Topolograph

You run the Topolograph MCP Server to connect AI agents with the Topolograph API for real-time network analysis, graph management, event monitoring, and path calculations for OSPF and IS-IS. This server exposes a stable MCP interface you can query to retrieve graphs, inspect nodes and edges, monitor events, and compute shortest paths with optional backup paths.

How to use

Start by running the MCP server locally or as part of your stack. You can connect through a standard HTTP MCP endpoint or launch the server locally for direct, inline usage.

How to install

Prerequisites: Python 3.8+ and pip must be available on your system.

pip install -r requirements.txt

Additional configuration and usage notes

The MCP server provides two connection methods you can use. The HTTP endpoint is typically hosted at your local or remote server and is accessible via the /mcp path. You can also run the server locally in stdio mode for direct control from your development environment.

Available tools

get_all_graphs

List available graphs with filtering options

get_graph_by_time

Fetch specific graph by time

get_network_by_graph_time

Query network information by graph and time

get_graph_status

Check graph health and connectivity

get_network_events

Retrieve network up/down events

get_adjacency_events

Get node/host and link events

get_nodes

Query diagram nodes

get_edges

Query diagram edges

get_shortest_path

Calculate shortest paths between nodes

upload_graph

Upload new graphs to the API