NetworkX Graph MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_state_graphC | Create a new state/decision graph (directed, cycles allowed). |
| delete_state_graphC | Delete a state graph. |
| list_state_graphsB | List all available state graph files on disk (memory resets each session, so this scans for YAML/JSON files in graphs directories). Returns file paths that can be imported. |
| get_state_graph_infoC | Get graph metadata and stats. |
| add_nodeC | Add a node (action/decision/verification/loop/success/failure). |
| update_nodeC | Update node properties (label, phase, tool, properties). |
| remove_nodeD | Remove a node. |
| get_nodeD | Get node details. |
| list_nodesD | List all nodes. |
| add_edgeC | Add an edge with order and optional condition. |
| remove_edgeD | Remove an edge. |
| get_edgesC | Get edges (optionally filter by node). |
| set_edge_orderC | Set execution order for an edge. |
| set_edge_conditionC | Set condition label for an edge. |
| get_node_edgesC | Get incoming/outgoing edges for a node. |
| bulk_add_nodesB | Add multiple nodes at once (parents before children). |
| bulk_add_edgesC | Add multiple edges at once (with order/condition). |
| export_graphC | Export graph to YAML or JSON file. |
| import_graphC | Import graph from YAML or JSON file. |
| visualize_graphB | Render graph to PNG file (saves to disk, not base64). |
| validate_graphC | Validate graph structure (cycles allowed, warnings only). |
| get_graph_statsC | Get statistics: node counts by type, edges, phases, decision points, loops. |
| find_pathC | Find shortest path between two nodes. |
| get_execution_sequenceA | Get nodes in execution order from a start node, following edges by order attribute. Stops at first decision node by default. Returns sequence of nodes with their details. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 24 tools
Most tools have distinct purposes, such as add_edge vs. add_node or get_edges vs. get_node_edges, but some overlap exists, like get_graph_stats and get_state_graph_info both providing statistical insights, which could cause mild confusion. The descriptions generally clarify differences, but the overlap in statistical tools is noticeable.
Tool names follow a consistent verb_noun pattern throughout, such as add_edge, remove_node, and validate_graph, with no deviations in style or convention. This predictability makes it easy for agents to understand and use the tool set without naming confusion.
With 24 tools, the count is borderline high for a graph management server, as it includes many specific operations like set_edge_condition and visualize_graph that might be consolidated. While comprehensive, it feels slightly heavy compared to typical well-scoped sets of 3-15 tools, potentially overwhelming for agents.
The tool set provides complete CRUD/lifecycle coverage for graph management, including creation (create_state_graph), reading (get_node, list_nodes), updating (update_node, set_edge_order), deletion (delete_state_graph, remove_node), and additional utilities like import/export, validation, and visualization. No obvious gaps exist for the domain.