:2222-:22,hostfwd=tcp:0.0.0.0:8765-:8765 \
-device virtio-net-pci,netdev=mgmt \
-nographicBy default the OS will have services like ssh and nginx enabled. In order to get the NVUE API connection to work, you need to modify your nginx config:
sudo ln -s /etc/nginx/sites-{available,enabled}/nvue.conf
sudo sed -i 's/listen localhost:8765 ssl;/listen 0.0.0.0:8765 ssl;/g' /etc/nginx/sites-available/nvue.conf
sudo systemctl restart nginxYou can confirm that this API is reachable from your host machine by doing
curl -u '<username>:<password>' -k https://localhost:8765/nvue_v1/interfaceConfiguring the target machine
Once you have a simulator or an actual switch to use you can run the MCP by doing:
uv sync
export CUMULUS_HOST=127.0.0.1
export CUMULUS_PORT=8765
export CUMULUS_USERNAME=cumulus
export CUMULUS_PASSWORD=cumulus100
export CUMULUS_VERIFY_TLS=false
uv run nvidia-cumulus-mcpAlternatively, you can add the MCP config:
{
"mcpServers": {
"nvidia-cumulus-nvue": {
"command": "uv",
"args": ["run", "nvidia-cumulus-mcp"],
"env": {
"CUMULUS_HOST": "127.0.0.1",
"CUMULUS_PORT": "8765",
"CUMULUS_USERNAME": "cumulus",
"CUMULUS_PASSWORD": "cumulus100",
"CUMULUS_VERIFY_TLS": "false"
}
}
}
}Related MCP server: gNMIBuddy
Configuration
Variable | Default | Description |
|
| Cumulus VX or switch hostname/IP |
|
| NVUE API HTTPS port |
|
| NVUE basic-auth username |
| required | NVUE basic-auth password |
|
| Enable TLS certificate validation |
| unset | Optional CA bundle path for TLS validation |
|
| HTTP timeout in seconds |
Tools
All tools are read-only and return:
{
"endpoint": "/nvue/path",
"data": {}
}Available tools:
nvue_get(path, include=None, omit=None, rev=None)get_platform()get_system()get_system_resources()list_interfaces()get_interface(interface)get_interface_counters(interface)list_bridges()get_bridge(domain="br_default")get_mac_table(domain="br_default")list_vrfs()get_vrf(vrf="default")get_routes(vrf="default", afi=None)get_ip_neighbors(interface, family="all")get_lldp_neighbors(interface)get_bgp_global()get_bgp_vrf(vrf="default")get_bgp_neighbors(vrf="default")
Development
uv sync
.venv/bin/pytest
.venv/bin/ruff check .
.venv/bin/mypyLive integration tests are opt-in and only issue NVUE GET requests:
RUN_CUMULUS_INTEGRATION=1 \
CUMULUS_HOST=127.0.0.1 \
CUMULUS_USERNAME=cumulus \
CUMULUS_PASSWORD=cumulus100 \
.venv/bin/pytest tests/test_integration_live.pyReferences
NVIDIA Cumulus Linux 5.4 NVUE API: https://docs.nvidia.com/networking-ethernet-software/cumulus-linux-54/System-Configuration/NVIDIA-User-Experience-NVUE/NVUE-API/
NVIDIA Cumulus Linux 5.4 OpenAPI specification: https://docs.nvidia.com/networking-ethernet-software/cumulus-linux-54/api/openapi.json
FastMCP tools: https://gofastmcp.com/servers/tools
Available Tools
18 toolsget_bgp_globalARead-onlyIdempotent
Get global BGP information.
Inputs: no named parameters. Returns: object
get_bgp_neighborsBRead-onlyIdempotent
Get BGP neighbors for one VRF.
Inputs: vrf. Returns: object
get_bgp_vrfCRead-onlyIdempotent
Get BGP information for one VRF.
Inputs: vrf. Returns: object
get_bridgeBRead-onlyIdempotent
Get one bridge domain.
Inputs: domain. Returns: object
get_interfaceCRead-onlyIdempotent
Get one interface.
Inputs: interface (required). Returns: object
get_interface_countersARead-onlyIdempotent
Get link counters for one interface.
Inputs: interface (required). Returns: object
get_ip_neighborsCRead-onlyIdempotent
Get IP neighbors for one interface.
Inputs: interface (required), family. Returns: object
get_lldp_neighborsCRead-onlyIdempotent
Get LLDP neighbors for one interface.
Inputs: interface (required). Returns: object
get_mac_tableBRead-onlyIdempotent
Get the bridge domain MAC table.
Inputs: domain. Returns: object
get_platformBRead-onlyIdempotent
Get platform hardware and software information.
Inputs: no named parameters. Returns: object
get_routesARead-onlyIdempotent
Get the routing table for one VRF.
Inputs: afi, vrf. Returns: object
get_systemCRead-onlyIdempotent
Get system information.
Inputs: no named parameters. Returns: object
get_system_resourcesARead-onlyIdempotent
Get system CPU and memory information.
Inputs: no named parameters. Returns: object
get_vrfCRead-onlyIdempotent
Get one VRF.
Inputs: vrf. Returns: object
list_bridgesARead-onlyIdempotent
Get all bridge domains.
Inputs: no named parameters. Returns: object
list_interfacesARead-onlyIdempotent
Get all interfaces.
Inputs: no named parameters. Returns: object
list_vrfsARead-onlyIdempotent
Get all VRFs.
Inputs: no named parameters. Returns: object
nvue_getARead-onlyIdempotent
Read any safe relative NVUE path with HTTP GET.
Inputs: path (required), rev, omit, include. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools target distinct resources (e.g., BGP global vs VRF vs neighbors), but `nvue_get` introduces potential overlap as a generic path-reader that could replicate specific get_ tools. BGP-related tools are well-differentiated by scope and neighbors.
Tools predominantly use `get_<object>` for singular and `list_<object>` for plurals, but `nvue_get` breaks the pattern with reversed order. The verb mix between 'get' and 'list' is consistent with CRUD conventions, yet the outlier reduces overall consistency.
18 tools cover a broad but focused domain of Cumulus network state retrieval. The count is slightly on the higher side but still manageable and each tool serves a clear purpose, justifying its inclusion.
The tool set is read-only (get/list/nvue_get), which is complete for monitoring but lacks any create, update, or delete operations. Missing common read operations like per-prefix route details, but core resources (interfaces, BGP, bridges, system) are covered.
Maintenance
Related MCP Connectors
MCP server for network documentation, generated by doc2mcp.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for Product Management
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA powerful integration server that combines Netbox's network infrastructure management capabilities with MCP (Multi-Cloud Platform) functionality.-
- AlicenseAqualityDmaintenanceAn MCP server that enables LLMs to retrieve structured network information, including routing, interfaces, MPLS, and topology, from devices using gNMI and OpenConfig models. It facilitates real-time network analysis, log filtering, and status monitoring through a standardized interface.1014BSD 3-Clause
- FlicenseAqualityFmaintenanceAn MCP server that integrates Nornir with NAPALM and Netmiko, enabling LLMs to orchestrate multi-vendor network infrastructure through natural language.52-
- AlicenseNot gradedqualityDmaintenanceMCP server for network operations that lets AI assistants interact with Cisco/Juniper network devices through safe, well-defined tools like compliance audits and configuration backups.MIT